From 4a2bbe08596470052aa37d159c50434a9ae52a85 Mon Sep 17 00:00:00 2001 From: Ian Gulliver Date: Wed, 14 Oct 2026 21:06:30 -0700 Subject: [PATCH] Admin view in the web UI --- api/openapi.yaml | 31 ++- docs/operations.md | 8 +- docs/plan.md | 2 +- internal/agents/manager.go | 39 ++- internal/agents/manager_test.go | 2 +- internal/api/api.gen.go | 183 +++++++------ .../TestCommitIdentityHooksAndMCP.jsonl | 76 +++--- .../testdata/transcripts/TestImageInput.jsonl | 14 +- .../testdata/transcripts/TestInterrupt.jsonl | 32 +-- .../transcripts/TestResume-first.jsonl | 14 +- .../transcripts/TestResume-resumed.jsonl | 16 +- .../transcripts/TestStopHookBlocks.jsonl | 30 +-- .../testdata/transcripts/TestTextDeltas.jsonl | 14 +- internal/server/server.go | 1 + internal/store/queue.go | 5 +- web/dist/admin.js | 144 +++++++++++ web/dist/admin.js.map | 1 + web/dist/api.js.map | 2 +- web/dist/app.js | 2 +- web/dist/app.js.map | 2 +- web/dist/navbar.js | 8 +- web/dist/navbar.js.map | 2 +- web/dist/panes.js | 4 +- web/dist/panes.js.map | 2 +- web/dist/state.js | 1 + web/dist/state.js.map | 2 +- web/src/admin.ts | 242 ++++++++++++++++++ web/src/api.gen.ts | 20 +- web/src/api.ts | 1 + web/src/app.ts | 2 +- web/src/navbar.ts | 10 +- web/src/panes.ts | 6 +- web/src/state.ts | 4 +- web/style.css | 130 ++++++++++ 34 files changed, 838 insertions(+), 214 deletions(-) create mode 100644 web/dist/admin.js create mode 100644 web/dist/admin.js.map create mode 100644 web/src/admin.ts diff --git a/api/openapi.yaml b/api/openapi.yaml index dfc3ca0..5223a43 100644 --- a/api/openapi.yaml +++ b/api/openapi.yaml @@ -726,11 +726,18 @@ components: Status: type: object - required: [started_at, db_bytes, last_event_seq, projects, active_tasks, sse_clients, live_agents, running_turns, queued_turns, rate_limits] + required: [started_at, db_bytes, last_event_seq, projects, active_tasks, sse_clients, live_agents, running_turns, queued_turns, caps, rate_limits] properties: live_agents: { type: integer, description: Agent processes currently running. } - running_turns: { type: integer } - queued_turns: { type: integer } + running_turns: + type: array + description: Turns running now, oldest session first. + items: { $ref: "#/components/schemas/TurnRef" } + queued_turns: + type: array + description: Turns waiting for room under the caps, in the order they will start. + items: { $ref: "#/components/schemas/TurnRef" } + caps: { $ref: "#/components/schemas/Caps" } rate_limits: type: object description: The latest rate-limit status each vendor reported, keyed by vendor. @@ -741,3 +748,21 @@ components: projects: { type: integer } active_tasks: { type: integer } sse_clients: { type: integer } + + Caps: + type: object + required: [global, per_vendor] + properties: + global: { type: integer, description: Most turns running at once across all vendors. } + per_vendor: + type: object + description: Most turns running at once per vendor, keyed by vendor. + additionalProperties: { type: integer } + + TurnRef: + type: object + required: [session_id, task_id, vendor] + properties: + session_id: { type: string } + task_id: { type: string } + vendor: { type: string } diff --git a/docs/operations.md b/docs/operations.md index d97202f..6165d13 100644 --- a/docs/operations.md +++ b/docs/operations.md @@ -74,7 +74,13 @@ A turn's final message is its summary. When a turn ends normally (not an error, Running turns are capped globally and per vendor (`DefaultLimits` in `internal/agents/manager.go`). A turn that would exceed a cap leaves its session `queued`, with the message held in the `turn_queue` table; whenever a turn ends, a process exits, or a task is merged or discarded, the oldest queued turns whose vendor has room start. Interrupting a `queued` session cancels its queued turn. Idle sessions with a live process don't count against the caps. Whether a turn resumes the Claude conversation is decided by whether the session has ever sent one. -When Claude Code reports a rate-limit status of `rejected` and the turn then fails, the inbox gets a `rate_limited` item carrying the vendor's status (including when the limit resets) instead of a generic error. `GET /api/admin/status` reports running and queued turns and the latest rate-limit status each vendor sent. +When Claude Code reports a rate-limit status of `rejected` and the turn then fails, the inbox gets a `rate_limited` item carrying the vendor's status (including when the limit resets) instead of a generic error. + +## Admin view + +`GET /api/admin/status` reports `running_turns` (sessions now `running`) and `queued_turns` (rows of `turn_queue`, in the order they will start), each as session, task and vendor; `caps`, the global and per-vendor limits from `DefaultLimits`; `rate_limits`, the latest `rate_limit_info` each vendor sent since byre started, unchanged; and server counts (start time, agent processes, projects, active tasks, SSE clients, database size including WAL, last event seq). A turn's queue row is written before its session's `queued` state event, so a refetch triggered by that event sees it. + +The Admin view (a pane tab, also opened in the right pane by the navbar's **Admin** button) shows all of it: running turns against each cap, queued turns in order, both linking to their tasks, each vendor's rate-limit status with its reset time and per-window utilization, and the server counts. It refetches the status when a `session.created`, `session.state`, `task.*` or `project.created` event arrives, when an `agent.vendor` event carries a `rate_limit_event`, and when the SSE stream reconnects; other events only advance the last-event seq it shows. There is no timer, so the agent-process count can lag until one of those events, and the "in 2h 10m" beside a reset time is as of the last render. Agent activity becomes events with `agent_session_id` set: `user.message`, `agent.message`, `agent.thinking`, `agent.tool_call`, `agent.tool_result`, `turn.ended`, `session.state`, `session.model`, and `session.context`. Anything else Claude Code emits (rate-limit status, task progress, state changes) is recorded unchanged as `agent.vendor`. The one exception is partial output: each top-level `text_delta` is broadcast to SSE clients as an `agent.delta` event (`payload.text`, `seq` 0) that is never stored, and the transcript grows a live message from them until the finished `agent.message` replaces it. A `turn.ended` event carries `inbox_item_id` when its final message was filed as a `report` item. `session.context` records the context size whenever it changes: `used` is the last assistant message's input, cache-read, cache-creation and output tokens, and `window` is the model's context window from the turn's `result` (`modelUsage[model].contextWindow`), so it is 0 until the session's first turn after a server start ends. The task header shows the latest one as a percentage of the window, coloured green, amber from 70%, red from 90%. diff --git a/docs/plan.md b/docs/plan.md index 4b3dad0..0f94ed7 100644 --- a/docs/plan.md +++ b/docs/plan.md @@ -474,7 +474,7 @@ Record transcripts from the spike as the seed of the contract test suite. ### Milestones - **M0 — Skeleton.** launchd service, tailscale serve auth, SQLite schema, OpenAPI spec, projects, tasks, worktree create/delete, event log, SSE stream with resume, embedded SPA shell, basic server observability. - - **Status: done**, and running as a service on the Mac Studio. Observability is exposed through `GET /api/admin/status` only; the SPA has no admin view yet. + - **Status: done**, and running as a service on the Mac Studio. Observability covers queue state and vendor rate-limit status, through `GET /api/admin/status` and the SPA's Admin view; process liveness and stuck-process detection, adapter parse errors, and per-task snapshot counts and disk usage are not done. - **M1 — One agent end to end (Claude).** Sessions, streaming, messaging, the interface coverage for Claude, the `ask_human` MCP tool, turn summaries, inbox with all views and response types, web push notifications, restart-and-resume, concurrency caps. - **Done:** sessions, streaming, messaging, interrupt; `ask_human` with validation; each turn's final message filed to the inbox as its summary; inbox with global, project, and task views and every response type, answered as one batch and delivered to the agent as one message; restart-and-resume; global and per-vendor caps with queueing; rate limits as their own inbox state; the web UI (two panes, task switcher, transcript, inbox) with Markdown rendering; the session instructions from "Session configuration", given as an appended system prompt and a per-turn reminder; per-turn commits by byre; bouncing questions asked in plain prose. - **Not done:** web push notifications. Compaction is done, as a handoff into a fresh session; model switching is done, per message; image input is done, pasted or dropped into the composer and stored as blobs. diff --git a/internal/agents/manager.go b/internal/agents/manager.go index f13aa80..b81400c 100644 --- a/internal/agents/manager.go +++ b/internal/agents/manager.go @@ -282,27 +282,38 @@ func (m *Manager) LiveCount() int { } type Usage struct { - Running int - Queued int + Running []api.TurnRef + Queued []api.TurnRef + Caps api.Caps RateLimits map[string]map[string]any } func (m *Manager) Usage(ctx context.Context) (Usage, error) { - u := Usage{RateLimits: map[string]map[string]any{}} + u := Usage{ + Running: []api.TurnRef{}, + Queued: []api.TurnRef{}, + Caps: api.Caps{Global: m.limits.Global, PerVendor: map[string]int{}}, + RateLimits: map[string]map[string]any{}, + } + for vendor, n := range m.limits.PerVendor { + u.Caps.PerVendor[string(vendor)] = n + } - counts, err := m.store.CountRunning(ctx) + running, err := m.store.SessionsInState(ctx, api.AgentSessionStateRunning) if err != nil { return u, err } - for _, n := range counts { - u.Running += n + for _, sess := range running { + u.Running = append(u.Running, api.TurnRef{SessionId: sess.Id, TaskId: sess.TaskId, Vendor: string(sess.Vendor)}) } queued, err := m.store.QueuedTurns(ctx) if err != nil { return u, err } - u.Queued = len(queued) + for _, q := range queued { + u.Queued = append(u.Queued, api.TurnRef{SessionId: q.SessionID, TaskId: q.TaskID, Vendor: string(q.Vendor)}) + } m.mu.Lock() defer m.mu.Unlock() @@ -325,11 +336,6 @@ func (m *Manager) turn(ctx context.Context, sess api.AgentSession, task api.Task return m.start(ctx, sess, task, actor, text, images, api.AgentSessionStateIdle) } - err = transition(ctx, m.store, sess.Id, api.AgentSessionStateIdle, api.AgentSessionStateQueued, actor) - if err != nil { - return api.AgentSession{}, err - } - err = m.store.EnqueueTurn(ctx, store.QueuedTurn{ SessionID: sess.Id, Vendor: sess.Vendor, @@ -342,6 +348,15 @@ func (m *Manager) turn(ctx context.Context, sess api.AgentSession, task api.Task return api.AgentSession{}, err } + err = transition(ctx, m.store, sess.Id, api.AgentSessionStateIdle, api.AgentSessionStateQueued, actor) + if err != nil { + derr := m.store.DeleteQueuedTurn(ctx, sess.Id) + if derr != nil { + slog.Error("remove queued turn", "session", sess.Id, "err", derr) + } + return api.AgentSession{}, err + } + return m.store.GetSession(ctx, sess.Id) } diff --git a/internal/agents/manager_test.go b/internal/agents/manager_test.go index 656d9ba..f153557 100644 --- a/internal/agents/manager_test.go +++ b/internal/agents/manager_test.go @@ -753,7 +753,7 @@ func TestConcurrencyQueue(t *testing.T) { } usage, err := m.Usage(e.ctx) - if err != nil || usage.Running != 1 || usage.Queued != 1 { + if err != nil || len(usage.Running) != 1 || len(usage.Queued) != 1 || usage.Queued[0].TaskId != second.TaskId { t.Fatalf("usage %+v %v", usage, err) } diff --git a/internal/api/api.gen.go b/internal/api/api.gen.go index ad97059..504e154 100644 --- a/internal/api/api.gen.go +++ b/internal/api/api.gen.go @@ -312,6 +312,15 @@ type Blob struct { Id string `json:"id"` } +// Caps defines model for Caps. +type Caps struct { + // Global Most turns running at once across all vendors. + Global int `json:"global"` + + // PerVendor Most turns running at once per vendor, keyed by vendor. + PerVendor map[string]int `json:"per_vendor"` +} + // Error defines model for Error. type Error struct { Message string `json:"message"` @@ -458,19 +467,24 @@ type SessionCreate struct { // Status defines model for Status. type Status struct { ActiveTasks int `json:"active_tasks"` + Caps Caps `json:"caps"` DbBytes int64 `json:"db_bytes"` LastEventSeq int64 `json:"last_event_seq"` // LiveAgents Agent processes currently running. - LiveAgents int `json:"live_agents"` - Projects int `json:"projects"` - QueuedTurns int `json:"queued_turns"` + LiveAgents int `json:"live_agents"` + Projects int `json:"projects"` + + // QueuedTurns Turns waiting for room under the caps, in the order they will start. + QueuedTurns []TurnRef `json:"queued_turns"` // RateLimits The latest rate-limit status each vendor reported, keyed by vendor. - RateLimits map[string]map[string]interface{} `json:"rate_limits"` - RunningTurns int `json:"running_turns"` - SseClients int `json:"sse_clients"` - StartedAt time.Time `json:"started_at"` + RateLimits map[string]map[string]interface{} `json:"rate_limits"` + + // RunningTurns Turns running now, oldest session first. + RunningTurns []TurnRef `json:"running_turns"` + SseClients int `json:"sse_clients"` + StartedAt time.Time `json:"started_at"` } // Task defines model for Task. @@ -510,6 +524,13 @@ type TaskCreate struct { Title string `json:"title"` } +// TurnRef defines model for TurnRef. +type TurnRef struct { + SessionId string `json:"session_id"` + TaskId string `json:"task_id"` + Vendor string `json:"vendor"` +} + // Unmerged defines model for Unmerged. type Unmerged struct { // Commits Commits on the task branch that aren't on the default branch. @@ -1662,79 +1683,81 @@ func HandlerWithOptions(si ServerInterface, options StdHTTPServerOptions) http.H // const string: with thousands of chunks the chained `+` fold is several // times slower for the Go compiler than parsing a slice literal. var swaggerSpec = []string{ - "7Fxbbxu5kv4rRO8CToC27DkzZ4HVPGWSzMAHk1lvnCAPZwcC1V2SOO4mOyTbitbwf19UkeyLmi3JGsvJ", - "wexTlL6wi1Vf3Yu+TzJVVkqCtCaZ3icaTKWkAfrPW62Vxh+ZkhakxZ+8qgqRcSuUvPjDKInXTLaCkuOv", - "f9ewSKbJv120q164u+bCrfbw8JAmOZhMiwoXSabuM5MEb/hncalXS5D2BowR7iOVVhVoKxxpmQZuIZ9x", - "ImqhdIm/kpxbOLeihCRN7KaCZJoYq4VcJg9p8858g+8Mbos8erlUORR4p0/0e/hcg7GQM3rgRwZlZTes", - "BC4NsytgdyBzpc8My2HB68JOYiRpVQCuDbIuk+k/E1FWBZQgLejk98jzxnILQ2I+11AjJfRxzmytJROG", - "rbmwQi7ZQmnG2UIDMFMoy2qZgyYiMyWzWmuQ2YZlvDJIZENLXiAb3dpJmuhaSiQjJcgUYCEf0pgmX85x", - "gfM7riUvUVj/7InyBndw5ZYeXP/v8K3BnffNxwe3XrfUPKSJ5eZ2NiJKJ5Iuv7OC1zlEWe0enhn3pfiS", - "KEH4XAsNueNY0hLQfC5AKLZkkKhHQg+jaRfkLYVq/gdkFil8ZS3PVqVXzC394B4bETaAzGeFkNC5KaSF", - "JWhSg5IvIxCjy1OWc8vZx/e/RtF8K2Te5e5C0J5ysVgkYWH8L19qXnpWIQskr8xK2SRNal1EhVGCLrkT", - "QZ8sv9iUvXNPMKNqnUGUvIrb1XAFJHLKNFTqXEPBrbgDhk/G9RXN25CGxWLKlsIyDXcCRcs0l8s4EWGz", - "Yxg1lmu7Qzy78I3c2wtSElIMTj8Vah4BkjP9M/f4/bhVPbUljulaj7jHKU/j2/rbLcEYj//d3w8PRte+", - "i+okz6z75GDDHG3ablNzHKODRkZ0YVMo3r3Xkl9phT9HEQqfewQIaf/jh/bjB2F1i5m4pCc29WxqSdwr", - "yp9FAa9XqHERnue5QDU1cW2aC8l1F4RzpQrgMqEgpYAdr6oin8Utigb0fPmUPCw+wuawUBro/+7mTvsU", - "9fq16VpWnufkJ0uVi4Wgn0Suc9Tu+/4Ts4xYE/HV21Kg7zdfSzu86zKjYdqYKN6guR8IouI2W41AMbrt", - "OHFumdinr+RcfbmyUEZAcIh6zQuV3eLvKBiOUb6RD217SYojETm44Upp9IOBViArlSaaW5gVohTRoKuv", - "z4PQkFafMjKWX2zKwqWUrVebGe0b8pQpesWkTEOmyhJkDvnMXUwZb2INM2GOzCnD5dgLRPVCSF4wbxOZ", - "WoQg1K64ZbQSk8izoti8nLDe7qaM/pmw7h6nPnxOO1fdl5qwGm+cuxsOsS9Tv9L/yCSNWTWhtLCbLuv9", - "3pM0WfooDO4ErJM0WWxEnM+7baMGo4q7R+KkeWnEHfZyMmGhNPtSLdKF9/41ssRuTa4137goRKn/hXxW", - "SyuKwylt0o+9H6fIfF+8YlcaeH54aN1hfjfOHqh3d+XGrTTy76h618mEQLyj6V3Wj5ocx+Z8aHX+pNhe", - "Ex0U/Ap55V7/bluSW1w6mFwTc5Wtih9McScFiaDsGKOZQyHuQD+NqcU9jIFPjSdITjseqxxoDeMw96Hz", - "waL/gC9gPG9AH6gaYaf+Jf/RtCfUvYFUDH/PAJPDpNR3a+76lClJ7gY9Q3BrZya4spEErC/c/rru7pSt", - "VyBpVSSOaeBVBVzTio9DwxbZdgXaBYbkPA1Iy6yiC2TGoiQfCaBtnDQQofX2AuCD/2pwll4UqdtEEjhJ", - "Gb0phTFRh9nxBr21AFfi0qxR19s16LepK9AG8pFY550LM8YASnUGM+Q95rdM5IYttCpZXaHdx2vpUAqM", - "G+aWYbxQcmlEDo3QJl7dzA5lb8E9Uj58h5epMGdXwrhgicucFdyCRlSbCfuEGBSW5WKxAO3pRiq8qzsz", - "rvaYdi8ysxY2W4HpJh0hMBOG9jo5HLDv+IbNwRc3SSkCXzSwpbgDGVlsC3i0cgxu186fP0t111dhZ3PN", - "5UgiMmKCMJkaictKZcduVWp2WGJDGknf6L42ILj53OPKHJ7FY7qyY28Hb2BAe4wOX7D9GjpbaVVWx2pt", - "LAEoK3tAvuqei/KiSecH9SFxBzMMbEdqDvl8Nt9Y9/QB9ZeCGzuDOxcdH1q0wfBrRhyNyIOK78jRDIwB", - "w1zzwBYb5rsDk+iaPnAf2ZXrMMzQBo480SaBvaIOL657DBxwuk/8hxWQfTV2mDwy4NnKJ5c+v8Wc+BY2", - "kLP5xt+ZxBJLv/Nd9BsDs6wQgaeRByzXjzN42xW0doEOTAYQ6Igi7eOtT2QfBtt73BJZXz4xxH/g5naI", - "9zk3MPMV9WE5ZtxOZ4UyDa/6Iv4UwjbcFFtzw0rQS8iZ0iwXJuM6h/zwIO4Zu4xI5ixTZSki23KbcHGj", - "+Vxzs2LuUabcdr2zYI5rP3b9NQZrQKyQyq6EXKLVpAXjRcg9xd9hKZJQlPgt+FDOMfrA9iCiw9nEV2Gt", - "9tK7sGp76U27PppuYYu4D1srfWs1wGMccb/EQEs3WNxeMW0R3KmaPsY7455c5drE1SMSkCE/zvFeA4FF", - "i3hHKUWSQ1hE5b0QxSMqFJ1Se8RrImuGFH/Q0ORogYHkrBcM7kBvHCgxD0BbvHT6uVtUxBr/vbCFUf6O", - "hBxjuNkOXumx2OIfpUd8pGdWBlfVZ8VrdyNobVdkVCnlGuTZiFLHPeueJkUj3T4dKEbjPumSiza3oD2x", - "wOD+gmlSS7c3CzlzfQXDhMyKmszqVNZFgTZOGmTGKFWdVYa0XXO7Mmwt7IrFv9YDUowrWxIM0gjc6NHX", - "72x0CYuK3Bdk+uLOhakKvpmNBtNLYWdQclGM3h19tVBLIfej1D2W9knpLN2lYWxjH6s8qihHU79F44HE", - "PBCAFqqjo8l8o4HmJ7SbBkouJ5eTS1cfAskrkUyT7yeXk+9dh2hFdF/wSlzwvBTyovVaSyD3ivujGaar", - "PJkmv4C9Cea7V7X92+Xlk40/+S9E5p9uQN+BZivghXW2u8ZsfYLPPqRuH/NCzZ2PUCYSINxYpTHx8ek5", - "FRZqA6gtPGT/E4YB8FzlGybciJLma/f8jwytEgoCb+VgIUOda4wCRZNEWVkby+bArn/7JWX/uH77S8p+", - "ufoZw6tPML+esFeWlcpY9nf2TvzkOjF9Xn9scrjEwQOM/Unlmy0+E1kXS7HoM7gJwXwPMuYo3Kt/VLA8", - "9t1KHv3qGubVY9/t6YnVNTwMYPjdk8GQOB8BIWLDIIpyhliboHL94OAfW66hL4z1pckP331/8NNbwL64", - "x3+u8oddKtpgZqeC/sWAMxQicvLMOJVNnR9F5fYsIiX3wv3hEeJCu6p5CRY0xuz3CXql0JR39j9xMky2", - "0Zx29rS9g98DDChF7VromIk8p6KPe3TC3mLGTv85M0zkaLlwowY+/+jG1LyVo2kcDDj/cfNfv03cfw3j", - "Cwua/cqNPacr51dv2AvlpiLdvc816A1rtv2SSp4a0L+ikrjqKqbJgaKItbuxGnjpPpnEebgCnlNs5bnY", - "IylJY4AYK948pH5NIr1dkvbzyKV+36tpFr5YJ7dzQ9vsw3cvWJ1c3Ks9XyfkXH0ZhQI1FKgtY1K2EssV", - "GMtCc5cthDaWvWiGGpbcQspcWz9li414SdVyyVSR44v0/IT9LAqUCpNca7UmECgJHgJWMc58YnhmGA3T", - "Yuh+ZhguG5P7r8JYInRE6FsC6mWd4ywcEW/bCX/0q6HpfZjv6Hb2x1b02cDMTxjEiGrGag4A2W5Hd3hX", - "nQaDBinrEJTvuM0oH6Wlnfm0KxCaNYRO2BuXmBlEBgagKaul3697bwjni94+40HcK+qGGdfT1KxE++LI", - "EJIumnpeCqqjT1h4WFPhslcFx0ebURyZ4SJkHPMCKIaTvmmK1jKMQjTdU9fZqWVozcXQ7UceAsDHo7jj", - "w5TeaMVBIdLXRg763ppSqBYEjw6hHuGT8en/PCLgcnC8RxL3BFzt9k+YFnV4HOcpNeCbMKbVwtPEMI4t", - "x8UwLgke4+Y7OCUbqTIxwsGMFwWqeG2AjtkgI+oIka4A4Ol8epXu1BhOoNDHMieorGfO4zS21apuhyuK", - "AIwIrtvey+mNV2iuH2C6XhVFiG9MAIj3UP1NuFpqWPk0MOl3rJ85O26YFgeLhHVg1BNg5eLe/9pjh7v8", - "PpGG7Nl3f89PbXMbLhxndmPsvGia6KPK+MG3PU+vidT9PDCCaNMM2kGKkGvzlG+K/+lIGOs01zQdjjPT", - "bUs1HaCmuNhuedjwiJmfD+7U2ClsT6df9MyGx2Fk3OogI08cULYGyo+SmYt7/2uPgQqndE9ooHqngcfK", - "l+72ibSkYcVxVirGU6KK+wG4UxEwpqavzK3TUcoL25FCl0a6I8MrLnO1WLAXS8WLlOWQ0fFGk9LUDOAV", - "njOQuUkpEW6zyJRRs+2ln2KkViMNObqHuwOLwrDmQDGZCE6ID7d9M9Tw0jdMqQ1B45M09NIm6Q253FUC", - "XS0odD8ieexrx/5R+P7tWeEbqCc2rblhfqaHKapF1pBPnitHjIJVSAta19XXgetbmTu4+pEzYtPQRVwF", - "Ir8RoTZMI4k2hxu+riS9SpivIsgbp7ROyR3Wnf4K0+9UBgMQWo5op4YCvwGZ+4HwEwUF/XHzg+KC58UY", - "MXHVGoxvtPBEAe3FPf6zJ55oIrwTBRO7gq1OoPXUEYTb+XHhQ595F1k7NBZtkrxtB6uE7EbiTfj9opl0", - "Sf3YFVWx6ZebQZBWc9dEwf1CRn9KZLIUViyl0vAS3SxnuFhKDpxryFtfXLZzajsG1MZi/xSdHq1lhMzA", - "TTK64wZkG8I2zgxTa8mEzOELBhJSWWZVna3ihWuPrTByNxDaVoQUJuysChv0hUhpLAY+fmPtVlNmatwd", - "MoYKSqEMH9qUK+A03hbtxeBOkz029aQ6EfgSUY1r0OcY0VHg962Vtp9Z+XJ/wD2qeVRTlHQon2brECRK", - "AoXDbA52DSAZpwE7pwVNLrzsgXMyBt437q+pHNBV9EN8h294rL/oxiz/9DpeIH96neYvL3wtXWn+ysFY", - "EYfbbPVX1xGa0T4swjzmu2Ph5Xso1V2/+tQOHcs8OCC046q2ZLuFXDqv4p/XkCntnKCb7GAaSi4i2Yaf", - "RP+a8UozbH9c5PI0wdy+8Z0Oc6E7fsOZgc/p1izGNTrM+YZV3Bg6rkDHdozFZ9mcZ7fkX/H9SXTuArm1", - "c+LmCaZjRiwTHYHpLVXyL6Ksy2T63eXlJR3l9/89auTmCYrR7m8THVCN/lhh3OPOSHmhvQhB2t8vL19+", - "+0EyxWXPb4F8gtsUrVxBzZ3w9eeRzoWMFsaaP5KSsvlGh7M+I9ZMSKsotOgfBRoPqRfc2POF0muufS2l", - "fTZbQXaLBtEqJqyfkdIdWxozolSJ4/q2pc8ft5qw3/xZI2FYVRsMx9l7WNQGU4QVhkLtXyn0Z8s6Za5I", - "5E7HXuJ29nmTbXc+Ym+N7ttOvi8CCp9fO5qys4ez1w4VGLsDwQ7xW6kkZaequEMEcblhmZKLQmTWjatr", - "WIIkHMkl8z8hd7XpCbvpnCH25HSL4ZSEmlCuCuWotT+Vv6ITdRKeAthX8v9h/RSwDtXOnY3fm/DQc7jb", - "Pu8P6wH3NCNsaStK+nac7746r+xvZKwehdpqyAcK2zm23+/lxGv+rjLbLfg/fRG4//cLnrk5fIgCd1pm", - "/xq6WneOT0aThk8UGkWgslJF7k8vIjRG3UWuwMgzG62kNIc3Tzl2Fr4xNnrm74ezjZN/2RrAw8P/BQAA", - "//8=", + "7Fzdb9u4lv9XCO0CaQHFydw7d4H1PHXaziAX09lu02Ie7g4MWjq2OJFIlaTieoP874tzSOrDomwnE6e9", + "uPsURx/k4eHvfB/qLslUVSsJ0ppkfpdoMLWSBuift1orjT8yJS1Iiz95XZci41YoefGHURKvmayAiuOv", + "f9ewSubJv110o164u+bCjXZ/f58mOZhMixoHSeZumlmCN/yzONSrNUh7DcYIN0mtVQ3aCkdapoFbyBec", + "iFopXeGvJOcWzq2oIEkTu60hmSfGaiHXyX3avrPc4juj2yKPXq5UDiXeGRL9AT43YCzkjB74gUFV2y2r", + "gEvDbAHsFmSu9JlhOax4U9pZjCStSsCxQTZVMv9HIqq6hAqkBZ38HnneWG5hTMznBhqkhCbnzDZaMmHY", + "hgsr5JqtlGacrTQAM6WyrJE5aCIyUzJrtAaZbVnGa4NEtrTkJbLRjZ2kiW6kRDJSgkwJFvIxjWny5RwH", + "OL/lWvIKN+sfg628xhVcuaFH1/87zDW686GdfHTrdUfNfZpYbm4WE1vptqTP76zkTQ5RVruHF8bNFB8S", + "dxA+N0JD7jiWdAS00wUIxYYMO+qRMMBo2gd5R6Fa/gGZRQpfWcuzovKCuSMf3GMjwgaQ+aIUEno3hbSw", + "Bk1iUPF1BGJ0ec5ybjn79OGXKJpvhMz73F0JWlMuVqskDIz/8rXmlWcVskDy2hTKJmnS6DK6GRXoirst", + "GJLlB5uzd+4JZlSjM4iSV3NbjEdAIudMQ63ONZTciltg+GRcXlG9jWlYreZsLSzTcCtwa5nmch0nIix2", + "CqPGcm33bM8+fCP3DoKUNikGpx9LtYwAyan+hXv8blqrnloTx2RtQNzDhOc1r814tetSLXlE279TxpJa", + "NcyrQcYtUzIDxjOtjGG8LL3KN719721cDXrRKSCe5wLH5uX7AQHj944mpAbtKUjZDWwhZ8utv9CjKHBg", + "h51+4QMyY2xrXYIh3yowxquN/dsWHoyOfRtVZTyzbsoRTjiagv0a+nH4DIosokK2peL9ex35tVb4c1Kw", + "4fOAACHtf3wfRcq0iO8wE4f0xKaeTR2JByXgJ1HC6wIVVYTnHp4TmFwKyXVfdpdKlcClw2sJe15VZb6I", + "K2IN6DDkc3JM8BG2hJXSQP+7m3vVetRZakzfIPE8J/eiUrlYCfpJ5Dr/xs3vp1hkxJqIi7O7CzR/O1va", + "412fGS3TprbiDVrJ0UbU3GbFBBSjy44T54aJTX0ll+rLlYUqAoJjxGtZquwGf0fB8Bjhm5ho17kg9xuR", + "gwuulUb3IdAKpKXSRHMLi1JUIuqrDuV55FHT6HNGNuaLTVm4lLJNsV3QuiFPmaJXTMo0ZKqqQOaQL9zF", + "lPHWRTMz5sicMxyOvUBUr4TkJfM6kalV8N1twS2jkZhEnpXl9uWMDVY3Z/RnxvprnLcGoLvqZmqjEbxx", + "7m44xL5M/Uj/I5M0ptWE0sJu+6z3a0/SZO2dV7gVsEnSZLUVcT7v140ajCpvH4iT9qUJL2IQygoLlTkU", + "oZIsfPCvkSZ2Y3Kt+dY5b0r9L+SLRlpRHk9pG7UdnJwCmkNuni008Pz4iKTH/H54MhLv/sitWWn3vyfq", + "fSMT4peepPdZP6lyHJvzsdb5k9v2muigmEHIK/f6d7s7ucOlo8k1MVPZifjRFPcitwjKHqM0cyjFLein", + "UbW4hinwqem40knHQ4UDtWEc5j7iOHrrP+ILGAYZ0EeKRlipf8lPmg429aAjFcPfM8DkuF0amjV3fc6U", + "JHODliGYtTMTTNlE3Drc3OG47u6cbQqQNCoSxzTwugbuIqKHoWGHbFuAdo4hGU8D0jKr6AKpsSjJjwTQ", + "Lk5aiNB4BwHw0c8ajKXfitQtIgmcpESIqYQxUYPZswaDsQBH4tJsUNa7Mei3aWrQBvIJX+edczOmAErp", + "GTPm/Y+lWjKRG7bSqmJNjXofr6XjXWDcMDcM46WSayNyaDdt5sXN7BH2DtwTWdd3eJnymbYQxjlLXOas", + "5BY0otrM2G+IQWFZLlYr0J5upMKbujPjUrZp/yIzG2GzAkw/6AiOmTC01tnxgH3Ht2wJPidMQhH4ooGt", + "xS3IyGA7wKORY3B77+z5syTFffJ6sdRcTgQiEyoIg6kJv6xSdupWrRbHBTYkkTRH/7URwe10D8sOeRZP", + "ycqetR29gBHtMTp8nvtryGytVVU/VmpjAUBV2yPiVfdclBdtOD/KD4lbWKBjO5FzyHyub58hoHwgAn65", + "WG6tG/mIXE3JjV3ArfOkj03woKu2IO5H9o7qG8j9DIwBw1x9xpbbkPCbSC86xE5wwBVxFpQ4HE/5kfKJ", + "/WqRVoibrkzEa5My4Uy70v7ylm1EWTLKWA9wso/PONcHWMXQ08Ws5ogUaQeMncUUQObA2HGsy4BnhY+F", + "fTiOIfzhbGlb/drPwpCSlWqTMlXmSEQwMCuhzZOwyRhYZKUI6BlvNm3Ig8zAbl6xG6AnECOw90CXDqVw", + "SOQQ8Lus3AGnl9YhGmLq4CM3N2NlsOQGFr5KM85VTRuxrFSmZdlwa38LPi2ujW24YRXoNeRMaZYLk3Gd", + "Q368h/uMlWskc5GpqhKRZblFOKfafG64KZh7lCm3XG9JmePaD31nBj1ZIFZIZQtEvFWOK/EM7YHM+DhP", + "S2BK/BK8n+sYfWTJGdHhDMarMFZ36V0Ytbv0phsfRU7YMm7gN0rfWA3wEC9lmH+hoVss7o6YdgjupZQf", + "4rrgmlxa38TFI+KtIj/O8V4LgVWHeEcpudljWET3eyXKB6RvenWIiLZD1kTUrYY2gA0MJE9mxeAW9NaB", + "EoMk1PxrJ5/7t4pY4+cLS5jk74Q/NoWbXc+eHosO7tX+aOQDWfjjuh4OVZP6mcDdLoYYtZ+kl89I1bgK", + "Zny4ca/djaBj+gCjpDfXIM8mVFDc8TlQb2qxOKQDQWfclC5O7MJEWhMLcBgOmCaNdGuzkDNXIjJMyKxs", + "yAjMZVOWqJGlQWZMUtUbZUzbe24LwzbCFiw+2wD2Ma7s7GzYjcCNAX3DIlWfsOiW+9zacLtzYeqSbxeT", + "cdFa2AVUXJSTdydfLdVayMPodY+lQ1J6Q/dpmFrYpzqPivWjqd8tsh9HzD0BaKV6GiVZbjWQMGrXD5dc", + "zi5nly7VB5LXIpknf51dzv7qin0F0X3Ba3HB80rIi87GroGcAVwfdfFd5ck8+RnsdTA2gwT8Xy4vn6wB", + "0M8Q6QC8Bn0LmhXAS+ssTWM4OhP39DCtY1mqpbNoykTcmWurNMawPtNCUUxjAKWFh0TOjGFwsFT5lgnX", + "pKf5xj3/A0OthBuBt3KwkKHMtUqBXGCirGqMZUtg73/9OWV/f//255T9fPUTOoO/wfL9jL2yrFLGsr+x", + "d+JHV1Qb8vpTG44nDh5g7I8q3+7wmci6WIvVkMGtw+jLyTGz5l79o4b1Y9+t5aNf3cCyfui7AzmxuoH7", + "EQy/ezIYEucjIERsGERRzhBrMxSu7x38Y8O19IXG1jT5/ru/Hv30DrAv7vDPVX6/T0RbzOwV0H8x4Iw3", + "ETl5ZpzIps6OonB7FpGQ+839/gHbhXpV8wosaIww7hK0SqG/wun/xO1hsovmtLem3RX8HmBAcXVfQ8dU", + "5Dnl79yjM/aWZ4X758wwkaPmwoUa+PyDa9T0Wo4aq9A9/vv1f/06c/8axlcWNPuFG3tOV86v3rAXyiV8", + "3L3PDegta5f9krLXGtC+opC4RDnG9oGiiLa7thp45aZM4jwsgOfkW3kuDkhK0hggpnJr96kfk0jvhqT1", + "PHCo3w9KmoUv1u3buaFlDuF7EKxuX9yrA1sn5FJ9mYQC1YaowmZSVoh1AcayUKd3eSb2ou1PWXMLKXMd", + "GilbbcVLKnzIkJ9yeSn2kyhxV5jkWquNS/RJ8BCwinHmw9gzw6idHF33M8Nw2Ni+/yKMJUInNn1ngwYx", + "8jQLJ7a3i1Ye/GroXzjOdvSbNKZG9NHAwjeLxIhqO6SOANl+Q3d8gwT1eI0C7DEo33GbUfRMQzv1aQsQ", + "mrWEztgbF5gZRAY6oClrpF+ve28M54vBOuNO3CsqbBpXntasQv3iyBCSLppmWQkKU2csPKwpqTsoaOCj", + "bVeVzHAQUo55CeTDSV//Rm0ZulraQrgr0jUyVFlj6PbdKwHg017c492UQZfMUS7S10YO2t6GQqgOBA92", + "oR5gk/Hp/3yEw+XgeIckHnC4uuWfMCzq8TjOU+qlaN2YTgpP48M4tjzOh3FB8BQ338Ep2UiZiQkOZrws", + "UcQbA3TQDBnRRIh0CQBP59OLdC/HcAKBfixzgsh65jxMYjup6hcgowhAj+B9VzA6vfIKfRJHqK5XZRn8", + "GxMA4i3UcBEu8xtGPg1Mhs0Hzxwdt0yLg0XCJjDqCbByced/HdDDfX6fSEIOrHu45qfWuS0XHqd2Y+y8", + "aPshJoXxo6/Vnl4SqVZ7pAfRhRm0ghQh18Up3xT/0wk31kmuaSscZ6ZfRGvrVW1ysVvyuOARUz8f3bnJ", + "U+ieXnXrmRWPw8i01kFGntih7BSUr4WZizv/64CCCufUT6igBufhp9KX7vaJpKRlxeO0VIynRBX3vYyn", + "ImBKTF+ZGyejFBd23aEujHSH5gsuc7VasRdrxcuU5ZDRAV+TUkcR4BWeM5C5SSkQ7qLIlFGx7aVvSKVS", + "I/Wruof7vafCsPZIPakITogPt30x1PDKF0ypDEGdsNSp0wXpLbncZQJdLihUPyJx7GvH/kn4/uVZ4Ruo", + "JzZtuGG+EYkpykU2kM+eK0aMglVIC1o39deB61uZO7j6jkBi09hEXAUiv5FNbZlGO9qeU/m6O+lFwnyV", + "jbx2QuuE3GHdya8ww0plUACh5Ih6arzh1yBz39t/IqdgeHLgKL/geTFGTCw6hfGNJp7Iob24wz8H/InW", + "wzuRM7HP2eo5Wk/tQbiVP859GDLvIuta3KJFkrddG5iQfU+8db9ftJ0uqW8Soyw2/XI9CNJq7ooouF7I", + "qD16thZWrKXS8BLNLGc4WEoGnGvIO1tcdV11e9rppnz/FI0ejWWEzMD1XbqTI6QbwjLODFMbyYTM4Qs6", + "ElJZZlWTFfHEtcdWaBAcbdqOhxT6Aa0KC/SJSGksOj5+Yd1SU2YaXB0yhhJKIQ0fypQFcGrGi9ZicKXJ", + "AZ16UpkIfImIxnvQ5+jRkeP3raW2n1n4cv+tgqjkUU5R0vcVqLcOQaIkkDvMlmA3AJJxarBzUtDGwusB", + "OGdT4H3jvid0RFXRN/Edv+Cp+qJrCv3T4/gN+dPjtB/R+Fqy0n6wYiqJw21W/KvLCHWUH+dhPmbeKffy", + "A1Tqdph96lqkZR4MEOpx1VjS3UKunVXxz2vIlHZG0HV2MA0VF5Fow/fNf01/pT0a8DjP5WmcuUPtOz3m", + "Qr/9hjMDn9OdXoz3aDCXW1ZzY+hwBR1porNEn9mSZzdkX/H9WbTvArm1t+PmCbpjJjQTHdgZDFXxL6Jq", + "qmT+3eXlJX2Vwf/7qJabJ0hGu89MHZGN/lSj3+POj/lNexGctL9dXr789p1k8sueXwP5ALdNWrmEmjus", + "7U9PnQsZTYy137tJ2XKrw8mkCW0mpFXkWgwPLk271Ctu7PlK6Q3XPpfSPZsVkN2gQrSKCet7pHRPl8aU", + "KGXiuL7p6POHw2bsV38yShhWNwbdcfYBVo3BEKFAV6j7Tmc4NtiluSKeOx3SievZ5w223fmIgzm6bzv4", + "vggofH7paNPOHs5eOlRg7B4EO8TvhJIUnarylr4FKLcsU3JVisy6dnUNa5CEI7lm/ifkLjc9Y9e94+Ce", + "nH4ynIJQE9JVIR218R9YKOj8n4SnAPaV/H9YPwWsQ7Zzb+H3Ojz0HOZ2yPvjasADyQhL2vGSvh3jeyjP", + "K4cLmcpHobQasoHC9r7AMKzlxHP+LjPbT/g/fRJ4+CmKZy4OHyPAvZLZP4esNr3jk9Gg4TdyjSJQKVSZ", + "+9OLCI1Jc5ErMPLMRjMp7eHNU7adhTmmWs/8/XC2cfZPmwO4v/+/AAAA//8=", } // decodeSpec returns the embedded OpenAPI spec as raw JSON bytes, diff --git a/internal/claude/testdata/transcripts/TestCommitIdentityHooksAndMCP.jsonl b/internal/claude/testdata/transcripts/TestCommitIdentityHooksAndMCP.jsonl index b9701a7..fdc6460 100644 --- a/internal/claude/testdata/transcripts/TestCommitIdentityHooksAndMCP.jsonl +++ b/internal/claude/testdata/transcripts/TestCommitIdentityHooksAndMCP.jsonl @@ -1,36 +1,42 @@ -{"dir":"send","msg":{"request":{"hooks":{"PostToolUse":[{"hookCallbackIds":["hook_0"],"matcher":""}]},"subtype":"initialize"},"request_id":"req_9cb77f8b43f6be63","type":"control_request"}} -{"dir":"recv","msg":{"type":"control_request","request_id":"a6229ca5-1994-453a-83a3-8b3e05694cbe","request":{"subtype":"mcp_message","server_name":"byre","message":{"method":"initialize","params":{"protocolVersion":"2025-11-25","capabilities":{},"clientInfo":{"name":"claude-code","title":"Claude Code","description":"Anthropic's agentic coding tool","websiteUrl":"https://claude.com/claude-code","version":"2.1.296"}},"jsonrpc":"2.0","id":0}}}} -{"dir":"send","msg":{"response":{"request_id":"a6229ca5-1994-453a-83a3-8b3e05694cbe","response":{"mcp_response":{"jsonrpc":"2.0","id":0,"result":{"capabilities":{"tools":{}},"protocolVersion":"2025-06-18","serverInfo":{"name":"byre","version":"0.0.0"}}}},"subtype":"success"},"type":"control_response"}} -{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_9cb77f8b43f6be63","response":{"commands":[{"name":"deep-research","description":"Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. (dynamic workflow)","argumentHint":"","builtin":true},{"name":"design","description":"Make a new Design artifact from a brief","argumentHint":"[what to design]","builtin":true},{"name":"slides","description":"Make a new Slides deck artifact from a brief","argumentHint":"[what the deck is about]","builtin":true},{"name":"design-sync","description":"Push a React design system to claude.ai/design. This runs a converter that bundles the real component code (from Storybook or a bare package) and uploads it. Use when the user runs /design-sync or says \"sync my design system to Claude Design\".","argumentHint":"[\u003cproject hint, e.g. \"Acme DS\"\u003e]","builtin":true},{"name":"dataviz","description":"Use this skill whenever you are about to create ANY chart, graph, plot, dashboard, or data visualization, in ANY output medium — an HTML or React artifact, inline SVG, plotting code in any library (matplotlib, plotly, d3, Recharts, …), an image/PNG you will render and upload, or a chart shared into Slack. Read it BEFORE writing the first line of chart code, choosing chart colors, building a stat tile / meter / KPI row, or laying out a dashboard. When the destination is a first-party document connector (host-designated, never self-described) that renders live charts, hand it the rows (inline, or as an uploaded data file the chart cites) rather than a rendered PNG/SVG — a picture of a chart loses hover, data inspection and per-value comments. Produces visualizations that read as one system — elegant, accessible, consistent in light and dark — using a brand-neutral placeholder palette you swap for your own. Teaches a design-system-agnostic method: a form heuristic, a color formula with a runnable validator, mark specs, and interaction rules. A validated default palette is documented in `references/palette.md` — swap that file's values for your brand's. Triggers on: \"chart\", \"graph\", \"plot\", \"data viz\", \"visualization\", \"dashboard\", \"analytics\", \"visualize data\", \"categorical colors\", \"sequential / diverging palette\", \"stat tile\", \"sparkline\", \"heatmap\", \"legend\", \"axis\", \"tooltip\", \"chart colors\", \"color by series\".","argumentHint":"","builtin":true},{"name":"artifact-diagramming","description":"Diagramming know-how for Artifacts - when a picture earns its place, how to draw one that shows the real mechanism, and the inline-SVG mechanics that keep it legible in both themes.","argumentHint":"","builtin":true},{"name":"artifact-capabilities","description":"Runtime capabilities a published Artifact page can be granted — behavior static HTML cannot provide on its own, such as the page reading live or connected data, remembering what people do on it (a poll, a sign-up sheet, a checklist, a document edited in place — it saves new versions of itself), keeping state shared across viewers, knowing who is viewing, asking Claude a question of its own, storing files people add, handing the viewer a file to save, or using the viewer's camera, microphone, location, screen or device motion. Serves this user's live capability roster and the typed call definitions. Load it whenever any such runtime behavior would make an artifact more useful, before writing the page.","argumentHint":"","builtin":true},{"name":"update-config","description":"Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme/model, suggest the /config command.","argumentHint":"","builtin":true},{"name":"verify","description":"Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.","argumentHint":"","builtin":true},{"name":"debug","description":"Enable debug logging for this session and help diagnose issues","argumentHint":"[issue description]","builtin":true},{"name":"code-review","description":"Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep multi-agent review in the cloud); with no level given, it reuses the level you typed last. Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review. Pass --max-findings \u003cn\u003e to report up to n findings, or --max-findings all for every finding. The choice stays until you pass --max-findings default. For ultra on a GitHub.com PR target, --post asks to post the finished review’s findings to the PR as a single comment from the user’s GitHub account (not a review; the launch dialog still confirms in interactive sessions, while non-interactive mode posts on the flag alone) and --no-post hides that option.","argumentHint":"[low|medium|high|xhigh|max|ultra] [--fix] [--comment] [\u003cpr#\u003e|\u003cbranch\u003e|\u003cpath\u003e] [--max-findings \u003cn\u003e|all]","aliases":["review"],"builtin":true},{"name":"simplify","description":"Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.","argumentHint":"[\u003ctarget\u003e]","builtin":true},{"name":"batch","description":"Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.","argumentHint":"\u003cinstruction\u003e","builtin":true},{"name":"fewer-permission-prompts","description":"Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.","argumentHint":"","builtin":true},{"name":"doctor","description":"Health-check the user's Claude Code setup and fix issues: diagnose installation health — what the `claude doctor` terminal diagnostics cover — from local data (duplicate or leftover installs, PATH, unparseable settings files, broken or colliding agent definitions, skills whose frontmatter fails to parse); find unused skills, MCP servers, and plugins versus their context cost and disable dead weight; deduplicate local CLAUDE.md files against checked-in ones; trim checked-in CLAUDE.md files by cutting content a session could derive from the codebase (directory layouts, tech-stack lists, architecture overviews) while keeping gotchas, rationale, and non-standard conventions; migrate always-loaded CLAUDE.md guidance into lazy skills and nested CLAUDE.md files; flag slow hooks and context-heavy extensions; check the installed version is current; make auto mode the default permission mode; and pre-approve frequently denied read-only commands. Use when the user asks for a doctor run, checkup, audit, tune-up, or cleanup of their Claude Code setup or configuration.","argumentHint":"[prompt-audit [\u003cpath\u003e]]","aliases":["checkup"],"builtin":true},{"name":"loop","description":"Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.","argumentHint":"[interval] [prompt]","aliases":["proactive"],"builtin":true},{"name":"schedule","description":"Create, update, list, or run scheduled cloud agents (routines) that execute on a cron schedule.","argumentHint":"","aliases":["routines"],"builtin":true},{"name":"claude-api","description":"Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).","argumentHint":"","builtin":true},{"name":"workflow-authoring","description":"Reference for writing a Workflow tool script (script API and gotchas, resume, quality patterns, worked examples). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.","argumentHint":"","builtin":true},{"name":"run","description":"Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).","argumentHint":"","builtin":true},{"name":"run-skill-generator","description":"Author or improve the run-\u003cunit\u003e skill - a per-project skill that tells agents how to build, launch, and drive this project's app. Use when the user asks to set up the project, get it running, write run instructions, or verify build/run steps work from a clean environment.","argumentHint":"","builtin":true},{"name":"plugin-authoring","description":"Make a mod: a change to Claude's own interface or behaviour, such as a live pane or panel, a band above the prompt, a status line, a toast, a slash command, or a hook on tool calls or prompts. Use to make, change or debug a mod or its hooks module.","argumentHint":"","builtin":true},{"name":"advisor","description":"Let Claude consult a stronger model at key moments","argumentHint":"[fable|opus|sonnet|off]","builtin":true},{"name":"agents","description":"(removed) Ask Claude to create/manage subagents, or edit .claude/agents/","argumentHint":"","builtin":true},{"name":"auto-mode-setup","description":"Teach auto mode about your environment, plus optional rule tweaks","argumentHint":"[--request-id \u003cuuid\u003e] (--wizard posture=… scope=… depth=… --propose | --expect-sha256 \u003c64-hex\u003e --apply-file \u003cpath\u003e)","builtin":true},{"name":"autocompact","description":"Configure the auto-compact window size","argumentHint":"[auto|\u003ctokens\u003e]","builtin":true},{"name":"clear","description":"Start a new session with empty context; previous session stays on disk (resumable with /resume)","argumentHint":"[name]","aliases":["reset","new"],"builtin":true},{"name":"color","description":"Set the prompt bar color for this session","argumentHint":"[red|blue|green|yellow|purple|orange|pink|cyan|default]","builtin":true},{"name":"compact","description":"Free up context by summarizing the conversation so far","argumentHint":"\u003coptional custom summarization instructions\u003e","builtin":true},{"name":"config","description":"Set a setting by key","argumentHint":"key=value","aliases":["settings"],"builtin":true},{"name":"output-style","description":"List output styles or switch to one","argumentHint":"[style]","builtin":true},{"name":"context","description":"Show current context usage","argumentHint":"","builtin":true},{"name":"effort","description":"Set effort level for model usage","argumentHint":"\u003clow|medium|high|xhigh|max|auto|ultracode [on|off]\u003e","builtin":true},{"name":"fast","description":"Toggle fast mode (Opus 5.5)","argumentHint":"[on|off]","builtin":true},{"name":"focus","description":"Toggle focus view: just your prompt, summary, and response","argumentHint":"[on|off]","builtin":true},{"name":"heapdump","description":"Dump the JS heap to the Desktop; on Linux with no Desktop folder, the home directory","argumentHint":"","builtin":true},{"name":"init","description":"Initialize a new CLAUDE.md file with codebase documentation","argumentHint":"","builtin":true},{"name":"mcp","description":"Manage MCP servers","argumentHint":"[reconnect|enable|disable [\u003cserver\u003e|all]]","builtin":true},{"name":"import","description":"Import config from another AI coding agent","argumentHint":"","builtin":true},{"name":"model","description":"Set the AI model for Claude Code","argumentHint":"\u003cmodel\u003e","builtin":true},{"name":"__remote-workflow","description":"Run the workflow script delivered in this session environment (server-launched sessions only)","argumentHint":"","builtin":true},{"name":"workflow-launch-exec","description":"Execute a server-launched workflow handoff (workflow_launch event sessions only)","argumentHint":"","builtin":true},{"name":"reload-plugins","description":"Activate pending plugin changes in the current session","argumentHint":"[--force]","builtin":true},{"name":"reload-skills","description":"Pick up skills added or changed on disk during this session","argumentHint":"","builtin":true},{"name":"rename","description":"Rename the current conversation","argumentHint":"[name]","aliases":["name"],"builtin":true},{"name":"ultrareview","description":"Start a cloud agent that finds and verifies bugs in your branch (~15-25 min, $5-$25 USD) · Runs in a cloud session. See https://code.claude.com/docs/en/claude-code-on-the-web","argumentHint":"","builtin":true},{"name":"security-review","description":"Complete a security review of the pending changes on the current branch","argumentHint":"","builtin":true},{"name":"usage-credits","description":"Configure usage credits or request them from your admin when you hit a limit","argumentHint":"","builtin":true},{"name":"extra-usage","description":"Renamed to /usage-credits","argumentHint":"","builtin":true},{"name":"usage","description":"Show session cost, plan usage, and what's contributing to your limits","argumentHint":"","aliases":["cost","stats"],"builtin":true},{"name":"insights","description":"Generate a report analyzing your Claude Code sessions","argumentHint":"","builtin":true},{"name":"recap","description":"Generate a one-line session recap now","argumentHint":"","builtin":true},{"name":"skill-doctor","description":"Show which loaded skills are unused and costing context","argumentHint":"","builtin":true},{"name":"goal","description":"Set a goal — keep working until the condition is met","argumentHint":"","builtin":true},{"name":"design-consent","description":"Grant Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"design-revoke","description":"Revoke Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"list-agents","description":"List subagents, teammates, and other Claude sessions you can message","argumentHint":"","aliases":["peers"],"builtin":true},{"name":"team-onboarding","description":"Help teammates ramp on Claude Code with a guide from your usage","argumentHint":"","builtin":true},{"name":"docs","description":"docs (editable docs people share and comment on; the default for any document, named as a doc or not: a document, report, proposal, resume, cover letter, letter, contract, policy, form, template, worksheet, essay, handbook, guide, how-to, cheat sheet, SOP or other writing to keep, share, collaborate on, send, submit, print or sign; a doc exports to Word, PDF, Markdown or Google Docs, so needing a file to send, attach, upload, submit or print is no reason to pick Word, and a file nobody asked for is a doc, not Word; a plan, comparison, summary or notes asked in chat stays in chat; a pasted claude.ai artifact link may be a doc: check with docs tools first; Word or another file format named, tracked changes wanted, or a .docx to change or use as a template → that format's skill): making one → if no docs-connector instructions are in context, call its `guide` (topic.instructions) first; then create the doc (headings only, no body) before any search, file read or plan, even with files attached. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docs"]},{"name":"docx","description":"Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers include: any mention of Microsoft Word Documents, such as 'Word doc', 'word document', '.docx', '.dotx', 'microsoft doc'. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a deliverable as a Word or .docx file (to download, email or print), use this skill. However, if they ask for a document, page, report, memo, or notes WITHOUT naming a file format and the session offers Claude's own dedicated document or page skill or connector, use that instead, even if they will email or print it. Do NOT use for PDFs, spreadsheets, Google Docs, or coding unrelated to document generation. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docx"]},{"name":"google-workspace","description":"Read this before the first Google Drive, Docs, Sheets or Slides connector call whenever the task creates or changes a Google file. Use this skill whenever the user wants to create or change a Google Doc, Sheet or Slides file in their Google Drive. Triggers include: a request that names Google Docs, Sheets, Slides or Drive and asks to make, edit, format, copy or rename a file; a docs.google.com link with a request to change that file, even a one-line fix or suggested edits; and any follow-up change to a Google file from earlier in the chat, even \"change it\" or \"add a tab\". Includes helper scripts for document positions, cell ranges and slide layout. However, if the user asks for a doc, deck or spreadsheet without naming Google, or gives a Google file only as source material for something new, use Claude's own output type instead. Do NOT use for read-only questions about a Google file, or for Word, Excel, PowerPoint or PDF files. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:google-workspace"]},{"name":"import-memory","description":"Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:import-memory"]},{"name":"morning","description":"Render the user's morning brief as a styled HTML artifact, or set it up as a recurring weekday task. Use only when the user explicitly asks to run, see, or set up their morning brief, or if they invoke /morning by name. A question about their day, schedule, or calendar is not by itself a request for the brief; answer it directly instead. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:morning"]},{"name":"pdf","description":"Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pdf"]},{"name":"pptx","description":"Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations as PowerPoint (.pptx) files; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email, summary, or creating a different type of slide deck); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user asks for a PowerPoint or .pptx file, or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. However, when the user asks for a deck, slides, a slide deck, or a presentation without naming a file format, default to using a dedicated slide-deck artifact type or a separate slides skill if this session offers one; otherwise, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pptx"]},{"name":"skill-creator","description":"Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:skill-creator"]},{"name":"xlsx","description":"Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:xlsx"]}],"agents":[{"name":"claude","description":"Catch-all for any task that doesn't fit a more specific agent. FleetView's default when no agent name is typed."},{"name":"claude-code-guide","description":"Use this agent when the user asks questions (\"Can Claude...\", \"Does Claude...\", \"How do I...\") about: (1) Claude Code (the CLI tool) - features, hooks, slash commands, MCP servers, settings, IDE integrations, keyboard shortcuts; (2) Claude Agent SDK - building custom agents; (3) Claude API (formerly Anthropic API) - Messages API for directly passing messages to Claude, Tool Runner (`client.beta.messages.tool_runner`) for running an agentic loop over your own tools, manual tool-use loops, Managed Agents for server-hosted agents with a managed sandbox, prompt caching, and general Anthropic SDK usage; (4) Claude Tag (Claude in Slack) - what it is, setting it up for a Slack workspace, `/install-slack-app`; (5) `claude plugin eval` (writing and running plugin eval suites, its JSON/report, sandbox, CI) and the `/skill-doctor` report. **IMPORTANT:** Before spawning a new agent, check if there is already a running or recently completed claude-code-guide agent that you can continue via SendMessage.","model":"haiku"},{"name":"Explore","description":"Fast read-only search agent for locating code. Use it to find files by pattern (eg. \"src/components/**/*.tsx\"), grep for symbols or keywords (eg. \"API endpoints\"), or answer \"where is X defined / which files reference Y.\" Do NOT use it for code review, design-doc auditing, cross-file consistency checks, or open-ended analysis — it reads excerpts rather than whole files and will miss content past its read window. When calling, specify search breadth: \"quick\" for a single targeted lookup, \"medium\" for moderate exploration, or \"very thorough\" to search across multiple locations and naming conventions.","model":"inherit"},{"name":"general-purpose","description":"General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you."},{"name":"Plan","description":"Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs.","model":"inherit"},{"name":"statusline-setup","description":"Use this agent to configure the user's Claude Code status line setting.","model":"sonnet"}],"output_style":"default","available_output_styles":["default","Proactive","Concise","Explanatory","Learning"],"user_output_styles_dir":"/Users/flamingcow/.claude/output-styles","models":[{"value":"default","resolvedModel":"claude-opus-5-5","displayName":"Default (recommended)","description":"Opus 5.5 · Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"opus","resolvedModel":"claude-opus-5-5","displayName":"Opus 5.5","description":"For complex work and everyday tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"fable","resolvedModel":"claude-fable-5-1","displayName":"Fable 5.1","description":"For your toughest challenges","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"sonnet","resolvedModel":"claude-sonnet-5-5","displayName":"Sonnet 5.5","description":"Most efficient for simpler tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"haiku","resolvedModel":"claude-haiku-5-5","displayName":"Haiku 5.5","description":"Fastest for quick answers","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-haiku-4-5-20251001","resolvedModel":"claude-haiku-4-5-20251001","displayName":"Haiku 4.5","description":"Fastest for quick answers"},{"value":"claude-sonnet-5","resolvedModel":"claude-sonnet-5","displayName":"Sonnet 5","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-5","resolvedModel":"claude-opus-5","displayName":"Opus 5","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-fable-5","resolvedModel":"claude-fable-5","displayName":"Fable 5","description":"Most capable for your hardest and longest-running tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-8","resolvedModel":"claude-opus-4-8","displayName":"Opus 4.8","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-opus-4-7","resolvedModel":"claude-opus-4-7","displayName":"Opus 4.7","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-6","resolvedModel":"claude-opus-4-6","displayName":"Opus 4.6","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-sonnet-4-6","resolvedModel":"claude-sonnet-4-6","displayName":"Sonnet 4.6","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true}],"account":{"email":"[redacted]","organization":"[redacted]'s Organization","subscriptionType":"Claude Max","apiProvider":"firstParty"},"pid":98363,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","hooks_applied":true,"feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} +{"dir":"send","msg":{"request":{"hooks":{"PostToolUse":[{"hookCallbackIds":["hook_0"],"matcher":""}]},"subtype":"initialize"},"request_id":"req_2000d2831f87e860","type":"control_request"}} +{"dir":"recv","msg":{"type":"control_request","request_id":"45a47933-4c33-4f35-95ad-c56a77bc5fa1","request":{"subtype":"mcp_message","server_name":"byre","message":{"method":"initialize","params":{"protocolVersion":"2025-11-25","capabilities":{},"clientInfo":{"name":"claude-code","title":"Claude Code","description":"Anthropic's agentic coding tool","websiteUrl":"https://claude.com/claude-code","version":"2.1.296"}},"jsonrpc":"2.0","id":0}}}} +{"dir":"send","msg":{"response":{"request_id":"45a47933-4c33-4f35-95ad-c56a77bc5fa1","response":{"mcp_response":{"jsonrpc":"2.0","id":0,"result":{"capabilities":{"tools":{}},"protocolVersion":"2025-06-18","serverInfo":{"name":"byre","version":"0.0.0"}}}},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_2000d2831f87e860","response":{"commands":[{"name":"deep-research","description":"Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. (dynamic workflow)","argumentHint":"","builtin":true},{"name":"design","description":"Make a new Design artifact from a brief","argumentHint":"[what to design]","builtin":true},{"name":"slides","description":"Make a new Slides deck artifact from a brief","argumentHint":"[what the deck is about]","builtin":true},{"name":"design-sync","description":"Push a React design system to claude.ai/design. This runs a converter that bundles the real component code (from Storybook or a bare package) and uploads it. Use when the user runs /design-sync or says \"sync my design system to Claude Design\".","argumentHint":"[\u003cproject hint, e.g. \"Acme DS\"\u003e]","builtin":true},{"name":"dataviz","description":"Use this skill whenever you are about to create ANY chart, graph, plot, dashboard, or data visualization, in ANY output medium — an HTML or React artifact, inline SVG, plotting code in any library (matplotlib, plotly, d3, Recharts, …), an image/PNG you will render and upload, or a chart shared into Slack. Read it BEFORE writing the first line of chart code, choosing chart colors, building a stat tile / meter / KPI row, or laying out a dashboard. When the destination is a first-party document connector (host-designated, never self-described) that renders live charts, hand it the rows (inline, or as an uploaded data file the chart cites) rather than a rendered PNG/SVG — a picture of a chart loses hover, data inspection and per-value comments. Produces visualizations that read as one system — elegant, accessible, consistent in light and dark — using a brand-neutral placeholder palette you swap for your own. Teaches a design-system-agnostic method: a form heuristic, a color formula with a runnable validator, mark specs, and interaction rules. A validated default palette is documented in `references/palette.md` — swap that file's values for your brand's. Triggers on: \"chart\", \"graph\", \"plot\", \"data viz\", \"visualization\", \"dashboard\", \"analytics\", \"visualize data\", \"categorical colors\", \"sequential / diverging palette\", \"stat tile\", \"sparkline\", \"heatmap\", \"legend\", \"axis\", \"tooltip\", \"chart colors\", \"color by series\".","argumentHint":"","builtin":true},{"name":"artifact-diagramming","description":"Diagramming know-how for Artifacts - when a picture earns its place, how to draw one that shows the real mechanism, and the inline-SVG mechanics that keep it legible in both themes.","argumentHint":"","builtin":true},{"name":"artifact-capabilities","description":"Runtime capabilities a published Artifact page can be granted — behavior static HTML cannot provide on its own, such as the page reading live or connected data, remembering what people do on it (a poll, a sign-up sheet, a checklist, a document edited in place — it saves new versions of itself), keeping state shared across viewers, knowing who is viewing, asking Claude a question of its own, storing files people add, handing the viewer a file to save, or using the viewer's camera, microphone, location, screen or device motion. Serves this user's live capability roster and the typed call definitions. Load it whenever any such runtime behavior would make an artifact more useful, before writing the page.","argumentHint":"","builtin":true},{"name":"update-config","description":"Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme/model, suggest the /config command.","argumentHint":"","builtin":true},{"name":"verify","description":"Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.","argumentHint":"","builtin":true},{"name":"debug","description":"Enable debug logging for this session and help diagnose issues","argumentHint":"[issue description]","builtin":true},{"name":"code-review","description":"Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep multi-agent review in the cloud); with no level given, it reuses the level you typed last. Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review. Pass --max-findings \u003cn\u003e to report up to n findings, or --max-findings all for every finding. The choice stays until you pass --max-findings default. For ultra on a GitHub.com PR target, --post asks to post the finished review’s findings to the PR as a single comment from the user’s GitHub account (not a review; the launch dialog still confirms in interactive sessions, while non-interactive mode posts on the flag alone) and --no-post hides that option.","argumentHint":"[low|medium|high|xhigh|max|ultra] [--fix] [--comment] [\u003cpr#\u003e|\u003cbranch\u003e|\u003cpath\u003e] [--max-findings \u003cn\u003e|all]","aliases":["review"],"builtin":true},{"name":"simplify","description":"Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.","argumentHint":"[\u003ctarget\u003e]","builtin":true},{"name":"batch","description":"Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.","argumentHint":"\u003cinstruction\u003e","builtin":true},{"name":"fewer-permission-prompts","description":"Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.","argumentHint":"","builtin":true},{"name":"doctor","description":"Health-check the user's Claude Code setup and fix issues: diagnose installation health — what the `claude doctor` terminal diagnostics cover — from local data (duplicate or leftover installs, PATH, unparseable settings files, broken or colliding agent definitions, skills whose frontmatter fails to parse); find unused skills, MCP servers, and plugins versus their context cost and disable dead weight; deduplicate local CLAUDE.md files against checked-in ones; trim checked-in CLAUDE.md files by cutting content a session could derive from the codebase (directory layouts, tech-stack lists, architecture overviews) while keeping gotchas, rationale, and non-standard conventions; migrate always-loaded CLAUDE.md guidance into lazy skills and nested CLAUDE.md files; flag slow hooks and context-heavy extensions; check the installed version is current; make auto mode the default permission mode; and pre-approve frequently denied read-only commands. Use when the user asks for a doctor run, checkup, audit, tune-up, or cleanup of their Claude Code setup or configuration.","argumentHint":"[prompt-audit [\u003cpath\u003e]]","aliases":["checkup"],"builtin":true},{"name":"loop","description":"Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.","argumentHint":"[interval] [prompt]","aliases":["proactive"],"builtin":true},{"name":"schedule","description":"Create, update, list, or run scheduled cloud agents (routines) that execute on a cron schedule.","argumentHint":"","aliases":["routines"],"builtin":true},{"name":"claude-api","description":"Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).","argumentHint":"","builtin":true},{"name":"workflow-authoring","description":"Reference for writing a Workflow tool script (script API and gotchas, resume, quality patterns, worked examples). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.","argumentHint":"","builtin":true},{"name":"run","description":"Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).","argumentHint":"","builtin":true},{"name":"run-skill-generator","description":"Author or improve the run-\u003cunit\u003e skill - a per-project skill that tells agents how to build, launch, and drive this project's app. Use when the user asks to set up the project, get it running, write run instructions, or verify build/run steps work from a clean environment.","argumentHint":"","builtin":true},{"name":"plugin-authoring","description":"Make a mod: a change to Claude's own interface or behaviour, such as a live pane or panel, a band above the prompt, a status line, a toast, a slash command, or a hook on tool calls or prompts. Use to make, change or debug a mod or its hooks module.","argumentHint":"","builtin":true},{"name":"advisor","description":"Let Claude consult a stronger model at key moments","argumentHint":"[fable|opus|sonnet|off]","builtin":true},{"name":"agents","description":"(removed) Ask Claude to create/manage subagents, or edit .claude/agents/","argumentHint":"","builtin":true},{"name":"auto-mode-setup","description":"Teach auto mode about your environment, plus optional rule tweaks","argumentHint":"[--request-id \u003cuuid\u003e] (--wizard posture=… scope=… depth=… --propose | --expect-sha256 \u003c64-hex\u003e --apply-file \u003cpath\u003e)","builtin":true},{"name":"autocompact","description":"Configure the auto-compact window size","argumentHint":"[auto|\u003ctokens\u003e]","builtin":true},{"name":"clear","description":"Start a new session with empty context; previous session stays on disk (resumable with /resume)","argumentHint":"[name]","aliases":["reset","new"],"builtin":true},{"name":"color","description":"Set the prompt bar color for this session","argumentHint":"[red|blue|green|yellow|purple|orange|pink|cyan|default]","builtin":true},{"name":"compact","description":"Free up context by summarizing the conversation so far","argumentHint":"\u003coptional custom summarization instructions\u003e","builtin":true},{"name":"config","description":"Set a setting by key","argumentHint":"key=value","aliases":["settings"],"builtin":true},{"name":"output-style","description":"List output styles or switch to one","argumentHint":"[style]","builtin":true},{"name":"context","description":"Show current context usage","argumentHint":"","builtin":true},{"name":"effort","description":"Set effort level for model usage","argumentHint":"\u003clow|medium|high|xhigh|max|auto|ultracode [on|off]\u003e","builtin":true},{"name":"fast","description":"Toggle fast mode (Opus 5.5)","argumentHint":"[on|off]","builtin":true},{"name":"focus","description":"Toggle focus view: just your prompt, summary, and response","argumentHint":"[on|off]","builtin":true},{"name":"heapdump","description":"Dump the JS heap to the Desktop; on Linux with no Desktop folder, the home directory","argumentHint":"","builtin":true},{"name":"init","description":"Initialize a new CLAUDE.md file with codebase documentation","argumentHint":"","builtin":true},{"name":"mcp","description":"Manage MCP servers","argumentHint":"[reconnect|enable|disable [\u003cserver\u003e|all]]","builtin":true},{"name":"import","description":"Import config from another AI coding agent","argumentHint":"","builtin":true},{"name":"model","description":"Set the AI model for Claude Code","argumentHint":"\u003cmodel\u003e","builtin":true},{"name":"__remote-workflow","description":"Run the workflow script delivered in this session environment (server-launched sessions only)","argumentHint":"","builtin":true},{"name":"workflow-launch-exec","description":"Execute a server-launched workflow handoff (workflow_launch event sessions only)","argumentHint":"","builtin":true},{"name":"reload-plugins","description":"Activate pending plugin changes in the current session","argumentHint":"[--force]","builtin":true},{"name":"reload-skills","description":"Pick up skills added or changed on disk during this session","argumentHint":"","builtin":true},{"name":"rename","description":"Rename the current conversation","argumentHint":"[name]","aliases":["name"],"builtin":true},{"name":"ultrareview","description":"Start a cloud agent that finds and verifies bugs in your branch (~15-25 min, $5-$25 USD) · Runs in a cloud session. See https://code.claude.com/docs/en/claude-code-on-the-web","argumentHint":"","builtin":true},{"name":"security-review","description":"Complete a security review of the pending changes on the current branch","argumentHint":"","builtin":true},{"name":"usage-credits","description":"Configure usage credits or request them from your admin when you hit a limit","argumentHint":"","builtin":true},{"name":"extra-usage","description":"Renamed to /usage-credits","argumentHint":"","builtin":true},{"name":"usage","description":"Show session cost, plan usage, and what's contributing to your limits","argumentHint":"","aliases":["cost","stats"],"builtin":true},{"name":"insights","description":"Generate a report analyzing your Claude Code sessions","argumentHint":"","builtin":true},{"name":"recap","description":"Generate a one-line session recap now","argumentHint":"","builtin":true},{"name":"skill-doctor","description":"Show which loaded skills are unused and costing context","argumentHint":"","builtin":true},{"name":"goal","description":"Set a goal — keep working until the condition is met","argumentHint":"","builtin":true},{"name":"design-consent","description":"Grant Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"design-revoke","description":"Revoke Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"list-agents","description":"List subagents, teammates, and other Claude sessions you can message","argumentHint":"","aliases":["peers"],"builtin":true},{"name":"team-onboarding","description":"Help teammates ramp on Claude Code with a guide from your usage","argumentHint":"","builtin":true},{"name":"docs","description":"docs (editable docs people share and comment on; the default for any document, named as a doc or not: a document, report, proposal, resume, cover letter, letter, contract, policy, form, template, worksheet, essay, handbook, guide, how-to, cheat sheet, SOP or other writing to keep, share, collaborate on, send, submit, print or sign; a doc exports to Word, PDF, Markdown or Google Docs, so needing a file to send, attach, upload, submit or print is no reason to pick Word, and a file nobody asked for is a doc, not Word; a plan, comparison, summary or notes asked in chat stays in chat; a pasted claude.ai artifact link may be a doc: check with docs tools first; Word or another file format named, tracked changes wanted, or a .docx to change or use as a template → that format's skill): making one → if no docs-connector instructions are in context, call its `guide` (topic.instructions) first; then create the doc (headings only, no body) before any search, file read or plan, even with files attached. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docs"]},{"name":"docx","description":"Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers include: any mention of Microsoft Word Documents, such as 'Word doc', 'word document', '.docx', '.dotx', 'microsoft doc'. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a deliverable as a Word or .docx file (to download, email or print), use this skill. However, if they ask for a document, page, report, memo, or notes WITHOUT naming a file format and the session offers Claude's own dedicated document or page skill or connector, use that instead, even if they will email or print it. Do NOT use for PDFs, spreadsheets, Google Docs, or coding unrelated to document generation. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docx"]},{"name":"google-workspace","description":"Read this before the first Google Drive, Docs, Sheets or Slides connector call whenever the task creates or changes a Google file. Use this skill whenever the user wants to create or change a Google Doc, Sheet or Slides file in their Google Drive. Triggers include: a request that names Google Docs, Sheets, Slides or Drive and asks to make, edit, format, copy or rename a file; a docs.google.com link with a request to change that file, even a one-line fix or suggested edits; and any follow-up change to a Google file from earlier in the chat, even \"change it\" or \"add a tab\". Includes helper scripts for document positions, cell ranges and slide layout. However, if the user asks for a doc, deck or spreadsheet without naming Google, or gives a Google file only as source material for something new, use Claude's own output type instead. Do NOT use for read-only questions about a Google file, or for Word, Excel, PowerPoint or PDF files. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:google-workspace"]},{"name":"import-memory","description":"Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:import-memory"]},{"name":"morning","description":"Render the user's morning brief as a styled HTML artifact, or set it up as a recurring weekday task. Use only when the user explicitly asks to run, see, or set up their morning brief, or if they invoke /morning by name. A question about their day, schedule, or calendar is not by itself a request for the brief; answer it directly instead. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:morning"]},{"name":"pdf","description":"Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pdf"]},{"name":"pptx","description":"Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations as PowerPoint (.pptx) files; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email, summary, or creating a different type of slide deck); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user asks for a PowerPoint or .pptx file, or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. However, when the user asks for a deck, slides, a slide deck, or a presentation without naming a file format, default to using a dedicated slide-deck artifact type or a separate slides skill if this session offers one; otherwise, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pptx"]},{"name":"skill-creator","description":"Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:skill-creator"]},{"name":"xlsx","description":"Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:xlsx"]}],"agents":[{"name":"claude","description":"Catch-all for any task that doesn't fit a more specific agent. FleetView's default when no agent name is typed."},{"name":"claude-code-guide","description":"Use this agent when the user asks questions (\"Can Claude...\", \"Does Claude...\", \"How do I...\") about: (1) Claude Code (the CLI tool) - features, hooks, slash commands, MCP servers, settings, IDE integrations, keyboard shortcuts; (2) Claude Agent SDK - building custom agents; (3) Claude API (formerly Anthropic API) - Messages API for directly passing messages to Claude, Tool Runner (`client.beta.messages.tool_runner`) for running an agentic loop over your own tools, manual tool-use loops, Managed Agents for server-hosted agents with a managed sandbox, prompt caching, and general Anthropic SDK usage; (4) Claude Tag (Claude in Slack) - what it is, setting it up for a Slack workspace, `/install-slack-app`; (5) `claude plugin eval` (writing and running plugin eval suites, its JSON/report, sandbox, CI) and the `/skill-doctor` report. **IMPORTANT:** Before spawning a new agent, check if there is already a running or recently completed claude-code-guide agent that you can continue via SendMessage.","model":"haiku"},{"name":"Explore","description":"Fast read-only search agent for locating code. Use it to find files by pattern (eg. \"src/components/**/*.tsx\"), grep for symbols or keywords (eg. \"API endpoints\"), or answer \"where is X defined / which files reference Y.\" Do NOT use it for code review, design-doc auditing, cross-file consistency checks, or open-ended analysis — it reads excerpts rather than whole files and will miss content past its read window. When calling, specify search breadth: \"quick\" for a single targeted lookup, \"medium\" for moderate exploration, or \"very thorough\" to search across multiple locations and naming conventions.","model":"inherit"},{"name":"general-purpose","description":"General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you."},{"name":"Plan","description":"Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs.","model":"inherit"},{"name":"statusline-setup","description":"Use this agent to configure the user's Claude Code status line setting.","model":"sonnet"}],"output_style":"default","available_output_styles":["default","Proactive","Concise","Explanatory","Learning"],"user_output_styles_dir":"/Users/flamingcow/.claude/output-styles","models":[{"value":"default","resolvedModel":"claude-opus-5-5","displayName":"Default (recommended)","description":"Opus 5.5 · Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"opus","resolvedModel":"claude-opus-5-5","displayName":"Opus 5.5","description":"For complex work and everyday tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"fable","resolvedModel":"claude-fable-5-1","displayName":"Fable 5.1","description":"For your toughest challenges","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"sonnet","resolvedModel":"claude-sonnet-5-5","displayName":"Sonnet 5.5","description":"Most efficient for simpler tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"haiku","resolvedModel":"claude-haiku-5-5","displayName":"Haiku 5.5","description":"Fastest for quick answers","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-haiku-4-5-20251001","resolvedModel":"claude-haiku-4-5-20251001","displayName":"Haiku 4.5","description":"Fastest for quick answers"},{"value":"claude-sonnet-5","resolvedModel":"claude-sonnet-5","displayName":"Sonnet 5","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-5","resolvedModel":"claude-opus-5","displayName":"Opus 5","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-fable-5","resolvedModel":"claude-fable-5","displayName":"Fable 5","description":"Most capable for your hardest and longest-running tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-8","resolvedModel":"claude-opus-4-8","displayName":"Opus 4.8","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-opus-4-7","resolvedModel":"claude-opus-4-7","displayName":"Opus 4.7","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-6","resolvedModel":"claude-opus-4-6","displayName":"Opus 4.6","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-sonnet-4-6","resolvedModel":"claude-sonnet-4-6","displayName":"Sonnet 4.6","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true}],"account":{"email":"[redacted]","organization":"[redacted]'s Organization","subscriptionType":"Claude Max","apiProvider":"firstParty"},"pid":2404,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","hooks_applied":true,"feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} {"dir":"send","msg":{"message":{"content":"Create a file hello.txt containing exactly the word hi, then git add and git commit it with the message \"add hello\", then call the finish tool.","role":"user"},"parent_tool_use_id":null,"session_id":"","type":"user"}} -{"dir":"recv","msg":{"type":"control_request","request_id":"06906118-7e10-4f24-b5da-c74d19ece14b","request":{"subtype":"mcp_message","server_name":"byre","message":{"jsonrpc":"2.0","method":"notifications/initialized"}}}} -{"dir":"send","msg":{"response":{"request_id":"06906118-7e10-4f24-b5da-c74d19ece14b","response":{"mcp_response":{"jsonrpc":"2.0","id":null,"result":{}}},"subtype":"success"},"type":"control_response"}} -{"dir":"recv","msg":{"type":"control_request","request_id":"6eacdcc3-72a7-4cf3-9680-26dcfaf5dc86","request":{"subtype":"mcp_message","server_name":"byre","message":{"method":"tools/list","jsonrpc":"2.0","id":1}}}} -{"dir":"send","msg":{"response":{"request_id":"6eacdcc3-72a7-4cf3-9680-26dcfaf5dc86","response":{"mcp_response":{"jsonrpc":"2.0","id":1,"result":{"tools":[{"name":"finish","description":"Call this once the task is complete.","inputSchema":{"type":"object","properties":{}}}]}}},"subtype":"success"},"type":"control_response"}} -{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP2708089900/001","session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","LSP","Monitor","NotebookEdit","PushNotification","Read","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write","mcp__byre__finish"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"pending","source":"claudeai"},{"name":"claude.ai Heliosian","status":"pending","source":"claudeai"},{"name":"claude.ai Fastmail","status":"pending","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"},{"name":"byre","status":"connected","source":"sdk"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"82482951-e1f4-46fa-91ba-5451032b96e8","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP2708089900-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP2708089900-001/d50a2e9d-312b-417d-b170-52615c3b7607/scratchpad","messaging_socket_path":"/tmp/cc-socks/98363.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","uuid":"df9da8f0-0c65-4ede-b6e0-5466e93d1f40"}} -{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.01,"resetsAt":1792054200},"seven_day":{"utilization":0.34,"resetsAt":1792270800}}},"uuid":"470c07e2-2518-4208-b65b-5a6a1264e4bb","session_id":"d50a2e9d-312b-417d-b170-52615c3b7607"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3Mazc5AwLTmBXXhF9g4","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01PTz61sYh9BChK8j25Ufgo6","name":"Write","input":{"file_path":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP2708089900/001/hello.txt","content":"hi"},"caller":{"type":"direct"}}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15288,"cache_read_input_tokens":22425,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15288},"output_tokens":16,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","uuid":"1bfa04d3-4d53-434a-aeaf-8f4d79a43914","timestamp":"2026-10-15T04:01:03.895Z","request_id":"req_011Cg3MazPBKSDDCkt2cTyYy","wire_tool_inputs":{"toolu_01PTz61sYh9BChK8j25Ufgo6":{"file_path":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP2708089900/001/hello.txt","content":"hi"}}}} -{"dir":"recv","msg":{"type":"control_request","request_id":"e871528f-5b0e-4825-8e78-becf403d7dea","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP2708089900-001/d50a2e9d-312b-417d-b170-52615c3b7607.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP2708089900/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP2708089900-001/d50a2e9d-312b-417d-b170-52615c3b7607/scratchpad","prompt_id":"83f6996d-b89f-4bc4-b44f-7e33e389dd78","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"PostToolUse","tool_name":"Write","tool_input":{"file_path":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP2708089900/001/hello.txt","content":"hi"},"tool_response":{"type":"create","filePath":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP2708089900/001/hello.txt","content":"hi","structuredPatch":[],"originalFile":null,"userModified":false},"tool_use_id":"toolu_01PTz61sYh9BChK8j25Ufgo6","duration_ms":2},"tool_use_id":"toolu_01PTz61sYh9BChK8j25Ufgo6"}}} -{"dir":"send","msg":{"response":{"request_id":"e871528f-5b0e-4825-8e78-becf403d7dea","response":{},"subtype":"success"},"type":"control_response"}} -{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01PTz61sYh9BChK8j25Ufgo6","type":"tool_result","content":"File created successfully at: /private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP2708089900/001/hello.txt (file state is current in your context — no need to Read it back)"}]},"parent_tool_use_id":null,"session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","uuid":"1cc511cd-a275-4158-a560-22592a6690c4","timestamp":"2026-10-15T04:01:03.906Z","tool_use_result":{"type":"create","filePath":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP2708089900/001/hello.txt","content":"hi","structuredPatch":[],"originalFile":null,"userModified":false},"tool_result_meta":[{"id":"toolu_01PTz61sYh9BChK8j25Ufgo6","permission_decision":{"decision":"accept","source":"config","reason_type":"mode"}}]}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","uuid":"d08ba37d-7a1d-49b2-9f59-b269885dbe22"}} -{"dir":"recv","msg":{"type":"system","subtype":"thinking_tokens","estimated_tokens":50,"estimated_tokens_delta":50,"session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","uuid":"352b51a2-b363-4fdc-b326-dd52c56e15fe"}} -{"dir":"recv","msg":{"type":"system","subtype":"thinking_tokens","estimated_tokens":175,"estimated_tokens_delta":125,"session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","uuid":"c1569831-922a-4213-a220-b169d7dfcf55"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3Mb9niCnhu6pdEc7bqP","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4714,"cache_read_input_tokens":37713,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4714},"output_tokens":9,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","uuid":"8aa1070b-1b43-4de6-95f3-1b95bcd678b7","timestamp":"2026-10-15T04:01:05.644Z","request_id":"req_011Cg3Mb9VrfYwz8CvMJ45xd","thinking_duration_ms":651,"thinking_display":"updates"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3Mb9niCnhu6pdEc7bqP","type":"message","role":"assistant","content":[{"type":"text","text":"Authorization for the commit, quoted from the current turn: \"then git add and git commit it with the message \"add hello\"\"."}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4714,"cache_read_input_tokens":37713,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4714},"output_tokens":9,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","uuid":"3af318ea-9049-4d28-b4a6-b6f1ef41e5d6","timestamp":"2026-10-15T04:01:05.645Z","request_id":"req_011Cg3Mb9VrfYwz8CvMJ45xd"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3Mb9niCnhu6pdEc7bqP","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Kdth8WgpR7RU3So7ZfHqAx","name":"Bash","input":{"command":"git add hello.txt \u0026\u0026 git commit -m \"add hello\" -- hello.txt # USER EXPLICITLY AUTHORIZED THIS COMMIT IN THE IMMEDIATELY PRECEDING REQUEST","description":"Stage and commit hello.txt","timeout":30000},"caller":{"type":"direct"}}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4714,"cache_read_input_tokens":37713,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4714},"output_tokens":9,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","uuid":"b9c75e96-e56f-4804-b252-b0924f4bacd9","timestamp":"2026-10-15T04:01:06.329Z","request_id":"req_011Cg3Mb9VrfYwz8CvMJ45xd","wire_tool_inputs":{"toolu_01Kdth8WgpR7RU3So7ZfHqAx":{"command":"git add hello.txt \u0026\u0026 git commit -m \"add hello\" -- hello.txt # USER EXPLICITLY AUTHORIZED THIS COMMIT IN THE IMMEDIATELY PRECEDING REQUEST","timeout":30000,"description":"Stage and commit hello.txt"}}}} -{"dir":"recv","msg":{"type":"system","subtype":"vcs_state_changed","kind":"commit","branch":"main","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP2708089900/001","uuid":"d3d17884-f3bf-4d30-9e33-2d2bf6ab1319","session_id":"d50a2e9d-312b-417d-b170-52615c3b7607"}} -{"dir":"recv","msg":{"type":"control_request","request_id":"693fcc91-eef3-4df1-8c9e-3faf01e28505","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP2708089900-001/d50a2e9d-312b-417d-b170-52615c3b7607.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP2708089900/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP2708089900-001/d50a2e9d-312b-417d-b170-52615c3b7607/scratchpad","prompt_id":"83f6996d-b89f-4bc4-b44f-7e33e389dd78","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"PostToolUse","tool_name":"Bash","tool_input":{"command":"git add hello.txt \u0026\u0026 git commit -m \"add hello\" -- hello.txt # USER EXPLICITLY AUTHORIZED THIS COMMIT IN THE IMMEDIATELY PRECEDING REQUEST","timeout":30000,"description":"Stage and commit hello.txt"},"tool_response":{"stdout":"[main 38d200e] add hello\n 1 file changed, 1 insertion(+)\n create mode 100644 hello.txt","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false,"gitOperation":{"commit":{"sha":"38d200e","kind":"committed","branch":"main"}}},"tool_use_id":"toolu_01Kdth8WgpR7RU3So7ZfHqAx","duration_ms":73},"tool_use_id":"toolu_01Kdth8WgpR7RU3So7ZfHqAx"}}} -{"dir":"send","msg":{"response":{"request_id":"693fcc91-eef3-4df1-8c9e-3faf01e28505","response":{},"subtype":"success"},"type":"control_response"}} -{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01Kdth8WgpR7RU3So7ZfHqAx","type":"tool_result","content":"[main 38d200e] add hello\n 1 file changed, 1 insertion(+)\n create mode 100644 hello.txt","is_error":false}]},"parent_tool_use_id":null,"session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","uuid":"6ad92344-fa35-4937-b216-1e648cca4536","timestamp":"2026-10-15T04:01:06.423Z","tool_use_result":{"stdout":"[main 38d200e] add hello\n 1 file changed, 1 insertion(+)\n create mode 100644 hello.txt","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false,"gitOperation":{"commit":{"sha":"38d200e","kind":"committed","branch":"main"}}},"tool_result_meta":[{"id":"toolu_01Kdth8WgpR7RU3So7ZfHqAx","permission_decision":{"decision":"accept","source":"config","reason_type":"mode"}}]}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","uuid":"5541f04e-7a98-4b33-ba21-ca8017d1c088"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3MbLTR9oKNbR6WJ5WEc","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_0193tN3xiKgw4xd3XKGsHavL","name":"mcp__byre__finish","input":{},"caller":{"type":"direct"}}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":333,"cache_read_input_tokens":42427,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":333},"output_tokens":24,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","uuid":"59e07fbc-a065-495a-bb98-c1e58c546a5a","timestamp":"2026-10-15T04:01:07.549Z","request_id":"req_011Cg3MbLCHFaZhwoVvd6Pep","wire_tool_inputs":{"toolu_0193tN3xiKgw4xd3XKGsHavL":{}},"tool_use_meta":[{"id":"toolu_0193tN3xiKgw4xd3XKGsHavL","display_name":"Finish","server_display_name":"byre"}]}} -{"dir":"recv","msg":{"type":"control_request","request_id":"ac85329e-c81d-40d4-bf52-9be41e5d411d","request":{"subtype":"mcp_message","server_name":"byre","message":{"method":"tools/call","params":{"name":"finish","arguments":{},"_meta":{"claudecode/toolUseId":"toolu_0193tN3xiKgw4xd3XKGsHavL","progressToken":2}},"jsonrpc":"2.0","id":2}}}} -{"dir":"send","msg":{"response":{"request_id":"ac85329e-c81d-40d4-bf52-9be41e5d411d","response":{"mcp_response":{"jsonrpc":"2.0","id":2,"result":{"content":[{"type":"text","text":"noted"}]}}},"subtype":"success"},"type":"control_response"}} -{"dir":"recv","msg":{"type":"control_request","request_id":"8f0ebd1b-949b-498b-9309-3a05ae9918ac","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP2708089900-001/d50a2e9d-312b-417d-b170-52615c3b7607.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP2708089900/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP2708089900-001/d50a2e9d-312b-417d-b170-52615c3b7607/scratchpad","prompt_id":"83f6996d-b89f-4bc4-b44f-7e33e389dd78","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"PostToolUse","tool_name":"mcp__byre__finish","tool_input":{},"tool_response":[{"type":"text","text":"noted"}],"tool_use_id":"toolu_0193tN3xiKgw4xd3XKGsHavL","duration_ms":2,"mcp_server":{"name":"byre","source":"sdk"}},"tool_use_id":"toolu_0193tN3xiKgw4xd3XKGsHavL"}}} -{"dir":"send","msg":{"response":{"request_id":"8f0ebd1b-949b-498b-9309-3a05ae9918ac","response":{},"subtype":"success"},"type":"control_response"}} -{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_0193tN3xiKgw4xd3XKGsHavL","type":"tool_result","content":[{"type":"text","text":"noted"}]}]},"parent_tool_use_id":null,"session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","uuid":"899b48af-c55a-454e-a593-5bf601c24d7f","timestamp":"2026-10-15T04:01:07.559Z","tool_use_result":[{"type":"text","text":"noted"}],"tool_result_meta":[{"id":"toolu_0193tN3xiKgw4xd3XKGsHavL","permission_decision":{"decision":"accept","source":"config","reason_type":"mode"}}]}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","uuid":"683ce938-eca8-4bc5-b464-479820dc7ade"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3MbRKMTqGWwKcK8UZCJ","type":"message","role":"assistant","content":[{"type":"text","text":"I created `hello.txt` containing `hi` and committed it to main as \"add hello\" (commit `38d200e`). I then called the finish tool."}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":63,"cache_read_input_tokens":42760,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":63},"output_tokens":48,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","uuid":"401cbe37-6748-485b-87db-e67b17eeb4e0","timestamp":"2026-10-15T04:01:08.527Z","request_id":"req_011Cg3MbR4jXQdGy2FhTfPxf"}} -{"dir":"recv","msg":{"duration_api_ms":7264,"stop_reason":"end_turn","session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","total_cost_usd":0.10104020000000001,"usage":{"input_tokens":8,"cache_creation_input_tokens":20398,"cache_read_input_tokens":145325,"output_tokens":477,"output_tokens_details":{"thinking_tokens":48},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":20398,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":48,"cache_read_input_tokens":42760,"cache_creation_input_tokens":63,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":63},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1207,"outputTokens":18,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.0001297,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":8,"outputTokens":477,"cacheReadInputTokens":145325,"cacheCreationInputTokens":20398,"webSearchRequests":0,"costUSD":0.1009105,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":48,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":4,"subtype":"success","api_error_status":null,"result":"I created `hello.txt` containing `hi` and committed it to main as \"add hello\" (commit `38d200e`). I then called the finish tool.","ttft_ms":2229,"type":"result","duration_ms":6876,"uuid":"473931ce-c34c-498e-a6ad-bde383ae9da7","ttft_stream_ms":1227,"time_to_request_ms":27,"first_content_frame_ms":1227,"queued_turn_count":0,"result_index":0}} +{"dir":"recv","msg":{"type":"control_request","request_id":"31be8671-2721-4d23-a452-8fe9bdbd0187","request":{"subtype":"mcp_message","server_name":"byre","message":{"jsonrpc":"2.0","method":"notifications/initialized"}}}} +{"dir":"send","msg":{"response":{"request_id":"31be8671-2721-4d23-a452-8fe9bdbd0187","response":{"mcp_response":{"jsonrpc":"2.0","id":null,"result":{}}},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"control_request","request_id":"4035b83d-bbb5-4108-9a46-d4e0e4923ffb","request":{"subtype":"mcp_message","server_name":"byre","message":{"method":"tools/list","jsonrpc":"2.0","id":1}}}} +{"dir":"send","msg":{"response":{"request_id":"4035b83d-bbb5-4108-9a46-d4e0e4923ffb","response":{"mcp_response":{"jsonrpc":"2.0","id":1,"result":{"tools":[{"name":"finish","description":"Call this once the task is complete.","inputSchema":{"type":"object","properties":{}}}]}}},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP628460560/001","session_id":"23b17814-7a1c-453b-9665-5dac4f60b4a4","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","LSP","Monitor","NotebookEdit","PushNotification","Read","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write","mcp__byre__finish"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"pending","source":"claudeai"},{"name":"claude.ai Heliosian","status":"pending","source":"claudeai"},{"name":"claude.ai Fastmail","status":"pending","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"},{"name":"byre","status":"connected","source":"sdk"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"576872a3-186e-4567-aa15-45c9e6d96725","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP628460560-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP628460560-001/23b17814-7a1c-453b-9665-5dac4f60b4a4/scratchpad","messaging_socket_path":"/tmp/cc-socks/2404.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"23b17814-7a1c-453b-9665-5dac4f60b4a4","uuid":"6c7f7e12-df2d-4d9a-9557-fb69733e5fa0"}} +{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.01,"resetsAt":1792054200},"seven_day":{"utilization":0.34,"resetsAt":1792270800}}},"uuid":"19d48949-e063-4a11-b091-792b0c45f298","session_id":"23b17814-7a1c-453b-9665-5dac4f60b4a4"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3MyvQSfRAgihbviGPqt","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01UWqhkEafC7X1MGBZV14316","name":"Write","input":{"file_path":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP628460560/001/hello.txt","content":"hi"},"caller":{"type":"direct"}}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15289,"cache_read_input_tokens":22425,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15289},"output_tokens":16,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"23b17814-7a1c-453b-9665-5dac4f60b4a4","uuid":"d5e5d4f3-7373-4a54-b8fc-bf3ad4a116d9","timestamp":"2026-10-15T04:06:14.851Z","request_id":"req_011Cg3Myv9KQFRuK9SLr9RDP","wire_tool_inputs":{"toolu_01UWqhkEafC7X1MGBZV14316":{"file_path":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP628460560/001/hello.txt","content":"hi"}}}} +{"dir":"recv","msg":{"type":"control_request","request_id":"1989ee1d-ec28-4754-b3d7-1910dd9686b4","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"23b17814-7a1c-453b-9665-5dac4f60b4a4","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP628460560-001/23b17814-7a1c-453b-9665-5dac4f60b4a4.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP628460560/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP628460560-001/23b17814-7a1c-453b-9665-5dac4f60b4a4/scratchpad","prompt_id":"cd9c7b99-164e-4dc6-a723-32cbae14bb23","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"PostToolUse","tool_name":"Write","tool_input":{"file_path":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP628460560/001/hello.txt","content":"hi"},"tool_response":{"type":"create","filePath":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP628460560/001/hello.txt","content":"hi","structuredPatch":[],"originalFile":null,"userModified":false},"tool_use_id":"toolu_01UWqhkEafC7X1MGBZV14316","duration_ms":2},"tool_use_id":"toolu_01UWqhkEafC7X1MGBZV14316"}}} +{"dir":"send","msg":{"response":{"request_id":"1989ee1d-ec28-4754-b3d7-1910dd9686b4","response":{},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01UWqhkEafC7X1MGBZV14316","type":"tool_result","content":"File created successfully at: /private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP628460560/001/hello.txt (file state is current in your context — no need to Read it back)"}]},"parent_tool_use_id":null,"session_id":"23b17814-7a1c-453b-9665-5dac4f60b4a4","uuid":"d1e7e33d-9b4a-4a4d-a407-a33adcc5c29d","timestamp":"2026-10-15T04:06:14.862Z","tool_use_result":{"type":"create","filePath":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP628460560/001/hello.txt","content":"hi","structuredPatch":[],"originalFile":null,"userModified":false},"tool_result_meta":[{"id":"toolu_01UWqhkEafC7X1MGBZV14316","permission_decision":{"decision":"accept","source":"config","reason_type":"mode"}}]}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"23b17814-7a1c-453b-9665-5dac4f60b4a4","uuid":"46af7992-353f-4649-86ba-e2fed828548e"}} +{"dir":"recv","msg":{"type":"system","subtype":"thinking_tokens","estimated_tokens":50,"estimated_tokens_delta":50,"session_id":"23b17814-7a1c-453b-9665-5dac4f60b4a4","uuid":"b4b9e281-39c0-4952-b4ff-79a747278f4e"}} +{"dir":"recv","msg":{"type":"system","subtype":"thinking_tokens","estimated_tokens":150,"estimated_tokens_delta":100,"session_id":"23b17814-7a1c-453b-9665-5dac4f60b4a4","uuid":"67ce85e1-8666-463f-85d3-6181aac45191"}} +{"dir":"recv","msg":{"type":"system","subtype":"thinking_tokens","estimated_tokens":340,"estimated_tokens_delta":190,"session_id":"23b17814-7a1c-453b-9665-5dac4f60b4a4","uuid":"4f0ce0ca-5413-42e6-a706-51d7b72da070"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3Mz5F1JKpnakSqYsFLi","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSyAoKEAgSGAI4AUIIdGhpbmtpbmcSDCFEoCWYANvWHPfuLRoMoPhiefkTtgf+dzwWIjA3YbNYWIFXGhoLfCEp2Mrq8wfAGZiRFY7uMeBBsZ2gxRq3BsGWSjaGg6IF1eztJEsq5QmBRb/0xzuy0THZW4LyJ4iXxS7dDzUi+aO0sHL8P3HqoUa6pcX5yfjq2lFf6praz1Rb4tjUOFLYY6ysB3TCSQsKOEwSlQK7LfmbnQHZKknhEBcgB7W52ACRmGpbHg0NEfqKdPxoEtAfRzCtkpHIr7qCSpND4eysoGkMat+z2kIf2FLN/mbPyVMcsjolD41hB03cW/jkVkhbRzfO3qIytUKu7AX8XmDw/QsbMLMwzc1Yg31rlNY9lLtjxoq1VD9NGbh4/43I1l+PwdU6+X31oSaW6IS/bkuteogE1tW6nyY4D4J6OinNnJKtDBovb2T5qTER/CdUkfWRPj2zUWaNym9vG1LtgFSXLFNuJis6BuUc95q9IE1kdKEtY6CLw0DkyimqXXiV085NPgOqcYbOOmS4Q1Tvilxj2OGnEFGTlp6BTN/q99SXGIvzHOOsV4Uvop8Jy5FSTvqu5zNc3EjNWuKbICkPbDNqJZD8NfmRsLFWXFx58ZKN8tr4i7VHruTclkr/lcDdizQzMixQqjGWBNG7dMHU2hb+Bz3bHwGegdEZVUxHYv+yhTErwm2azIOixCutpSdljQfZ6ymOgA72Yl99P/lqhWEENSLggoIWBbxX45FSPYDeREtxnu2SZ2F+T4vI3codSoizCezFiSqcuc2sP7sMX3l0fyDq4T2Oj6quCrTdYb8cxAMGMQkMud0IoT1HjJ+Z03thAQxx6b8FP9dhGDvOTS8td/wC3mrRO+j3wTmszg01ptHibbFlY4dWKWa4FziooOusAM5aXzpIWgEsM8Ok2gMIKvDwYtZMlmLuSa0jjPkBmEeBhAFQg2zQYelO5mgFKs86V6ovz25FN3nJOlWAMRGu4fVaCmMS4oi048B3T3ii2T4bPvFrBDE5P34qKCk/eP0SO5965ZvIqEONX9M6+JtM385UorM3qpStPUtGzDKfSJMH00Ps5U5envDYkZCAxlFvLfL0u0sl/NaqNQ92H1gyGQf0j43+ijyGm42RAONr/aEfu8nydYBgjepr/Kjg979mMLZ5nxMZRcRqjj+gVHvYyjgMvfeYksjl7GAAGWulcnIT1+2VL4fhibTI+sfb4mUfvJtHEGMOgXch58dHkwqhBadzBHH7DPe6tA9nr03GonHKl+0wg5QmIwxihADMMwsgSOrxBJgPNROVjRQcIZFBwc6d2hmR66q7KoKa0FIZ/a/YGkZ6omZDn5KOi0CmDhqJTB5Ig49FGAzE+yasyN6o+mTGl3YYubOo2AyBFQmWgsOp9sf4CKZdvd4Ye5b97EU6N+U4UChOhfLwwfPATZhfv97g/p37IKnnJ8StmuaRVk3A7OcJE+C3F1GLdRZpie2f2gQZzp3NdtMImcgNCTi4OsvoujCwS8Q2wIBOFSed9i2ULYgW6o+qZYsiuEy+kDt+gimNkfd/ramKN8YupN2tJx+C/xgYyPBdqUUPD0CYne6MRxfLZPh+epHF8kcmCbWQqI9R/BXJOXVInmInrl7fdX2dTkFDUw4xP08IfnvnrjBAZ8yqFUNYa6ohR/LDFi1b36KR5pDMhKpKRDJqeVUGbbgg+YHNiO/WE9OOWu8SjICFy0gq4PXWqIW6XYUOArYb3c9YQWOjyvUlNHxEMgkhsmAfEdZWR/A6uV8nCJZ7iLY538w+jx2prQ7OtZ6/AxgB"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4712,"cache_read_input_tokens":37714,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4712},"output_tokens":3,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"23b17814-7a1c-453b-9665-5dac4f60b4a4","uuid":"9ae55332-c8ca-4cfb-9cfa-de7b73b5c1c8","timestamp":"2026-10-15T04:06:18.735Z","request_id":"req_011Cg3Mz4y8fXHiMzzGcc663","thinking_duration_ms":2939,"thinking_display":"updates"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3Mz5F1JKpnakSqYsFLi","type":"message","role":"assistant","content":[{"type":"text","text":"Authorization for the commit is your words in this turn: \"git add and git commit it with the message \"add hello\"\"."}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4712,"cache_read_input_tokens":37714,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4712},"output_tokens":3,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"23b17814-7a1c-453b-9665-5dac4f60b4a4","uuid":"2dcf4d1f-aa1e-457f-b0fa-fdec2ba332db","timestamp":"2026-10-15T04:06:18.741Z","request_id":"req_011Cg3Mz4y8fXHiMzzGcc663"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3Mz5F1JKpnakSqYsFLi","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_016ANo9CMFgreMuCLwua6WbT","name":"Bash","input":{"command":"git add hello.txt","description":"Stage hello.txt","timeout":15000},"caller":{"type":"direct"}}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4712,"cache_read_input_tokens":37714,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4712},"output_tokens":3,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"23b17814-7a1c-453b-9665-5dac4f60b4a4","uuid":"71428f1b-c1ec-46fd-9a46-bce9d74aeab1","timestamp":"2026-10-15T04:06:19.140Z","request_id":"req_011Cg3Mz4y8fXHiMzzGcc663","wire_tool_inputs":{"toolu_016ANo9CMFgreMuCLwua6WbT":{"command":"git add hello.txt","timeout":15000,"description":"Stage hello.txt"}}}} +{"dir":"recv","msg":{"type":"control_request","request_id":"bbb6f009-4b68-4d12-aa44-88e7d0ce87d6","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"23b17814-7a1c-453b-9665-5dac4f60b4a4","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP628460560-001/23b17814-7a1c-453b-9665-5dac4f60b4a4.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP628460560/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP628460560-001/23b17814-7a1c-453b-9665-5dac4f60b4a4/scratchpad","prompt_id":"cd9c7b99-164e-4dc6-a723-32cbae14bb23","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"PostToolUse","tool_name":"Bash","tool_input":{"command":"git add hello.txt","timeout":15000,"description":"Stage hello.txt"},"tool_response":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"tool_use_id":"toolu_016ANo9CMFgreMuCLwua6WbT","duration_ms":70},"tool_use_id":"toolu_016ANo9CMFgreMuCLwua6WbT"}}} +{"dir":"send","msg":{"response":{"request_id":"bbb6f009-4b68-4d12-aa44-88e7d0ce87d6","response":{},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_016ANo9CMFgreMuCLwua6WbT","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"parent_tool_use_id":null,"session_id":"23b17814-7a1c-453b-9665-5dac4f60b4a4","uuid":"41ab4576-8f03-4cee-81dc-d091b1000f87","timestamp":"2026-10-15T04:06:19.250Z","tool_use_result":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"tool_result_meta":[{"id":"toolu_016ANo9CMFgreMuCLwua6WbT","permission_decision":{"decision":"accept","source":"config","reason_type":"mode"}}]}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"23b17814-7a1c-453b-9665-5dac4f60b4a4","uuid":"33b9f4f6-dbfd-4c0c-ba54-0d6666bb740b"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3MzPytJWC6jgmrpCJiU","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_011tFGBf5SFsHJAA9ejZ6tgD","name":"Bash","input":{"command":"git -c user.email=git@flamingcow.io commit -m \"add hello\" -- hello.txt # USER EXPLICITLY AUTHORIZED THIS COMMIT IN THE IMMEDIATELY PRECEDING REQUEST","description":"Commit hello.txt","timeout":15000},"caller":{"type":"direct"}}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":464,"cache_read_input_tokens":42426,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":464},"output_tokens":16,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"23b17814-7a1c-453b-9665-5dac4f60b4a4","uuid":"a3c3704d-23d9-4105-aacc-1af1576bc740","timestamp":"2026-10-15T04:06:20.820Z","request_id":"req_011Cg3MzPhmcGy2wj96tRBG4","wire_tool_inputs":{"toolu_011tFGBf5SFsHJAA9ejZ6tgD":{"command":"git -c user.email=git@flamingcow.io commit -m \"add hello\" -- hello.txt # USER EXPLICITLY AUTHORIZED THIS COMMIT IN THE IMMEDIATELY PRECEDING REQUEST","timeout":15000,"description":"Commit hello.txt"}}}} +{"dir":"recv","msg":{"type":"system","subtype":"vcs_state_changed","kind":"commit","branch":"main","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP628460560/001","uuid":"0f448e1d-d066-4feb-9b7c-b1e37cfe275d","session_id":"23b17814-7a1c-453b-9665-5dac4f60b4a4"}} +{"dir":"recv","msg":{"type":"control_request","request_id":"fe580a25-4b30-4911-b448-3c02c5f3f034","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"23b17814-7a1c-453b-9665-5dac4f60b4a4","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP628460560-001/23b17814-7a1c-453b-9665-5dac4f60b4a4.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP628460560/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP628460560-001/23b17814-7a1c-453b-9665-5dac4f60b4a4/scratchpad","prompt_id":"cd9c7b99-164e-4dc6-a723-32cbae14bb23","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"PostToolUse","tool_name":"Bash","tool_input":{"command":"git -c user.email=git@flamingcow.io commit -m \"add hello\" -- hello.txt # USER EXPLICITLY AUTHORIZED THIS COMMIT IN THE IMMEDIATELY PRECEDING REQUEST","timeout":15000,"description":"Commit hello.txt"},"tool_response":{"stdout":"[main 1c744ce] add hello\n 1 file changed, 1 insertion(+)\n create mode 100644 hello.txt","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false,"gitOperation":{"commit":{"sha":"1c744ce","kind":"committed","branch":"main"}}},"tool_use_id":"toolu_011tFGBf5SFsHJAA9ejZ6tgD","duration_ms":38},"tool_use_id":"toolu_011tFGBf5SFsHJAA9ejZ6tgD"}}} +{"dir":"send","msg":{"response":{"request_id":"fe580a25-4b30-4911-b448-3c02c5f3f034","response":{},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_011tFGBf5SFsHJAA9ejZ6tgD","type":"tool_result","content":"[main 1c744ce] add hello\n 1 file changed, 1 insertion(+)\n create mode 100644 hello.txt","is_error":false}]},"parent_tool_use_id":null,"session_id":"23b17814-7a1c-453b-9665-5dac4f60b4a4","uuid":"b317d57a-ceef-4644-b44a-3909479fffc3","timestamp":"2026-10-15T04:06:20.899Z","tool_use_result":{"stdout":"[main 1c744ce] add hello\n 1 file changed, 1 insertion(+)\n create mode 100644 hello.txt","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false,"gitOperation":{"commit":{"sha":"1c744ce","kind":"committed","branch":"main"}}},"tool_result_meta":[{"id":"toolu_011tFGBf5SFsHJAA9ejZ6tgD","permission_decision":{"decision":"accept","source":"config","reason_type":"mode"}}]}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"23b17814-7a1c-453b-9665-5dac4f60b4a4","uuid":"9cf799d6-c405-4024-9547-b30fe9c885a5"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3MzX4nUU1TGzW9uxrt7","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Sdu7ac1MUYxNDgmjzjx4dH","name":"mcp__byre__finish","input":{},"caller":{"type":"direct"}}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":253,"cache_read_input_tokens":42890,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":253},"output_tokens":24,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"23b17814-7a1c-453b-9665-5dac4f60b4a4","uuid":"72a5e927-525c-4d5d-a49d-b43fef090ad3","timestamp":"2026-10-15T04:06:21.994Z","request_id":"req_011Cg3MzWjvtgC9GvXxE9F8R","wire_tool_inputs":{"toolu_01Sdu7ac1MUYxNDgmjzjx4dH":{}},"tool_use_meta":[{"id":"toolu_01Sdu7ac1MUYxNDgmjzjx4dH","display_name":"Finish","server_display_name":"byre"}]}} +{"dir":"recv","msg":{"type":"control_request","request_id":"eac1c0c1-4112-4da8-ba9c-cbfdc2dce528","request":{"subtype":"mcp_message","server_name":"byre","message":{"method":"tools/call","params":{"name":"finish","arguments":{},"_meta":{"claudecode/toolUseId":"toolu_01Sdu7ac1MUYxNDgmjzjx4dH","progressToken":2}},"jsonrpc":"2.0","id":2}}}} +{"dir":"send","msg":{"response":{"request_id":"eac1c0c1-4112-4da8-ba9c-cbfdc2dce528","response":{"mcp_response":{"jsonrpc":"2.0","id":2,"result":{"content":[{"type":"text","text":"noted"}]}}},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"control_request","request_id":"60ced7fb-50a8-4bd2-8b71-82ab563daf7c","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"23b17814-7a1c-453b-9665-5dac4f60b4a4","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP628460560-001/23b17814-7a1c-453b-9665-5dac4f60b4a4.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP628460560/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP628460560-001/23b17814-7a1c-453b-9665-5dac4f60b4a4/scratchpad","prompt_id":"cd9c7b99-164e-4dc6-a723-32cbae14bb23","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"PostToolUse","tool_name":"mcp__byre__finish","tool_input":{},"tool_response":[{"type":"text","text":"noted"}],"tool_use_id":"toolu_01Sdu7ac1MUYxNDgmjzjx4dH","duration_ms":14,"mcp_server":{"name":"byre","source":"sdk"}},"tool_use_id":"toolu_01Sdu7ac1MUYxNDgmjzjx4dH"}}} +{"dir":"send","msg":{"response":{"request_id":"60ced7fb-50a8-4bd2-8b71-82ab563daf7c","response":{},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01Sdu7ac1MUYxNDgmjzjx4dH","type":"tool_result","content":[{"type":"text","text":"noted"}]}]},"parent_tool_use_id":null,"session_id":"23b17814-7a1c-453b-9665-5dac4f60b4a4","uuid":"9a5a8412-0496-4b14-a83e-8dc47b46fc07","timestamp":"2026-10-15T04:06:22.018Z","tool_use_result":[{"type":"text","text":"noted"}],"tool_result_meta":[{"id":"toolu_01Sdu7ac1MUYxNDgmjzjx4dH","permission_decision":{"decision":"accept","source":"config","reason_type":"mode"}}]}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"23b17814-7a1c-453b-9665-5dac4f60b4a4","uuid":"95f11ba6-6e2a-474e-9d7f-e4024ab8a328"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3MzbqWviY7LnUBQYATR","type":"message","role":"assistant","content":[{"type":"text","text":"I created `hello.txt` containing `hi`, staged it and committed it on `main` with the message \"add hello\" (commit `1c744ce`). I then called the finish tool.\n\nI set the commit email to `git@flamingcow.io` for that one commit, using `git -c`. I didn't change the repo's git config."}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":63,"cache_read_input_tokens":43143,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":63},"output_tokens":101,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"23b17814-7a1c-453b-9665-5dac4f60b4a4","uuid":"121406d4-4247-4af2-846a-fab33a6831d2","timestamp":"2026-10-15T04:06:23.512Z","request_id":"req_011Cg3Mzbb8YE8kVViRQX4fm"}} +{"dir":"recv","msg":{"duration_api_ms":12103,"stop_reason":"end_turn","session_id":"23b17814-7a1c-453b-9665-5dac4f60b4a4","total_cost_usd":0.11086350000000002,"usage":{"input_tokens":10,"cache_creation_input_tokens":20781,"cache_read_input_tokens":188598,"output_tokens":873,"output_tokens_details":{"thinking_tokens":286},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":20781,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":101,"cache_read_input_tokens":43143,"cache_creation_input_tokens":63,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":63},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1207,"outputTokens":18,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.0001297,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":10,"outputTokens":873,"cacheReadInputTokens":188598,"cacheCreationInputTokens":20781,"webSearchRequests":0,"costUSD":0.11073380000000001,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":286,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":5,"subtype":"success","api_error_status":null,"result":"I created `hello.txt` containing `hi`, staged it and committed it on `main` with the message \"add hello\" (commit `1c744ce`). I then called the finish tool.\n\nI set the commit email to `git@flamingcow.io` for that one commit, using `git -c`. I didn't change the repo's git config.","ttft_ms":2162,"type":"result","duration_ms":10845,"uuid":"2069930a-2ba9-4ff2-9441-cee9f8ffc878","ttft_stream_ms":1255,"time_to_request_ms":24,"first_content_frame_ms":1256,"queued_turn_count":0,"result_index":0}} diff --git a/internal/claude/testdata/transcripts/TestImageInput.jsonl b/internal/claude/testdata/transcripts/TestImageInput.jsonl index 55382e8..d5bb36b 100644 --- a/internal/claude/testdata/transcripts/TestImageInput.jsonl +++ b/internal/claude/testdata/transcripts/TestImageInput.jsonl @@ -1,8 +1,8 @@ -{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_f69e88afb0ab9ff3","type":"control_request"}} -{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_f69e88afb0ab9ff3","response":{"commands":[{"name":"deep-research","description":"Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. (dynamic workflow)","argumentHint":"","builtin":true},{"name":"design","description":"Make a new Design artifact from a brief","argumentHint":"[what to design]","builtin":true},{"name":"slides","description":"Make a new Slides deck artifact from a brief","argumentHint":"[what the deck is about]","builtin":true},{"name":"design-sync","description":"Push a React design system to claude.ai/design. This runs a converter that bundles the real component code (from Storybook or a bare package) and uploads it. Use when the user runs /design-sync or says \"sync my design system to Claude Design\".","argumentHint":"[\u003cproject hint, e.g. \"Acme DS\"\u003e]","builtin":true},{"name":"dataviz","description":"Use this skill whenever you are about to create ANY chart, graph, plot, dashboard, or data visualization, in ANY output medium — an HTML or React artifact, inline SVG, plotting code in any library (matplotlib, plotly, d3, Recharts, …), an image/PNG you will render and upload, or a chart shared into Slack. Read it BEFORE writing the first line of chart code, choosing chart colors, building a stat tile / meter / KPI row, or laying out a dashboard. When the destination is a first-party document connector (host-designated, never self-described) that renders live charts, hand it the rows (inline, or as an uploaded data file the chart cites) rather than a rendered PNG/SVG — a picture of a chart loses hover, data inspection and per-value comments. Produces visualizations that read as one system — elegant, accessible, consistent in light and dark — using a brand-neutral placeholder palette you swap for your own. Teaches a design-system-agnostic method: a form heuristic, a color formula with a runnable validator, mark specs, and interaction rules. A validated default palette is documented in `references/palette.md` — swap that file's values for your brand's. Triggers on: \"chart\", \"graph\", \"plot\", \"data viz\", \"visualization\", \"dashboard\", \"analytics\", \"visualize data\", \"categorical colors\", \"sequential / diverging palette\", \"stat tile\", \"sparkline\", \"heatmap\", \"legend\", \"axis\", \"tooltip\", \"chart colors\", \"color by series\".","argumentHint":"","builtin":true},{"name":"artifact-diagramming","description":"Diagramming know-how for Artifacts - when a picture earns its place, how to draw one that shows the real mechanism, and the inline-SVG mechanics that keep it legible in both themes.","argumentHint":"","builtin":true},{"name":"artifact-capabilities","description":"Runtime capabilities a published Artifact page can be granted — behavior static HTML cannot provide on its own, such as the page reading live or connected data, remembering what people do on it (a poll, a sign-up sheet, a checklist, a document edited in place — it saves new versions of itself), keeping state shared across viewers, knowing who is viewing, asking Claude a question of its own, storing files people add, handing the viewer a file to save, or using the viewer's camera, microphone, location, screen or device motion. Serves this user's live capability roster and the typed call definitions. Load it whenever any such runtime behavior would make an artifact more useful, before writing the page.","argumentHint":"","builtin":true},{"name":"update-config","description":"Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme/model, suggest the /config command.","argumentHint":"","builtin":true},{"name":"verify","description":"Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.","argumentHint":"","builtin":true},{"name":"debug","description":"Enable debug logging for this session and help diagnose issues","argumentHint":"[issue description]","builtin":true},{"name":"code-review","description":"Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep multi-agent review in the cloud); with no level given, it reuses the level you typed last. Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review. Pass --max-findings \u003cn\u003e to report up to n findings, or --max-findings all for every finding. The choice stays until you pass --max-findings default. For ultra on a GitHub.com PR target, --post asks to post the finished review’s findings to the PR as a single comment from the user’s GitHub account (not a review; the launch dialog still confirms in interactive sessions, while non-interactive mode posts on the flag alone) and --no-post hides that option.","argumentHint":"[low|medium|high|xhigh|max|ultra] [--fix] [--comment] [\u003cpr#\u003e|\u003cbranch\u003e|\u003cpath\u003e] [--max-findings \u003cn\u003e|all]","aliases":["review"],"builtin":true},{"name":"simplify","description":"Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.","argumentHint":"[\u003ctarget\u003e]","builtin":true},{"name":"batch","description":"Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.","argumentHint":"\u003cinstruction\u003e","builtin":true},{"name":"fewer-permission-prompts","description":"Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.","argumentHint":"","builtin":true},{"name":"doctor","description":"Health-check the user's Claude Code setup and fix issues: diagnose installation health — what the `claude doctor` terminal diagnostics cover — from local data (duplicate or leftover installs, PATH, unparseable settings files, broken or colliding agent definitions, skills whose frontmatter fails to parse); find unused skills, MCP servers, and plugins versus their context cost and disable dead weight; deduplicate local CLAUDE.md files against checked-in ones; trim checked-in CLAUDE.md files by cutting content a session could derive from the codebase (directory layouts, tech-stack lists, architecture overviews) while keeping gotchas, rationale, and non-standard conventions; migrate always-loaded CLAUDE.md guidance into lazy skills and nested CLAUDE.md files; flag slow hooks and context-heavy extensions; check the installed version is current; make auto mode the default permission mode; and pre-approve frequently denied read-only commands. Use when the user asks for a doctor run, checkup, audit, tune-up, or cleanup of their Claude Code setup or configuration.","argumentHint":"[prompt-audit [\u003cpath\u003e]]","aliases":["checkup"],"builtin":true},{"name":"loop","description":"Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.","argumentHint":"[interval] [prompt]","aliases":["proactive"],"builtin":true},{"name":"schedule","description":"Create, update, list, or run scheduled cloud agents (routines) that execute on a cron schedule.","argumentHint":"","aliases":["routines"],"builtin":true},{"name":"claude-api","description":"Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).","argumentHint":"","builtin":true},{"name":"workflow-authoring","description":"Reference for writing a Workflow tool script (script API and gotchas, resume, quality patterns, worked examples). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.","argumentHint":"","builtin":true},{"name":"run","description":"Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).","argumentHint":"","builtin":true},{"name":"run-skill-generator","description":"Author or improve the run-\u003cunit\u003e skill - a per-project skill that tells agents how to build, launch, and drive this project's app. Use when the user asks to set up the project, get it running, write run instructions, or verify build/run steps work from a clean environment.","argumentHint":"","builtin":true},{"name":"plugin-authoring","description":"Make a mod: a change to Claude's own interface or behaviour, such as a live pane or panel, a band above the prompt, a status line, a toast, a slash command, or a hook on tool calls or prompts. Use to make, change or debug a mod or its hooks module.","argumentHint":"","builtin":true},{"name":"advisor","description":"Let Claude consult a stronger model at key moments","argumentHint":"[fable|opus|sonnet|off]","builtin":true},{"name":"agents","description":"(removed) Ask Claude to create/manage subagents, or edit .claude/agents/","argumentHint":"","builtin":true},{"name":"auto-mode-setup","description":"Teach auto mode about your environment, plus optional rule tweaks","argumentHint":"[--request-id \u003cuuid\u003e] (--wizard posture=… scope=… depth=… --propose | --expect-sha256 \u003c64-hex\u003e --apply-file \u003cpath\u003e)","builtin":true},{"name":"autocompact","description":"Configure the auto-compact window size","argumentHint":"[auto|\u003ctokens\u003e]","builtin":true},{"name":"clear","description":"Start a new session with empty context; previous session stays on disk (resumable with /resume)","argumentHint":"[name]","aliases":["reset","new"],"builtin":true},{"name":"color","description":"Set the prompt bar color for this session","argumentHint":"[red|blue|green|yellow|purple|orange|pink|cyan|default]","builtin":true},{"name":"compact","description":"Free up context by summarizing the conversation so far","argumentHint":"\u003coptional custom summarization instructions\u003e","builtin":true},{"name":"config","description":"Set a setting by key","argumentHint":"key=value","aliases":["settings"],"builtin":true},{"name":"output-style","description":"List output styles or switch to one","argumentHint":"[style]","builtin":true},{"name":"context","description":"Show current context usage","argumentHint":"","builtin":true},{"name":"effort","description":"Set effort level for model usage","argumentHint":"\u003clow|medium|high|xhigh|max|auto|ultracode [on|off]\u003e","builtin":true},{"name":"fast","description":"Toggle fast mode (Opus 5.5)","argumentHint":"[on|off]","builtin":true},{"name":"focus","description":"Toggle focus view: just your prompt, summary, and response","argumentHint":"[on|off]","builtin":true},{"name":"heapdump","description":"Dump the JS heap to the Desktop; on Linux with no Desktop folder, the home directory","argumentHint":"","builtin":true},{"name":"init","description":"Initialize a new CLAUDE.md file with codebase documentation","argumentHint":"","builtin":true},{"name":"mcp","description":"Manage MCP servers","argumentHint":"[reconnect|enable|disable [\u003cserver\u003e|all]]","builtin":true},{"name":"import","description":"Import config from another AI coding agent","argumentHint":"","builtin":true},{"name":"model","description":"Set the AI model for Claude Code","argumentHint":"\u003cmodel\u003e","builtin":true},{"name":"__remote-workflow","description":"Run the workflow script delivered in this session environment (server-launched sessions only)","argumentHint":"","builtin":true},{"name":"workflow-launch-exec","description":"Execute a server-launched workflow handoff (workflow_launch event sessions only)","argumentHint":"","builtin":true},{"name":"reload-plugins","description":"Activate pending plugin changes in the current session","argumentHint":"[--force]","builtin":true},{"name":"reload-skills","description":"Pick up skills added or changed on disk during this session","argumentHint":"","builtin":true},{"name":"rename","description":"Rename the current conversation","argumentHint":"[name]","aliases":["name"],"builtin":true},{"name":"ultrareview","description":"Start a cloud agent that finds and verifies bugs in your branch (~15-25 min, $5-$25 USD) · Runs in a cloud session. See https://code.claude.com/docs/en/claude-code-on-the-web","argumentHint":"","builtin":true},{"name":"security-review","description":"Complete a security review of the pending changes on the current branch","argumentHint":"","builtin":true},{"name":"usage-credits","description":"Configure usage credits or request them from your admin when you hit a limit","argumentHint":"","builtin":true},{"name":"extra-usage","description":"Renamed to /usage-credits","argumentHint":"","builtin":true},{"name":"usage","description":"Show session cost, plan usage, and what's contributing to your limits","argumentHint":"","aliases":["cost","stats"],"builtin":true},{"name":"insights","description":"Generate a report analyzing your Claude Code sessions","argumentHint":"","builtin":true},{"name":"recap","description":"Generate a one-line session recap now","argumentHint":"","builtin":true},{"name":"skill-doctor","description":"Show which loaded skills are unused and costing context","argumentHint":"","builtin":true},{"name":"goal","description":"Set a goal — keep working until the condition is met","argumentHint":"","builtin":true},{"name":"design-consent","description":"Grant Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"design-revoke","description":"Revoke Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"list-agents","description":"List subagents, teammates, and other Claude sessions you can message","argumentHint":"","aliases":["peers"],"builtin":true},{"name":"team-onboarding","description":"Help teammates ramp on Claude Code with a guide from your usage","argumentHint":"","builtin":true},{"name":"docs","description":"docs (editable docs people share and comment on; the default for any document, named as a doc or not: a document, report, proposal, resume, cover letter, letter, contract, policy, form, template, worksheet, essay, handbook, guide, how-to, cheat sheet, SOP or other writing to keep, share, collaborate on, send, submit, print or sign; a doc exports to Word, PDF, Markdown or Google Docs, so needing a file to send, attach, upload, submit or print is no reason to pick Word, and a file nobody asked for is a doc, not Word; a plan, comparison, summary or notes asked in chat stays in chat; a pasted claude.ai artifact link may be a doc: check with docs tools first; Word or another file format named, tracked changes wanted, or a .docx to change or use as a template → that format's skill): making one → if no docs-connector instructions are in context, call its `guide` (topic.instructions) first; then create the doc (headings only, no body) before any search, file read or plan, even with files attached. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docs"]},{"name":"docx","description":"Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers include: any mention of Microsoft Word Documents, such as 'Word doc', 'word document', '.docx', '.dotx', 'microsoft doc'. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a deliverable as a Word or .docx file (to download, email or print), use this skill. However, if they ask for a document, page, report, memo, or notes WITHOUT naming a file format and the session offers Claude's own dedicated document or page skill or connector, use that instead, even if they will email or print it. Do NOT use for PDFs, spreadsheets, Google Docs, or coding unrelated to document generation. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docx"]},{"name":"google-workspace","description":"Read this before the first Google Drive, Docs, Sheets or Slides connector call whenever the task creates or changes a Google file. Use this skill whenever the user wants to create or change a Google Doc, Sheet or Slides file in their Google Drive. Triggers include: a request that names Google Docs, Sheets, Slides or Drive and asks to make, edit, format, copy or rename a file; a docs.google.com link with a request to change that file, even a one-line fix or suggested edits; and any follow-up change to a Google file from earlier in the chat, even \"change it\" or \"add a tab\". Includes helper scripts for document positions, cell ranges and slide layout. However, if the user asks for a doc, deck or spreadsheet without naming Google, or gives a Google file only as source material for something new, use Claude's own output type instead. Do NOT use for read-only questions about a Google file, or for Word, Excel, PowerPoint or PDF files. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:google-workspace"]},{"name":"import-memory","description":"Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:import-memory"]},{"name":"morning","description":"Render the user's morning brief as a styled HTML artifact, or set it up as a recurring weekday task. Use only when the user explicitly asks to run, see, or set up their morning brief, or if they invoke /morning by name. A question about their day, schedule, or calendar is not by itself a request for the brief; answer it directly instead. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:morning"]},{"name":"pdf","description":"Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pdf"]},{"name":"pptx","description":"Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations as PowerPoint (.pptx) files; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email, summary, or creating a different type of slide deck); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user asks for a PowerPoint or .pptx file, or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. However, when the user asks for a deck, slides, a slide deck, or a presentation without naming a file format, default to using a dedicated slide-deck artifact type or a separate slides skill if this session offers one; otherwise, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pptx"]},{"name":"skill-creator","description":"Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:skill-creator"]},{"name":"xlsx","description":"Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:xlsx"]}],"agents":[{"name":"claude","description":"Catch-all for any task that doesn't fit a more specific agent. FleetView's default when no agent name is typed."},{"name":"claude-code-guide","description":"Use this agent when the user asks questions (\"Can Claude...\", \"Does Claude...\", \"How do I...\") about: (1) Claude Code (the CLI tool) - features, hooks, slash commands, MCP servers, settings, IDE integrations, keyboard shortcuts; (2) Claude Agent SDK - building custom agents; (3) Claude API (formerly Anthropic API) - Messages API for directly passing messages to Claude, Tool Runner (`client.beta.messages.tool_runner`) for running an agentic loop over your own tools, manual tool-use loops, Managed Agents for server-hosted agents with a managed sandbox, prompt caching, and general Anthropic SDK usage; (4) Claude Tag (Claude in Slack) - what it is, setting it up for a Slack workspace, `/install-slack-app`; (5) `claude plugin eval` (writing and running plugin eval suites, its JSON/report, sandbox, CI) and the `/skill-doctor` report. **IMPORTANT:** Before spawning a new agent, check if there is already a running or recently completed claude-code-guide agent that you can continue via SendMessage.","model":"haiku"},{"name":"Explore","description":"Fast read-only search agent for locating code. Use it to find files by pattern (eg. \"src/components/**/*.tsx\"), grep for symbols or keywords (eg. \"API endpoints\"), or answer \"where is X defined / which files reference Y.\" Do NOT use it for code review, design-doc auditing, cross-file consistency checks, or open-ended analysis — it reads excerpts rather than whole files and will miss content past its read window. When calling, specify search breadth: \"quick\" for a single targeted lookup, \"medium\" for moderate exploration, or \"very thorough\" to search across multiple locations and naming conventions.","model":"inherit"},{"name":"general-purpose","description":"General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you."},{"name":"Plan","description":"Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs.","model":"inherit"},{"name":"statusline-setup","description":"Use this agent to configure the user's Claude Code status line setting.","model":"sonnet"}],"output_style":"default","available_output_styles":["default","Proactive","Concise","Explanatory","Learning"],"user_output_styles_dir":"/Users/flamingcow/.claude/output-styles","models":[{"value":"default","resolvedModel":"claude-opus-5-5","displayName":"Default (recommended)","description":"Opus 5.5 · Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"opus","resolvedModel":"claude-opus-5-5","displayName":"Opus 5.5","description":"For complex work and everyday tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"fable","resolvedModel":"claude-fable-5-1","displayName":"Fable 5.1","description":"For your toughest challenges","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"sonnet","resolvedModel":"claude-sonnet-5-5","displayName":"Sonnet 5.5","description":"Most efficient for simpler tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"haiku","resolvedModel":"claude-haiku-5-5","displayName":"Haiku 5.5","description":"Fastest for quick answers","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-haiku-4-5-20251001","resolvedModel":"claude-haiku-4-5-20251001","displayName":"Haiku 4.5","description":"Fastest for quick answers"},{"value":"claude-sonnet-5","resolvedModel":"claude-sonnet-5","displayName":"Sonnet 5","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-5","resolvedModel":"claude-opus-5","displayName":"Opus 5","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-fable-5","resolvedModel":"claude-fable-5","displayName":"Fable 5","description":"Most capable for your hardest and longest-running tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-8","resolvedModel":"claude-opus-4-8","displayName":"Opus 4.8","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-opus-4-7","resolvedModel":"claude-opus-4-7","displayName":"Opus 4.7","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-6","resolvedModel":"claude-opus-4-6","displayName":"Opus 4.6","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-sonnet-4-6","resolvedModel":"claude-sonnet-4-6","displayName":"Sonnet 4.6","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true}],"account":{"email":"[redacted]","organization":"[redacted]'s Organization","subscriptionType":"Claude Max","apiProvider":"firstParty"},"pid":98366,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} +{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_fd22fa81289020a0","type":"control_request"}} +{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_fd22fa81289020a0","response":{"commands":[{"name":"deep-research","description":"Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. (dynamic workflow)","argumentHint":"","builtin":true},{"name":"design","description":"Make a new Design artifact from a brief","argumentHint":"[what to design]","builtin":true},{"name":"slides","description":"Make a new Slides deck artifact from a brief","argumentHint":"[what the deck is about]","builtin":true},{"name":"design-sync","description":"Push a React design system to claude.ai/design. This runs a converter that bundles the real component code (from Storybook or a bare package) and uploads it. Use when the user runs /design-sync or says \"sync my design system to Claude Design\".","argumentHint":"[\u003cproject hint, e.g. \"Acme DS\"\u003e]","builtin":true},{"name":"dataviz","description":"Use this skill whenever you are about to create ANY chart, graph, plot, dashboard, or data visualization, in ANY output medium — an HTML or React artifact, inline SVG, plotting code in any library (matplotlib, plotly, d3, Recharts, …), an image/PNG you will render and upload, or a chart shared into Slack. Read it BEFORE writing the first line of chart code, choosing chart colors, building a stat tile / meter / KPI row, or laying out a dashboard. When the destination is a first-party document connector (host-designated, never self-described) that renders live charts, hand it the rows (inline, or as an uploaded data file the chart cites) rather than a rendered PNG/SVG — a picture of a chart loses hover, data inspection and per-value comments. Produces visualizations that read as one system — elegant, accessible, consistent in light and dark — using a brand-neutral placeholder palette you swap for your own. Teaches a design-system-agnostic method: a form heuristic, a color formula with a runnable validator, mark specs, and interaction rules. A validated default palette is documented in `references/palette.md` — swap that file's values for your brand's. Triggers on: \"chart\", \"graph\", \"plot\", \"data viz\", \"visualization\", \"dashboard\", \"analytics\", \"visualize data\", \"categorical colors\", \"sequential / diverging palette\", \"stat tile\", \"sparkline\", \"heatmap\", \"legend\", \"axis\", \"tooltip\", \"chart colors\", \"color by series\".","argumentHint":"","builtin":true},{"name":"artifact-diagramming","description":"Diagramming know-how for Artifacts - when a picture earns its place, how to draw one that shows the real mechanism, and the inline-SVG mechanics that keep it legible in both themes.","argumentHint":"","builtin":true},{"name":"artifact-capabilities","description":"Runtime capabilities a published Artifact page can be granted — behavior static HTML cannot provide on its own, such as the page reading live or connected data, remembering what people do on it (a poll, a sign-up sheet, a checklist, a document edited in place — it saves new versions of itself), keeping state shared across viewers, knowing who is viewing, asking Claude a question of its own, storing files people add, handing the viewer a file to save, or using the viewer's camera, microphone, location, screen or device motion. Serves this user's live capability roster and the typed call definitions. Load it whenever any such runtime behavior would make an artifact more useful, before writing the page.","argumentHint":"","builtin":true},{"name":"update-config","description":"Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme/model, suggest the /config command.","argumentHint":"","builtin":true},{"name":"verify","description":"Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.","argumentHint":"","builtin":true},{"name":"debug","description":"Enable debug logging for this session and help diagnose issues","argumentHint":"[issue description]","builtin":true},{"name":"code-review","description":"Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep multi-agent review in the cloud); with no level given, it reuses the level you typed last. Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review. Pass --max-findings \u003cn\u003e to report up to n findings, or --max-findings all for every finding. The choice stays until you pass --max-findings default. For ultra on a GitHub.com PR target, --post asks to post the finished review’s findings to the PR as a single comment from the user’s GitHub account (not a review; the launch dialog still confirms in interactive sessions, while non-interactive mode posts on the flag alone) and --no-post hides that option.","argumentHint":"[low|medium|high|xhigh|max|ultra] [--fix] [--comment] [\u003cpr#\u003e|\u003cbranch\u003e|\u003cpath\u003e] [--max-findings \u003cn\u003e|all]","aliases":["review"],"builtin":true},{"name":"simplify","description":"Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.","argumentHint":"[\u003ctarget\u003e]","builtin":true},{"name":"batch","description":"Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.","argumentHint":"\u003cinstruction\u003e","builtin":true},{"name":"fewer-permission-prompts","description":"Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.","argumentHint":"","builtin":true},{"name":"doctor","description":"Health-check the user's Claude Code setup and fix issues: diagnose installation health — what the `claude doctor` terminal diagnostics cover — from local data (duplicate or leftover installs, PATH, unparseable settings files, broken or colliding agent definitions, skills whose frontmatter fails to parse); find unused skills, MCP servers, and plugins versus their context cost and disable dead weight; deduplicate local CLAUDE.md files against checked-in ones; trim checked-in CLAUDE.md files by cutting content a session could derive from the codebase (directory layouts, tech-stack lists, architecture overviews) while keeping gotchas, rationale, and non-standard conventions; migrate always-loaded CLAUDE.md guidance into lazy skills and nested CLAUDE.md files; flag slow hooks and context-heavy extensions; check the installed version is current; make auto mode the default permission mode; and pre-approve frequently denied read-only commands. Use when the user asks for a doctor run, checkup, audit, tune-up, or cleanup of their Claude Code setup or configuration.","argumentHint":"[prompt-audit [\u003cpath\u003e]]","aliases":["checkup"],"builtin":true},{"name":"loop","description":"Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.","argumentHint":"[interval] [prompt]","aliases":["proactive"],"builtin":true},{"name":"schedule","description":"Create, update, list, or run scheduled cloud agents (routines) that execute on a cron schedule.","argumentHint":"","aliases":["routines"],"builtin":true},{"name":"claude-api","description":"Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).","argumentHint":"","builtin":true},{"name":"workflow-authoring","description":"Reference for writing a Workflow tool script (script API and gotchas, resume, quality patterns, worked examples). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.","argumentHint":"","builtin":true},{"name":"run","description":"Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).","argumentHint":"","builtin":true},{"name":"run-skill-generator","description":"Author or improve the run-\u003cunit\u003e skill - a per-project skill that tells agents how to build, launch, and drive this project's app. Use when the user asks to set up the project, get it running, write run instructions, or verify build/run steps work from a clean environment.","argumentHint":"","builtin":true},{"name":"plugin-authoring","description":"Make a mod: a change to Claude's own interface or behaviour, such as a live pane or panel, a band above the prompt, a status line, a toast, a slash command, or a hook on tool calls or prompts. Use to make, change or debug a mod or its hooks module.","argumentHint":"","builtin":true},{"name":"advisor","description":"Let Claude consult a stronger model at key moments","argumentHint":"[fable|opus|sonnet|off]","builtin":true},{"name":"agents","description":"(removed) Ask Claude to create/manage subagents, or edit .claude/agents/","argumentHint":"","builtin":true},{"name":"auto-mode-setup","description":"Teach auto mode about your environment, plus optional rule tweaks","argumentHint":"[--request-id \u003cuuid\u003e] (--wizard posture=… scope=… depth=… --propose | --expect-sha256 \u003c64-hex\u003e --apply-file \u003cpath\u003e)","builtin":true},{"name":"autocompact","description":"Configure the auto-compact window size","argumentHint":"[auto|\u003ctokens\u003e]","builtin":true},{"name":"clear","description":"Start a new session with empty context; previous session stays on disk (resumable with /resume)","argumentHint":"[name]","aliases":["reset","new"],"builtin":true},{"name":"color","description":"Set the prompt bar color for this session","argumentHint":"[red|blue|green|yellow|purple|orange|pink|cyan|default]","builtin":true},{"name":"compact","description":"Free up context by summarizing the conversation so far","argumentHint":"\u003coptional custom summarization instructions\u003e","builtin":true},{"name":"config","description":"Set a setting by key","argumentHint":"key=value","aliases":["settings"],"builtin":true},{"name":"output-style","description":"List output styles or switch to one","argumentHint":"[style]","builtin":true},{"name":"context","description":"Show current context usage","argumentHint":"","builtin":true},{"name":"effort","description":"Set effort level for model usage","argumentHint":"\u003clow|medium|high|xhigh|max|auto|ultracode [on|off]\u003e","builtin":true},{"name":"fast","description":"Toggle fast mode (Opus 5.5)","argumentHint":"[on|off]","builtin":true},{"name":"focus","description":"Toggle focus view: just your prompt, summary, and response","argumentHint":"[on|off]","builtin":true},{"name":"heapdump","description":"Dump the JS heap to the Desktop; on Linux with no Desktop folder, the home directory","argumentHint":"","builtin":true},{"name":"init","description":"Initialize a new CLAUDE.md file with codebase documentation","argumentHint":"","builtin":true},{"name":"mcp","description":"Manage MCP servers","argumentHint":"[reconnect|enable|disable [\u003cserver\u003e|all]]","builtin":true},{"name":"import","description":"Import config from another AI coding agent","argumentHint":"","builtin":true},{"name":"model","description":"Set the AI model for Claude Code","argumentHint":"\u003cmodel\u003e","builtin":true},{"name":"__remote-workflow","description":"Run the workflow script delivered in this session environment (server-launched sessions only)","argumentHint":"","builtin":true},{"name":"workflow-launch-exec","description":"Execute a server-launched workflow handoff (workflow_launch event sessions only)","argumentHint":"","builtin":true},{"name":"reload-plugins","description":"Activate pending plugin changes in the current session","argumentHint":"[--force]","builtin":true},{"name":"reload-skills","description":"Pick up skills added or changed on disk during this session","argumentHint":"","builtin":true},{"name":"rename","description":"Rename the current conversation","argumentHint":"[name]","aliases":["name"],"builtin":true},{"name":"ultrareview","description":"Start a cloud agent that finds and verifies bugs in your branch (~15-25 min, $5-$25 USD) · Runs in a cloud session. See https://code.claude.com/docs/en/claude-code-on-the-web","argumentHint":"","builtin":true},{"name":"security-review","description":"Complete a security review of the pending changes on the current branch","argumentHint":"","builtin":true},{"name":"usage-credits","description":"Configure usage credits or request them from your admin when you hit a limit","argumentHint":"","builtin":true},{"name":"extra-usage","description":"Renamed to /usage-credits","argumentHint":"","builtin":true},{"name":"usage","description":"Show session cost, plan usage, and what's contributing to your limits","argumentHint":"","aliases":["cost","stats"],"builtin":true},{"name":"insights","description":"Generate a report analyzing your Claude Code sessions","argumentHint":"","builtin":true},{"name":"recap","description":"Generate a one-line session recap now","argumentHint":"","builtin":true},{"name":"skill-doctor","description":"Show which loaded skills are unused and costing context","argumentHint":"","builtin":true},{"name":"goal","description":"Set a goal — keep working until the condition is met","argumentHint":"","builtin":true},{"name":"design-consent","description":"Grant Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"design-revoke","description":"Revoke Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"list-agents","description":"List subagents, teammates, and other Claude sessions you can message","argumentHint":"","aliases":["peers"],"builtin":true},{"name":"team-onboarding","description":"Help teammates ramp on Claude Code with a guide from your usage","argumentHint":"","builtin":true},{"name":"docs","description":"docs (editable docs people share and comment on; the default for any document, named as a doc or not: a document, report, proposal, resume, cover letter, letter, contract, policy, form, template, worksheet, essay, handbook, guide, how-to, cheat sheet, SOP or other writing to keep, share, collaborate on, send, submit, print or sign; a doc exports to Word, PDF, Markdown or Google Docs, so needing a file to send, attach, upload, submit or print is no reason to pick Word, and a file nobody asked for is a doc, not Word; a plan, comparison, summary or notes asked in chat stays in chat; a pasted claude.ai artifact link may be a doc: check with docs tools first; Word or another file format named, tracked changes wanted, or a .docx to change or use as a template → that format's skill): making one → if no docs-connector instructions are in context, call its `guide` (topic.instructions) first; then create the doc (headings only, no body) before any search, file read or plan, even with files attached. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docs"]},{"name":"docx","description":"Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers include: any mention of Microsoft Word Documents, such as 'Word doc', 'word document', '.docx', '.dotx', 'microsoft doc'. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a deliverable as a Word or .docx file (to download, email or print), use this skill. However, if they ask for a document, page, report, memo, or notes WITHOUT naming a file format and the session offers Claude's own dedicated document or page skill or connector, use that instead, even if they will email or print it. Do NOT use for PDFs, spreadsheets, Google Docs, or coding unrelated to document generation. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docx"]},{"name":"google-workspace","description":"Read this before the first Google Drive, Docs, Sheets or Slides connector call whenever the task creates or changes a Google file. Use this skill whenever the user wants to create or change a Google Doc, Sheet or Slides file in their Google Drive. Triggers include: a request that names Google Docs, Sheets, Slides or Drive and asks to make, edit, format, copy or rename a file; a docs.google.com link with a request to change that file, even a one-line fix or suggested edits; and any follow-up change to a Google file from earlier in the chat, even \"change it\" or \"add a tab\". Includes helper scripts for document positions, cell ranges and slide layout. However, if the user asks for a doc, deck or spreadsheet without naming Google, or gives a Google file only as source material for something new, use Claude's own output type instead. Do NOT use for read-only questions about a Google file, or for Word, Excel, PowerPoint or PDF files. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:google-workspace"]},{"name":"import-memory","description":"Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:import-memory"]},{"name":"morning","description":"Render the user's morning brief as a styled HTML artifact, or set it up as a recurring weekday task. Use only when the user explicitly asks to run, see, or set up their morning brief, or if they invoke /morning by name. A question about their day, schedule, or calendar is not by itself a request for the brief; answer it directly instead. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:morning"]},{"name":"pdf","description":"Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pdf"]},{"name":"pptx","description":"Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations as PowerPoint (.pptx) files; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email, summary, or creating a different type of slide deck); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user asks for a PowerPoint or .pptx file, or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. However, when the user asks for a deck, slides, a slide deck, or a presentation without naming a file format, default to using a dedicated slide-deck artifact type or a separate slides skill if this session offers one; otherwise, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pptx"]},{"name":"skill-creator","description":"Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:skill-creator"]},{"name":"xlsx","description":"Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:xlsx"]}],"agents":[{"name":"claude","description":"Catch-all for any task that doesn't fit a more specific agent. FleetView's default when no agent name is typed."},{"name":"claude-code-guide","description":"Use this agent when the user asks questions (\"Can Claude...\", \"Does Claude...\", \"How do I...\") about: (1) Claude Code (the CLI tool) - features, hooks, slash commands, MCP servers, settings, IDE integrations, keyboard shortcuts; (2) Claude Agent SDK - building custom agents; (3) Claude API (formerly Anthropic API) - Messages API for directly passing messages to Claude, Tool Runner (`client.beta.messages.tool_runner`) for running an agentic loop over your own tools, manual tool-use loops, Managed Agents for server-hosted agents with a managed sandbox, prompt caching, and general Anthropic SDK usage; (4) Claude Tag (Claude in Slack) - what it is, setting it up for a Slack workspace, `/install-slack-app`; (5) `claude plugin eval` (writing and running plugin eval suites, its JSON/report, sandbox, CI) and the `/skill-doctor` report. **IMPORTANT:** Before spawning a new agent, check if there is already a running or recently completed claude-code-guide agent that you can continue via SendMessage.","model":"haiku"},{"name":"Explore","description":"Fast read-only search agent for locating code. Use it to find files by pattern (eg. \"src/components/**/*.tsx\"), grep for symbols or keywords (eg. \"API endpoints\"), or answer \"where is X defined / which files reference Y.\" Do NOT use it for code review, design-doc auditing, cross-file consistency checks, or open-ended analysis — it reads excerpts rather than whole files and will miss content past its read window. When calling, specify search breadth: \"quick\" for a single targeted lookup, \"medium\" for moderate exploration, or \"very thorough\" to search across multiple locations and naming conventions.","model":"inherit"},{"name":"general-purpose","description":"General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you."},{"name":"Plan","description":"Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs.","model":"inherit"},{"name":"statusline-setup","description":"Use this agent to configure the user's Claude Code status line setting.","model":"sonnet"}],"output_style":"default","available_output_styles":["default","Proactive","Concise","Explanatory","Learning"],"user_output_styles_dir":"/Users/flamingcow/.claude/output-styles","models":[{"value":"default","resolvedModel":"claude-opus-5-5","displayName":"Default (recommended)","description":"Opus 5.5 · Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"opus","resolvedModel":"claude-opus-5-5","displayName":"Opus 5.5","description":"For complex work and everyday tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"fable","resolvedModel":"claude-fable-5-1","displayName":"Fable 5.1","description":"For your toughest challenges","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"sonnet","resolvedModel":"claude-sonnet-5-5","displayName":"Sonnet 5.5","description":"Most efficient for simpler tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"haiku","resolvedModel":"claude-haiku-5-5","displayName":"Haiku 5.5","description":"Fastest for quick answers","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-haiku-4-5-20251001","resolvedModel":"claude-haiku-4-5-20251001","displayName":"Haiku 4.5","description":"Fastest for quick answers"},{"value":"claude-sonnet-5","resolvedModel":"claude-sonnet-5","displayName":"Sonnet 5","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-5","resolvedModel":"claude-opus-5","displayName":"Opus 5","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-fable-5","resolvedModel":"claude-fable-5","displayName":"Fable 5","description":"Most capable for your hardest and longest-running tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-8","resolvedModel":"claude-opus-4-8","displayName":"Opus 4.8","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-opus-4-7","resolvedModel":"claude-opus-4-7","displayName":"Opus 4.7","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-6","resolvedModel":"claude-opus-4-6","displayName":"Opus 4.6","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-sonnet-4-6","resolvedModel":"claude-sonnet-4-6","displayName":"Sonnet 4.6","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true}],"account":{"email":"[redacted]","organization":"[redacted]'s Organization","subscriptionType":"Claude Max","apiProvider":"firstParty"},"pid":2406,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} {"dir":"send","msg":{"message":{"content":[{"source":{"data":"iVBORw0KGgoAAAANSUhEUgAAAEAAAABACAIAAAAlC+aJAAAAZElEQVR4nOzPUQkAIBTAQBH7V9YQfhwPdgm2c9dsWwf8akBrQGtAa0BrQGtAa0BrQGtAa0BrQGtAa0BrQGtAa0BrQGtAa0BrQGtAa0BrQGtAa0BrQGtAa0BrQGtAa0B7AQAA///jRQGCmaQfxwAAAABJRU5ErkJggg==","media_type":"image/png","type":"base64"},"type":"image"},{"text":"Without using any tools, what single colour fills the attached image? Reply with just the colour name.","type":"text"}],"role":"user"},"parent_tool_use_id":null,"session_id":"","type":"user"}} -{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestImageInput344995001/001","session_id":"4071b9c2-8eaa-4dc7-8728-d111bbfd6614","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","LSP","Monitor","NotebookEdit","PushNotification","Read","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"pending","source":"claudeai"},{"name":"claude.ai Heliosian","status":"pending","source":"claudeai"},{"name":"claude.ai Fastmail","status":"pending","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"cdf35a6a-4739-402b-8946-f1cc1cfa195c","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestImageInput344995001-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestImageInput344995001-001/4071b9c2-8eaa-4dc7-8728-d111bbfd6614/scratchpad","messaging_socket_path":"/tmp/cc-socks/98366.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"4071b9c2-8eaa-4dc7-8728-d111bbfd6614","uuid":"4a0f0781-c467-4039-83de-41973b4331e6"}} -{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.01,"resetsAt":1792054200},"seven_day":{"utilization":0.34,"resetsAt":1792270800}}},"uuid":"4eae71b6-44db-4115-a35f-4725c09ff1ed","session_id":"4071b9c2-8eaa-4dc7-8728-d111bbfd6614"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3MazeJKLj6L1nCEpvXJ","type":"message","role":"assistant","content":[{"type":"text","text":"Red"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15356,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15356},"output_tokens":4,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"4071b9c2-8eaa-4dc7-8728-d111bbfd6614","uuid":"f4e1de95-8aae-4a2f-ab81-a57df5a10d96","timestamp":"2026-10-15T04:01:02.851Z","request_id":"req_011Cg3MazRQhqgHAiYLrirtd"}} -{"dir":"recv","msg":{"duration_api_ms":1689,"stop_reason":"end_turn","session_id":"4071b9c2-8eaa-4dc7-8728-d111bbfd6614","total_cost_usd":0.0638324,"usage":{"input_tokens":2,"cache_creation_input_tokens":15356,"cache_read_input_tokens":22367,"output_tokens":4,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":15356,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":4,"cache_read_input_tokens":22367,"cache_creation_input_tokens":15356,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15356},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1192,"outputTokens":17,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.0001277,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":2,"outputTokens":4,"cacheReadInputTokens":22367,"cacheCreationInputTokens":15356,"webSearchRequests":0,"costUSD":0.0637047,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":1,"subtype":"success","api_error_status":null,"result":"Red","ttft_ms":1174,"type":"result","duration_ms":1197,"uuid":"be796010-891c-418d-a156-fdcd1805cc17","ttft_stream_ms":1173,"time_to_request_ms":32,"first_content_frame_ms":1173,"queued_turn_count":0,"result_index":0}} +{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestImageInput3052101782/001","session_id":"43cec58d-d07c-4a17-beb0-0b02b6e1c93e","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","LSP","Monitor","NotebookEdit","PushNotification","Read","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"pending","source":"claudeai"},{"name":"claude.ai Heliosian","status":"pending","source":"claudeai"},{"name":"claude.ai Fastmail","status":"pending","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"8c5a45c4-3ccd-4ece-85ec-528a7abb8bf6","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestImageInput3052101782-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestImageInput3052101782-001/43cec58d-d07c-4a17-beb0-0b02b6e1c93e/scratchpad","messaging_socket_path":"/tmp/cc-socks/2406.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"43cec58d-d07c-4a17-beb0-0b02b6e1c93e","uuid":"13d7c921-fed1-435b-ac49-a1f7cdb4e68e"}} +{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.01,"resetsAt":1792054200},"seven_day":{"utilization":0.34,"resetsAt":1792270800}}},"uuid":"d70dc9be-e044-41c5-ac83-287825ce4560","session_id":"43cec58d-d07c-4a17-beb0-0b02b6e1c93e"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3MyvMUB57LGH5jLvviw","type":"message","role":"assistant","content":[{"type":"text","text":"Red"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15362,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15362},"output_tokens":4,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"43cec58d-d07c-4a17-beb0-0b02b6e1c93e","uuid":"9f9072e2-f0ba-4c8c-b3e0-19708b90bd0a","timestamp":"2026-10-15T04:06:13.909Z","request_id":"req_011Cg3Myv7L8YYm2XkiDhNLg"}} +{"dir":"recv","msg":{"duration_api_ms":2130,"stop_reason":"end_turn","session_id":"43cec58d-d07c-4a17-beb0-0b02b6e1c93e","total_cost_usd":0.0638559,"usage":{"input_tokens":2,"cache_creation_input_tokens":15362,"cache_read_input_tokens":22367,"output_tokens":4,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":15362,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":4,"cache_read_input_tokens":22367,"cache_creation_input_tokens":15362,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15362},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1192,"outputTokens":16,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.0001272,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":2,"outputTokens":4,"cacheReadInputTokens":22367,"cacheCreationInputTokens":15362,"webSearchRequests":0,"costUSD":0.0637287,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":1,"subtype":"success","api_error_status":null,"result":"Red","ttft_ms":1224,"type":"result","duration_ms":1239,"uuid":"38063c7b-5451-4489-87e4-1d07b188e23d","ttft_stream_ms":1222,"time_to_request_ms":30,"first_content_frame_ms":1223,"queued_turn_count":0,"result_index":0}} diff --git a/internal/claude/testdata/transcripts/TestInterrupt.jsonl b/internal/claude/testdata/transcripts/TestInterrupt.jsonl index 5569d6e..6190e29 100644 --- a/internal/claude/testdata/transcripts/TestInterrupt.jsonl +++ b/internal/claude/testdata/transcripts/TestInterrupt.jsonl @@ -1,17 +1,17 @@ -{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_93626c7c73aa88ff","type":"control_request"}} -{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_93626c7c73aa88ff","response":{"commands":[{"name":"deep-research","description":"Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. (dynamic workflow)","argumentHint":"","builtin":true},{"name":"design","description":"Make a new Design artifact from a brief","argumentHint":"[what to design]","builtin":true},{"name":"slides","description":"Make a new Slides deck artifact from a brief","argumentHint":"[what the deck is about]","builtin":true},{"name":"design-sync","description":"Push a React design system to claude.ai/design. This runs a converter that bundles the real component code (from Storybook or a bare package) and uploads it. Use when the user runs /design-sync or says \"sync my design system to Claude Design\".","argumentHint":"[\u003cproject hint, e.g. \"Acme DS\"\u003e]","builtin":true},{"name":"dataviz","description":"Use this skill whenever you are about to create ANY chart, graph, plot, dashboard, or data visualization, in ANY output medium — an HTML or React artifact, inline SVG, plotting code in any library (matplotlib, plotly, d3, Recharts, …), an image/PNG you will render and upload, or a chart shared into Slack. Read it BEFORE writing the first line of chart code, choosing chart colors, building a stat tile / meter / KPI row, or laying out a dashboard. When the destination is a first-party document connector (host-designated, never self-described) that renders live charts, hand it the rows (inline, or as an uploaded data file the chart cites) rather than a rendered PNG/SVG — a picture of a chart loses hover, data inspection and per-value comments. Produces visualizations that read as one system — elegant, accessible, consistent in light and dark — using a brand-neutral placeholder palette you swap for your own. Teaches a design-system-agnostic method: a form heuristic, a color formula with a runnable validator, mark specs, and interaction rules. A validated default palette is documented in `references/palette.md` — swap that file's values for your brand's. Triggers on: \"chart\", \"graph\", \"plot\", \"data viz\", \"visualization\", \"dashboard\", \"analytics\", \"visualize data\", \"categorical colors\", \"sequential / diverging palette\", \"stat tile\", \"sparkline\", \"heatmap\", \"legend\", \"axis\", \"tooltip\", \"chart colors\", \"color by series\".","argumentHint":"","builtin":true},{"name":"artifact-diagramming","description":"Diagramming know-how for Artifacts - when a picture earns its place, how to draw one that shows the real mechanism, and the inline-SVG mechanics that keep it legible in both themes.","argumentHint":"","builtin":true},{"name":"artifact-capabilities","description":"Runtime capabilities a published Artifact page can be granted — behavior static HTML cannot provide on its own, such as the page reading live or connected data, remembering what people do on it (a poll, a sign-up sheet, a checklist, a document edited in place — it saves new versions of itself), keeping state shared across viewers, knowing who is viewing, asking Claude a question of its own, storing files people add, handing the viewer a file to save, or using the viewer's camera, microphone, location, screen or device motion. Serves this user's live capability roster and the typed call definitions. Load it whenever any such runtime behavior would make an artifact more useful, before writing the page.","argumentHint":"","builtin":true},{"name":"update-config","description":"Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme/model, suggest the /config command.","argumentHint":"","builtin":true},{"name":"verify","description":"Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.","argumentHint":"","builtin":true},{"name":"debug","description":"Enable debug logging for this session and help diagnose issues","argumentHint":"[issue description]","builtin":true},{"name":"code-review","description":"Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep multi-agent review in the cloud); with no level given, it reuses the level you typed last. Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review. Pass --max-findings \u003cn\u003e to report up to n findings, or --max-findings all for every finding. The choice stays until you pass --max-findings default. For ultra on a GitHub.com PR target, --post asks to post the finished review’s findings to the PR as a single comment from the user’s GitHub account (not a review; the launch dialog still confirms in interactive sessions, while non-interactive mode posts on the flag alone) and --no-post hides that option.","argumentHint":"[low|medium|high|xhigh|max|ultra] [--fix] [--comment] [\u003cpr#\u003e|\u003cbranch\u003e|\u003cpath\u003e] [--max-findings \u003cn\u003e|all]","aliases":["review"],"builtin":true},{"name":"simplify","description":"Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.","argumentHint":"[\u003ctarget\u003e]","builtin":true},{"name":"batch","description":"Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.","argumentHint":"\u003cinstruction\u003e","builtin":true},{"name":"fewer-permission-prompts","description":"Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.","argumentHint":"","builtin":true},{"name":"doctor","description":"Health-check the user's Claude Code setup and fix issues: diagnose installation health — what the `claude doctor` terminal diagnostics cover — from local data (duplicate or leftover installs, PATH, unparseable settings files, broken or colliding agent definitions, skills whose frontmatter fails to parse); find unused skills, MCP servers, and plugins versus their context cost and disable dead weight; deduplicate local CLAUDE.md files against checked-in ones; trim checked-in CLAUDE.md files by cutting content a session could derive from the codebase (directory layouts, tech-stack lists, architecture overviews) while keeping gotchas, rationale, and non-standard conventions; migrate always-loaded CLAUDE.md guidance into lazy skills and nested CLAUDE.md files; flag slow hooks and context-heavy extensions; check the installed version is current; make auto mode the default permission mode; and pre-approve frequently denied read-only commands. Use when the user asks for a doctor run, checkup, audit, tune-up, or cleanup of their Claude Code setup or configuration.","argumentHint":"[prompt-audit [\u003cpath\u003e]]","aliases":["checkup"],"builtin":true},{"name":"loop","description":"Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.","argumentHint":"[interval] [prompt]","aliases":["proactive"],"builtin":true},{"name":"schedule","description":"Create, update, list, or run scheduled cloud agents (routines) that execute on a cron schedule.","argumentHint":"","aliases":["routines"],"builtin":true},{"name":"claude-api","description":"Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).","argumentHint":"","builtin":true},{"name":"workflow-authoring","description":"Reference for writing a Workflow tool script (script API and gotchas, resume, quality patterns, worked examples). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.","argumentHint":"","builtin":true},{"name":"run","description":"Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).","argumentHint":"","builtin":true},{"name":"run-skill-generator","description":"Author or improve the run-\u003cunit\u003e skill - a per-project skill that tells agents how to build, launch, and drive this project's app. Use when the user asks to set up the project, get it running, write run instructions, or verify build/run steps work from a clean environment.","argumentHint":"","builtin":true},{"name":"plugin-authoring","description":"Make a mod: a change to Claude's own interface or behaviour, such as a live pane or panel, a band above the prompt, a status line, a toast, a slash command, or a hook on tool calls or prompts. Use to make, change or debug a mod or its hooks module.","argumentHint":"","builtin":true},{"name":"advisor","description":"Let Claude consult a stronger model at key moments","argumentHint":"[fable|opus|sonnet|off]","builtin":true},{"name":"agents","description":"(removed) Ask Claude to create/manage subagents, or edit .claude/agents/","argumentHint":"","builtin":true},{"name":"auto-mode-setup","description":"Teach auto mode about your environment, plus optional rule tweaks","argumentHint":"[--request-id \u003cuuid\u003e] (--wizard posture=… scope=… depth=… --propose | --expect-sha256 \u003c64-hex\u003e --apply-file \u003cpath\u003e)","builtin":true},{"name":"autocompact","description":"Configure the auto-compact window size","argumentHint":"[auto|\u003ctokens\u003e]","builtin":true},{"name":"clear","description":"Start a new session with empty context; previous session stays on disk (resumable with /resume)","argumentHint":"[name]","aliases":["reset","new"],"builtin":true},{"name":"color","description":"Set the prompt bar color for this session","argumentHint":"[red|blue|green|yellow|purple|orange|pink|cyan|default]","builtin":true},{"name":"compact","description":"Free up context by summarizing the conversation so far","argumentHint":"\u003coptional custom summarization instructions\u003e","builtin":true},{"name":"config","description":"Set a setting by key","argumentHint":"key=value","aliases":["settings"],"builtin":true},{"name":"output-style","description":"List output styles or switch to one","argumentHint":"[style]","builtin":true},{"name":"context","description":"Show current context usage","argumentHint":"","builtin":true},{"name":"effort","description":"Set effort level for model usage","argumentHint":"\u003clow|medium|high|xhigh|max|auto|ultracode [on|off]\u003e","builtin":true},{"name":"fast","description":"Toggle fast mode (Opus 5.5)","argumentHint":"[on|off]","builtin":true},{"name":"focus","description":"Toggle focus view: just your prompt, summary, and response","argumentHint":"[on|off]","builtin":true},{"name":"heapdump","description":"Dump the JS heap to the Desktop; on Linux with no Desktop folder, the home directory","argumentHint":"","builtin":true},{"name":"init","description":"Initialize a new CLAUDE.md file with codebase documentation","argumentHint":"","builtin":true},{"name":"mcp","description":"Manage MCP servers","argumentHint":"[reconnect|enable|disable [\u003cserver\u003e|all]]","builtin":true},{"name":"import","description":"Import config from another AI coding agent","argumentHint":"","builtin":true},{"name":"model","description":"Set the AI model for Claude Code","argumentHint":"\u003cmodel\u003e","builtin":true},{"name":"__remote-workflow","description":"Run the workflow script delivered in this session environment (server-launched sessions only)","argumentHint":"","builtin":true},{"name":"workflow-launch-exec","description":"Execute a server-launched workflow handoff (workflow_launch event sessions only)","argumentHint":"","builtin":true},{"name":"reload-plugins","description":"Activate pending plugin changes in the current session","argumentHint":"[--force]","builtin":true},{"name":"reload-skills","description":"Pick up skills added or changed on disk during this session","argumentHint":"","builtin":true},{"name":"rename","description":"Rename the current conversation","argumentHint":"[name]","aliases":["name"],"builtin":true},{"name":"ultrareview","description":"Start a cloud agent that finds and verifies bugs in your branch (~15-25 min, $5-$25 USD) · Runs in a cloud session. See https://code.claude.com/docs/en/claude-code-on-the-web","argumentHint":"","builtin":true},{"name":"security-review","description":"Complete a security review of the pending changes on the current branch","argumentHint":"","builtin":true},{"name":"usage-credits","description":"Configure usage credits or request them from your admin when you hit a limit","argumentHint":"","builtin":true},{"name":"extra-usage","description":"Renamed to /usage-credits","argumentHint":"","builtin":true},{"name":"usage","description":"Show session cost, plan usage, and what's contributing to your limits","argumentHint":"","aliases":["cost","stats"],"builtin":true},{"name":"insights","description":"Generate a report analyzing your Claude Code sessions","argumentHint":"","builtin":true},{"name":"recap","description":"Generate a one-line session recap now","argumentHint":"","builtin":true},{"name":"skill-doctor","description":"Show which loaded skills are unused and costing context","argumentHint":"","builtin":true},{"name":"goal","description":"Set a goal — keep working until the condition is met","argumentHint":"","builtin":true},{"name":"design-consent","description":"Grant Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"design-revoke","description":"Revoke Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"list-agents","description":"List subagents, teammates, and other Claude sessions you can message","argumentHint":"","aliases":["peers"],"builtin":true},{"name":"team-onboarding","description":"Help teammates ramp on Claude Code with a guide from your usage","argumentHint":"","builtin":true},{"name":"docs","description":"docs (editable docs people share and comment on; the default for any document, named as a doc or not: a document, report, proposal, resume, cover letter, letter, contract, policy, form, template, worksheet, essay, handbook, guide, how-to, cheat sheet, SOP or other writing to keep, share, collaborate on, send, submit, print or sign; a doc exports to Word, PDF, Markdown or Google Docs, so needing a file to send, attach, upload, submit or print is no reason to pick Word, and a file nobody asked for is a doc, not Word; a plan, comparison, summary or notes asked in chat stays in chat; a pasted claude.ai artifact link may be a doc: check with docs tools first; Word or another file format named, tracked changes wanted, or a .docx to change or use as a template → that format's skill): making one → if no docs-connector instructions are in context, call its `guide` (topic.instructions) first; then create the doc (headings only, no body) before any search, file read or plan, even with files attached. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docs"]},{"name":"docx","description":"Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers include: any mention of Microsoft Word Documents, such as 'Word doc', 'word document', '.docx', '.dotx', 'microsoft doc'. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a deliverable as a Word or .docx file (to download, email or print), use this skill. However, if they ask for a document, page, report, memo, or notes WITHOUT naming a file format and the session offers Claude's own dedicated document or page skill or connector, use that instead, even if they will email or print it. Do NOT use for PDFs, spreadsheets, Google Docs, or coding unrelated to document generation. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docx"]},{"name":"google-workspace","description":"Read this before the first Google Drive, Docs, Sheets or Slides connector call whenever the task creates or changes a Google file. Use this skill whenever the user wants to create or change a Google Doc, Sheet or Slides file in their Google Drive. Triggers include: a request that names Google Docs, Sheets, Slides or Drive and asks to make, edit, format, copy or rename a file; a docs.google.com link with a request to change that file, even a one-line fix or suggested edits; and any follow-up change to a Google file from earlier in the chat, even \"change it\" or \"add a tab\". Includes helper scripts for document positions, cell ranges and slide layout. However, if the user asks for a doc, deck or spreadsheet without naming Google, or gives a Google file only as source material for something new, use Claude's own output type instead. Do NOT use for read-only questions about a Google file, or for Word, Excel, PowerPoint or PDF files. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:google-workspace"]},{"name":"import-memory","description":"Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:import-memory"]},{"name":"morning","description":"Render the user's morning brief as a styled HTML artifact, or set it up as a recurring weekday task. Use only when the user explicitly asks to run, see, or set up their morning brief, or if they invoke /morning by name. A question about their day, schedule, or calendar is not by itself a request for the brief; answer it directly instead. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:morning"]},{"name":"pdf","description":"Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pdf"]},{"name":"pptx","description":"Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations as PowerPoint (.pptx) files; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email, summary, or creating a different type of slide deck); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user asks for a PowerPoint or .pptx file, or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. However, when the user asks for a deck, slides, a slide deck, or a presentation without naming a file format, default to using a dedicated slide-deck artifact type or a separate slides skill if this session offers one; otherwise, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pptx"]},{"name":"skill-creator","description":"Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:skill-creator"]},{"name":"xlsx","description":"Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:xlsx"]}],"agents":[{"name":"claude","description":"Catch-all for any task that doesn't fit a more specific agent. FleetView's default when no agent name is typed."},{"name":"claude-code-guide","description":"Use this agent when the user asks questions (\"Can Claude...\", \"Does Claude...\", \"How do I...\") about: (1) Claude Code (the CLI tool) - features, hooks, slash commands, MCP servers, settings, IDE integrations, keyboard shortcuts; (2) Claude Agent SDK - building custom agents; (3) Claude API (formerly Anthropic API) - Messages API for directly passing messages to Claude, Tool Runner (`client.beta.messages.tool_runner`) for running an agentic loop over your own tools, manual tool-use loops, Managed Agents for server-hosted agents with a managed sandbox, prompt caching, and general Anthropic SDK usage; (4) Claude Tag (Claude in Slack) - what it is, setting it up for a Slack workspace, `/install-slack-app`; (5) `claude plugin eval` (writing and running plugin eval suites, its JSON/report, sandbox, CI) and the `/skill-doctor` report. **IMPORTANT:** Before spawning a new agent, check if there is already a running or recently completed claude-code-guide agent that you can continue via SendMessage.","model":"haiku"},{"name":"Explore","description":"Fast read-only search agent for locating code. Use it to find files by pattern (eg. \"src/components/**/*.tsx\"), grep for symbols or keywords (eg. \"API endpoints\"), or answer \"where is X defined / which files reference Y.\" Do NOT use it for code review, design-doc auditing, cross-file consistency checks, or open-ended analysis — it reads excerpts rather than whole files and will miss content past its read window. When calling, specify search breadth: \"quick\" for a single targeted lookup, \"medium\" for moderate exploration, or \"very thorough\" to search across multiple locations and naming conventions.","model":"inherit"},{"name":"general-purpose","description":"General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you."},{"name":"Plan","description":"Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs.","model":"inherit"},{"name":"statusline-setup","description":"Use this agent to configure the user's Claude Code status line setting.","model":"sonnet"}],"output_style":"default","available_output_styles":["default","Proactive","Concise","Explanatory","Learning"],"user_output_styles_dir":"/Users/flamingcow/.claude/output-styles","models":[{"value":"default","resolvedModel":"claude-opus-5-5","displayName":"Default (recommended)","description":"Opus 5.5 · Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"opus","resolvedModel":"claude-opus-5-5","displayName":"Opus 5.5","description":"For complex work and everyday tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"fable","resolvedModel":"claude-fable-5-1","displayName":"Fable 5.1","description":"For your toughest challenges","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"sonnet","resolvedModel":"claude-sonnet-5-5","displayName":"Sonnet 5.5","description":"Most efficient for simpler tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"haiku","resolvedModel":"claude-haiku-5-5","displayName":"Haiku 5.5","description":"Fastest for quick answers","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-haiku-4-5-20251001","resolvedModel":"claude-haiku-4-5-20251001","displayName":"Haiku 4.5","description":"Fastest for quick answers"},{"value":"claude-sonnet-5","resolvedModel":"claude-sonnet-5","displayName":"Sonnet 5","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-5","resolvedModel":"claude-opus-5","displayName":"Opus 5","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-fable-5","resolvedModel":"claude-fable-5","displayName":"Fable 5","description":"Most capable for your hardest and longest-running tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-8","resolvedModel":"claude-opus-4-8","displayName":"Opus 4.8","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-opus-4-7","resolvedModel":"claude-opus-4-7","displayName":"Opus 4.7","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-6","resolvedModel":"claude-opus-4-6","displayName":"Opus 4.6","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-sonnet-4-6","resolvedModel":"claude-sonnet-4-6","displayName":"Sonnet 4.6","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true}],"account":{"email":"[redacted]","organization":"[redacted]'s Organization","subscriptionType":"Claude Max","apiProvider":"firstParty"},"pid":98365,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} +{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_ea66e7f9ba965a83","type":"control_request"}} +{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_ea66e7f9ba965a83","response":{"commands":[{"name":"deep-research","description":"Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. (dynamic workflow)","argumentHint":"","builtin":true},{"name":"design","description":"Make a new Design artifact from a brief","argumentHint":"[what to design]","builtin":true},{"name":"slides","description":"Make a new Slides deck artifact from a brief","argumentHint":"[what the deck is about]","builtin":true},{"name":"design-sync","description":"Push a React design system to claude.ai/design. This runs a converter that bundles the real component code (from Storybook or a bare package) and uploads it. Use when the user runs /design-sync or says \"sync my design system to Claude Design\".","argumentHint":"[\u003cproject hint, e.g. \"Acme DS\"\u003e]","builtin":true},{"name":"dataviz","description":"Use this skill whenever you are about to create ANY chart, graph, plot, dashboard, or data visualization, in ANY output medium — an HTML or React artifact, inline SVG, plotting code in any library (matplotlib, plotly, d3, Recharts, …), an image/PNG you will render and upload, or a chart shared into Slack. Read it BEFORE writing the first line of chart code, choosing chart colors, building a stat tile / meter / KPI row, or laying out a dashboard. When the destination is a first-party document connector (host-designated, never self-described) that renders live charts, hand it the rows (inline, or as an uploaded data file the chart cites) rather than a rendered PNG/SVG — a picture of a chart loses hover, data inspection and per-value comments. Produces visualizations that read as one system — elegant, accessible, consistent in light and dark — using a brand-neutral placeholder palette you swap for your own. Teaches a design-system-agnostic method: a form heuristic, a color formula with a runnable validator, mark specs, and interaction rules. A validated default palette is documented in `references/palette.md` — swap that file's values for your brand's. Triggers on: \"chart\", \"graph\", \"plot\", \"data viz\", \"visualization\", \"dashboard\", \"analytics\", \"visualize data\", \"categorical colors\", \"sequential / diverging palette\", \"stat tile\", \"sparkline\", \"heatmap\", \"legend\", \"axis\", \"tooltip\", \"chart colors\", \"color by series\".","argumentHint":"","builtin":true},{"name":"artifact-diagramming","description":"Diagramming know-how for Artifacts - when a picture earns its place, how to draw one that shows the real mechanism, and the inline-SVG mechanics that keep it legible in both themes.","argumentHint":"","builtin":true},{"name":"artifact-capabilities","description":"Runtime capabilities a published Artifact page can be granted — behavior static HTML cannot provide on its own, such as the page reading live or connected data, remembering what people do on it (a poll, a sign-up sheet, a checklist, a document edited in place — it saves new versions of itself), keeping state shared across viewers, knowing who is viewing, asking Claude a question of its own, storing files people add, handing the viewer a file to save, or using the viewer's camera, microphone, location, screen or device motion. Serves this user's live capability roster and the typed call definitions. Load it whenever any such runtime behavior would make an artifact more useful, before writing the page.","argumentHint":"","builtin":true},{"name":"update-config","description":"Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme/model, suggest the /config command.","argumentHint":"","builtin":true},{"name":"verify","description":"Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.","argumentHint":"","builtin":true},{"name":"debug","description":"Enable debug logging for this session and help diagnose issues","argumentHint":"[issue description]","builtin":true},{"name":"code-review","description":"Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep multi-agent review in the cloud); with no level given, it reuses the level you typed last. Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review. Pass --max-findings \u003cn\u003e to report up to n findings, or --max-findings all for every finding. The choice stays until you pass --max-findings default. For ultra on a GitHub.com PR target, --post asks to post the finished review’s findings to the PR as a single comment from the user’s GitHub account (not a review; the launch dialog still confirms in interactive sessions, while non-interactive mode posts on the flag alone) and --no-post hides that option.","argumentHint":"[low|medium|high|xhigh|max|ultra] [--fix] [--comment] [\u003cpr#\u003e|\u003cbranch\u003e|\u003cpath\u003e] [--max-findings \u003cn\u003e|all]","aliases":["review"],"builtin":true},{"name":"simplify","description":"Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.","argumentHint":"[\u003ctarget\u003e]","builtin":true},{"name":"batch","description":"Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.","argumentHint":"\u003cinstruction\u003e","builtin":true},{"name":"fewer-permission-prompts","description":"Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.","argumentHint":"","builtin":true},{"name":"doctor","description":"Health-check the user's Claude Code setup and fix issues: diagnose installation health — what the `claude doctor` terminal diagnostics cover — from local data (duplicate or leftover installs, PATH, unparseable settings files, broken or colliding agent definitions, skills whose frontmatter fails to parse); find unused skills, MCP servers, and plugins versus their context cost and disable dead weight; deduplicate local CLAUDE.md files against checked-in ones; trim checked-in CLAUDE.md files by cutting content a session could derive from the codebase (directory layouts, tech-stack lists, architecture overviews) while keeping gotchas, rationale, and non-standard conventions; migrate always-loaded CLAUDE.md guidance into lazy skills and nested CLAUDE.md files; flag slow hooks and context-heavy extensions; check the installed version is current; make auto mode the default permission mode; and pre-approve frequently denied read-only commands. Use when the user asks for a doctor run, checkup, audit, tune-up, or cleanup of their Claude Code setup or configuration.","argumentHint":"[prompt-audit [\u003cpath\u003e]]","aliases":["checkup"],"builtin":true},{"name":"loop","description":"Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.","argumentHint":"[interval] [prompt]","aliases":["proactive"],"builtin":true},{"name":"schedule","description":"Create, update, list, or run scheduled cloud agents (routines) that execute on a cron schedule.","argumentHint":"","aliases":["routines"],"builtin":true},{"name":"claude-api","description":"Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).","argumentHint":"","builtin":true},{"name":"workflow-authoring","description":"Reference for writing a Workflow tool script (script API and gotchas, resume, quality patterns, worked examples). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.","argumentHint":"","builtin":true},{"name":"run","description":"Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).","argumentHint":"","builtin":true},{"name":"run-skill-generator","description":"Author or improve the run-\u003cunit\u003e skill - a per-project skill that tells agents how to build, launch, and drive this project's app. Use when the user asks to set up the project, get it running, write run instructions, or verify build/run steps work from a clean environment.","argumentHint":"","builtin":true},{"name":"plugin-authoring","description":"Make a mod: a change to Claude's own interface or behaviour, such as a live pane or panel, a band above the prompt, a status line, a toast, a slash command, or a hook on tool calls or prompts. Use to make, change or debug a mod or its hooks module.","argumentHint":"","builtin":true},{"name":"advisor","description":"Let Claude consult a stronger model at key moments","argumentHint":"[fable|opus|sonnet|off]","builtin":true},{"name":"agents","description":"(removed) Ask Claude to create/manage subagents, or edit .claude/agents/","argumentHint":"","builtin":true},{"name":"auto-mode-setup","description":"Teach auto mode about your environment, plus optional rule tweaks","argumentHint":"[--request-id \u003cuuid\u003e] (--wizard posture=… scope=… depth=… --propose | --expect-sha256 \u003c64-hex\u003e --apply-file \u003cpath\u003e)","builtin":true},{"name":"autocompact","description":"Configure the auto-compact window size","argumentHint":"[auto|\u003ctokens\u003e]","builtin":true},{"name":"clear","description":"Start a new session with empty context; previous session stays on disk (resumable with /resume)","argumentHint":"[name]","aliases":["reset","new"],"builtin":true},{"name":"color","description":"Set the prompt bar color for this session","argumentHint":"[red|blue|green|yellow|purple|orange|pink|cyan|default]","builtin":true},{"name":"compact","description":"Free up context by summarizing the conversation so far","argumentHint":"\u003coptional custom summarization instructions\u003e","builtin":true},{"name":"config","description":"Set a setting by key","argumentHint":"key=value","aliases":["settings"],"builtin":true},{"name":"output-style","description":"List output styles or switch to one","argumentHint":"[style]","builtin":true},{"name":"context","description":"Show current context usage","argumentHint":"","builtin":true},{"name":"effort","description":"Set effort level for model usage","argumentHint":"\u003clow|medium|high|xhigh|max|auto|ultracode [on|off]\u003e","builtin":true},{"name":"fast","description":"Toggle fast mode (Opus 5.5)","argumentHint":"[on|off]","builtin":true},{"name":"focus","description":"Toggle focus view: just your prompt, summary, and response","argumentHint":"[on|off]","builtin":true},{"name":"heapdump","description":"Dump the JS heap to the Desktop; on Linux with no Desktop folder, the home directory","argumentHint":"","builtin":true},{"name":"init","description":"Initialize a new CLAUDE.md file with codebase documentation","argumentHint":"","builtin":true},{"name":"mcp","description":"Manage MCP servers","argumentHint":"[reconnect|enable|disable [\u003cserver\u003e|all]]","builtin":true},{"name":"import","description":"Import config from another AI coding agent","argumentHint":"","builtin":true},{"name":"model","description":"Set the AI model for Claude Code","argumentHint":"\u003cmodel\u003e","builtin":true},{"name":"__remote-workflow","description":"Run the workflow script delivered in this session environment (server-launched sessions only)","argumentHint":"","builtin":true},{"name":"workflow-launch-exec","description":"Execute a server-launched workflow handoff (workflow_launch event sessions only)","argumentHint":"","builtin":true},{"name":"reload-plugins","description":"Activate pending plugin changes in the current session","argumentHint":"[--force]","builtin":true},{"name":"reload-skills","description":"Pick up skills added or changed on disk during this session","argumentHint":"","builtin":true},{"name":"rename","description":"Rename the current conversation","argumentHint":"[name]","aliases":["name"],"builtin":true},{"name":"ultrareview","description":"Start a cloud agent that finds and verifies bugs in your branch (~15-25 min, $5-$25 USD) · Runs in a cloud session. See https://code.claude.com/docs/en/claude-code-on-the-web","argumentHint":"","builtin":true},{"name":"security-review","description":"Complete a security review of the pending changes on the current branch","argumentHint":"","builtin":true},{"name":"usage-credits","description":"Configure usage credits or request them from your admin when you hit a limit","argumentHint":"","builtin":true},{"name":"extra-usage","description":"Renamed to /usage-credits","argumentHint":"","builtin":true},{"name":"usage","description":"Show session cost, plan usage, and what's contributing to your limits","argumentHint":"","aliases":["cost","stats"],"builtin":true},{"name":"insights","description":"Generate a report analyzing your Claude Code sessions","argumentHint":"","builtin":true},{"name":"recap","description":"Generate a one-line session recap now","argumentHint":"","builtin":true},{"name":"skill-doctor","description":"Show which loaded skills are unused and costing context","argumentHint":"","builtin":true},{"name":"goal","description":"Set a goal — keep working until the condition is met","argumentHint":"","builtin":true},{"name":"design-consent","description":"Grant Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"design-revoke","description":"Revoke Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"list-agents","description":"List subagents, teammates, and other Claude sessions you can message","argumentHint":"","aliases":["peers"],"builtin":true},{"name":"team-onboarding","description":"Help teammates ramp on Claude Code with a guide from your usage","argumentHint":"","builtin":true},{"name":"docs","description":"docs (editable docs people share and comment on; the default for any document, named as a doc or not: a document, report, proposal, resume, cover letter, letter, contract, policy, form, template, worksheet, essay, handbook, guide, how-to, cheat sheet, SOP or other writing to keep, share, collaborate on, send, submit, print or sign; a doc exports to Word, PDF, Markdown or Google Docs, so needing a file to send, attach, upload, submit or print is no reason to pick Word, and a file nobody asked for is a doc, not Word; a plan, comparison, summary or notes asked in chat stays in chat; a pasted claude.ai artifact link may be a doc: check with docs tools first; Word or another file format named, tracked changes wanted, or a .docx to change or use as a template → that format's skill): making one → if no docs-connector instructions are in context, call its `guide` (topic.instructions) first; then create the doc (headings only, no body) before any search, file read or plan, even with files attached. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docs"]},{"name":"docx","description":"Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers include: any mention of Microsoft Word Documents, such as 'Word doc', 'word document', '.docx', '.dotx', 'microsoft doc'. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a deliverable as a Word or .docx file (to download, email or print), use this skill. However, if they ask for a document, page, report, memo, or notes WITHOUT naming a file format and the session offers Claude's own dedicated document or page skill or connector, use that instead, even if they will email or print it. Do NOT use for PDFs, spreadsheets, Google Docs, or coding unrelated to document generation. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docx"]},{"name":"google-workspace","description":"Read this before the first Google Drive, Docs, Sheets or Slides connector call whenever the task creates or changes a Google file. Use this skill whenever the user wants to create or change a Google Doc, Sheet or Slides file in their Google Drive. Triggers include: a request that names Google Docs, Sheets, Slides or Drive and asks to make, edit, format, copy or rename a file; a docs.google.com link with a request to change that file, even a one-line fix or suggested edits; and any follow-up change to a Google file from earlier in the chat, even \"change it\" or \"add a tab\". Includes helper scripts for document positions, cell ranges and slide layout. However, if the user asks for a doc, deck or spreadsheet without naming Google, or gives a Google file only as source material for something new, use Claude's own output type instead. Do NOT use for read-only questions about a Google file, or for Word, Excel, PowerPoint or PDF files. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:google-workspace"]},{"name":"import-memory","description":"Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:import-memory"]},{"name":"morning","description":"Render the user's morning brief as a styled HTML artifact, or set it up as a recurring weekday task. Use only when the user explicitly asks to run, see, or set up their morning brief, or if they invoke /morning by name. A question about their day, schedule, or calendar is not by itself a request for the brief; answer it directly instead. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:morning"]},{"name":"pdf","description":"Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pdf"]},{"name":"pptx","description":"Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations as PowerPoint (.pptx) files; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email, summary, or creating a different type of slide deck); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user asks for a PowerPoint or .pptx file, or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. However, when the user asks for a deck, slides, a slide deck, or a presentation without naming a file format, default to using a dedicated slide-deck artifact type or a separate slides skill if this session offers one; otherwise, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pptx"]},{"name":"skill-creator","description":"Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:skill-creator"]},{"name":"xlsx","description":"Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:xlsx"]}],"agents":[{"name":"claude","description":"Catch-all for any task that doesn't fit a more specific agent. FleetView's default when no agent name is typed."},{"name":"claude-code-guide","description":"Use this agent when the user asks questions (\"Can Claude...\", \"Does Claude...\", \"How do I...\") about: (1) Claude Code (the CLI tool) - features, hooks, slash commands, MCP servers, settings, IDE integrations, keyboard shortcuts; (2) Claude Agent SDK - building custom agents; (3) Claude API (formerly Anthropic API) - Messages API for directly passing messages to Claude, Tool Runner (`client.beta.messages.tool_runner`) for running an agentic loop over your own tools, manual tool-use loops, Managed Agents for server-hosted agents with a managed sandbox, prompt caching, and general Anthropic SDK usage; (4) Claude Tag (Claude in Slack) - what it is, setting it up for a Slack workspace, `/install-slack-app`; (5) `claude plugin eval` (writing and running plugin eval suites, its JSON/report, sandbox, CI) and the `/skill-doctor` report. **IMPORTANT:** Before spawning a new agent, check if there is already a running or recently completed claude-code-guide agent that you can continue via SendMessage.","model":"haiku"},{"name":"Explore","description":"Fast read-only search agent for locating code. Use it to find files by pattern (eg. \"src/components/**/*.tsx\"), grep for symbols or keywords (eg. \"API endpoints\"), or answer \"where is X defined / which files reference Y.\" Do NOT use it for code review, design-doc auditing, cross-file consistency checks, or open-ended analysis — it reads excerpts rather than whole files and will miss content past its read window. When calling, specify search breadth: \"quick\" for a single targeted lookup, \"medium\" for moderate exploration, or \"very thorough\" to search across multiple locations and naming conventions.","model":"inherit"},{"name":"general-purpose","description":"General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you."},{"name":"Plan","description":"Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs.","model":"inherit"},{"name":"statusline-setup","description":"Use this agent to configure the user's Claude Code status line setting.","model":"sonnet"}],"output_style":"default","available_output_styles":["default","Proactive","Concise","Explanatory","Learning"],"user_output_styles_dir":"/Users/flamingcow/.claude/output-styles","models":[{"value":"default","resolvedModel":"claude-opus-5-5","displayName":"Default (recommended)","description":"Opus 5.5 · Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"opus","resolvedModel":"claude-opus-5-5","displayName":"Opus 5.5","description":"For complex work and everyday tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"fable","resolvedModel":"claude-fable-5-1","displayName":"Fable 5.1","description":"For your toughest challenges","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"sonnet","resolvedModel":"claude-sonnet-5-5","displayName":"Sonnet 5.5","description":"Most efficient for simpler tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"haiku","resolvedModel":"claude-haiku-5-5","displayName":"Haiku 5.5","description":"Fastest for quick answers","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-haiku-4-5-20251001","resolvedModel":"claude-haiku-4-5-20251001","displayName":"Haiku 4.5","description":"Fastest for quick answers"},{"value":"claude-sonnet-5","resolvedModel":"claude-sonnet-5","displayName":"Sonnet 5","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-5","resolvedModel":"claude-opus-5","displayName":"Opus 5","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-fable-5","resolvedModel":"claude-fable-5","displayName":"Fable 5","description":"Most capable for your hardest and longest-running tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-8","resolvedModel":"claude-opus-4-8","displayName":"Opus 4.8","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-opus-4-7","resolvedModel":"claude-opus-4-7","displayName":"Opus 4.7","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-6","resolvedModel":"claude-opus-4-6","displayName":"Opus 4.6","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-sonnet-4-6","resolvedModel":"claude-sonnet-4-6","displayName":"Sonnet 4.6","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true}],"account":{"email":"[redacted]","organization":"[redacted]'s Organization","subscriptionType":"Claude Max","apiProvider":"firstParty"},"pid":2405,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} {"dir":"send","msg":{"message":{"content":"Run the bash command `ping -c 120 127.0.0.1` in the foreground (not in the background) and wait for it to finish, then say done.","role":"user"},"parent_tool_use_id":null,"session_id":"","type":"user"}} -{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestInterrupt3118307443/001","session_id":"3e98ea6f-403d-4428-95b5-929359d3d2ee","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","LSP","Monitor","NotebookEdit","PushNotification","Read","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"pending","source":"claudeai"},{"name":"claude.ai Heliosian","status":"pending","source":"claudeai"},{"name":"claude.ai Fastmail","status":"pending","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"98fbe535-615a-4c35-b98a-b8a450c82d23","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestInterrupt3118307443-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestInterrupt3118307443-001/3e98ea6f-403d-4428-95b5-929359d3d2ee/scratchpad","messaging_socket_path":"/tmp/cc-socks/98365.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"3e98ea6f-403d-4428-95b5-929359d3d2ee","uuid":"8b9b397a-d89b-4e72-b9af-bba331c763e3"}} -{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.01,"resetsAt":1792054200},"seven_day":{"utilization":0.34,"resetsAt":1792270800}}},"uuid":"5dc4a698-6327-4edf-a518-133fbb837d0c","session_id":"3e98ea6f-403d-4428-95b5-929359d3d2ee"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3Mazh2n47jmF6uFm5sc","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01DAXvVXxANNsftpBUGzT6K5","name":"Bash","input":{"command":"ping -c 120 127.0.0.1","description":"Ping localhost 120 times","timeout":180000},"caller":{"type":"direct"}}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15263,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15263},"output_tokens":16,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"3e98ea6f-403d-4428-95b5-929359d3d2ee","uuid":"a4f7ffa9-8d8f-4930-bfc2-7e6915578427","timestamp":"2026-10-15T04:01:03.741Z","request_id":"req_011Cg3MazS9YHo9yTp56KQ6A","wire_tool_inputs":{"toolu_01DAXvVXxANNsftpBUGzT6K5":{"command":"ping -c 120 127.0.0.1","timeout":180000,"description":"Ping localhost 120 times"}}}} -{"dir":"send","msg":{"request":{"subtype":"interrupt"},"request_id":"req_40eed33f6f637dfa","type":"control_request"}} -{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_40eed33f6f637dfa","response":{"still_queued":[]}}}} -{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"The user doesn't want to proceed with this tool use. The tool use was rejected (eg. if it was a file edit, the new_string was NOT written to the file). STOP what you are doing and wait for the user to tell you how to proceed.\n\nNote: The user's next message may contain a correction or preference. Pay close attention — if they explain what went wrong or how they'd prefer you to work, consider saving that to memory for future sessions.","is_error":true,"tool_use_id":"toolu_01DAXvVXxANNsftpBUGzT6K5"}]},"parent_tool_use_id":null,"session_id":"3e98ea6f-403d-4428-95b5-929359d3d2ee","uuid":"ae028585-0fc4-4e1d-bc98-f6346bdc1843","timestamp":"2026-10-15T04:01:05.753Z","tool_use_result":"User rejected tool use","tool_result_meta":[{"id":"toolu_01DAXvVXxANNsftpBUGzT6K5","non_execution_kind":"user-rejected"}]}} -{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"type":"text","text":"[Request interrupted by user for tool use]"}]},"parent_tool_use_id":null,"session_id":"3e98ea6f-403d-4428-95b5-929359d3d2ee","uuid":"711a87e7-910e-4ac8-8cd3-574f52e3194e","timestamp":"2026-10-15T04:01:05.754Z"}} -{"dir":"recv","msg":{"duration_api_ms":2781,"stop_reason":"tool_use","session_id":"3e98ea6f-403d-4428-95b5-929359d3d2ee","total_cost_usd":0.0645662,"usage":{"input_tokens":2,"cache_creation_input_tokens":15263,"cache_read_input_tokens":22367,"output_tokens":114,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":15263,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":114,"cache_read_input_tokens":22367,"cache_creation_input_tokens":15263,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15263},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1210,"outputTokens":25,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.0001335,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":2,"outputTokens":114,"cacheReadInputTokens":22367,"cacheCreationInputTokens":15263,"webSearchRequests":0,"costUSD":0.06443270000000001,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"aborted_tools","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":true,"num_turns":3,"subtype":"error_during_execution","errors":["[ede_diagnostic] result_type=user last_content_type=n/a stop_reason=tool_use"],"type":"result","duration_ms":4076,"uuid":"7c04e01d-49dc-49e5-bb3e-5caebac96264","queued_turn_count":0,"result_index":0}} -{"dir":"send","msg":{"message":{"content":"Reply with the single word ok.","role":"user"},"parent_tool_use_id":null,"session_id":"3e98ea6f-403d-4428-95b5-929359d3d2ee","type":"user"}} -{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestInterrupt3118307443/001","session_id":"3e98ea6f-403d-4428-95b5-929359d3d2ee","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","ListMcpResourcesTool","LSP","Monitor","NotebookEdit","PushNotification","Read","ReadMcpResourceDirTool","ReadMcpResourceTool","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write","mcp__claude_ai_Claude_Docs__batch","mcp__claude_ai_Claude_Docs__create","mcp__claude_ai_Claude_Docs__delete","mcp__claude_ai_Claude_Docs__export","mcp__claude_ai_Claude_Docs__guide","mcp__claude_ai_Claude_Docs__query","mcp__claude_ai_Claude_Docs__read","mcp__claude_ai_Claude_Docs__update","mcp__claude_ai_Fastmail__list_calendars","mcp__claude_ai_Fastmail__list_identities","mcp__claude_ai_Fastmail__list_labels","mcp__claude_ai_Fastmail__read_attachment","mcp__claude_ai_Fastmail__read_email","mcp__claude_ai_Fastmail__read_note","mcp__claude_ai_Fastmail__read_thread","mcp__claude_ai_Fastmail__search_contacts","mcp__claude_ai_Fastmail__search_email","mcp__claude_ai_Fastmail__search_events","mcp__claude_ai_Fastmail__search_notes","mcp__claude_ai_Fastmail__search_org_contacts","mcp__claude_ai_Heliosian__helios_activities","mcp__claude_ai_Heliosian__helios_classroom","mcp__claude_ai_Heliosian__helios_days","mcp__claude_ai_Heliosian__helios_describe_schema","mcp__claude_ai_Heliosian__helios_describe_table","mcp__claude_ai_Heliosian__helios_events","mcp__claude_ai_Heliosian__helios_find_people","mcp__claude_ai_Heliosian__helios_get","mcp__claude_ai_Heliosian__helios_group","mcp__claude_ai_Heliosian__helios_links","mcp__claude_ai_Heliosian__helios_lists","mcp__claude_ai_Heliosian__helios_nearby_families","mcp__claude_ai_Heliosian__helios_parties","mcp__claude_ai_Heliosian__helios_policies","mcp__claude_ai_Heliosian__helios_query","mcp__claude_ai_Heliosian__helios_query_json","mcp__claude_ai_Heliosian__helios_read_document","mcp__claude_ai_Heliosian__helios_search","mcp__claude_ai_Heliosian__helios_similar","mcp__claude_ai_Heliosian__helios_whoami"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"connected","source":"claudeai"},{"name":"claude.ai Heliosian","status":"connected","source":"claudeai"},{"name":"claude.ai Fastmail","status":"connected","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"5accde2b-ad81-4a85-b942-5bc6b0aca562","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestInterrupt3118307443-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestInterrupt3118307443-001/3e98ea6f-403d-4428-95b5-929359d3d2ee/scratchpad","messaging_socket_path":"/tmp/cc-socks/98365.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"3e98ea6f-403d-4428-95b5-929359d3d2ee","uuid":"a612b0d0-f118-44c2-909b-96448602c4ea"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3MbHjxDqDpHhr8US96b","type":"message","role":"assistant","content":[{"type":"text","text":"ok"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4772,"cache_read_input_tokens":37630,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4772},"output_tokens":4,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"3e98ea6f-403d-4428-95b5-929359d3d2ee","uuid":"0e9faebc-ed7b-4210-a6d7-206864da3e11","timestamp":"2026-10-15T04:01:06.862Z","request_id":"req_011Cg3MbHT6R72nc4tBQxyPq"}} -{"dir":"recv","msg":{"duration_api_ms":3894,"stop_reason":"end_turn","session_id":"3e98ea6f-403d-4428-95b5-929359d3d2ee","total_cost_usd":0.0874612,"usage":{"input_tokens":2,"cache_creation_input_tokens":4772,"cache_read_input_tokens":37630,"output_tokens":4,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":4772,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":4,"cache_read_input_tokens":37630,"cache_creation_input_tokens":4772,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4772},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1210,"outputTokens":25,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.0001335,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":4,"outputTokens":118,"cacheReadInputTokens":59997,"cacheCreationInputTokens":20035,"webSearchRequests":0,"costUSD":0.08732770000000001,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":1,"subtype":"success","api_error_status":null,"result":"ok","ttft_ms":1104,"type":"result","duration_ms":1122,"uuid":"fae28eac-fe54-42e9-b54a-dab434fb98fb","ttft_stream_ms":1104,"time_to_request_ms":8,"first_content_frame_ms":1104,"queued_turn_count":0,"result_index":1}} +{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestInterrupt1120760215/001","session_id":"8c4bd017-0d55-48c6-bb5f-c7aac3289f49","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","LSP","Monitor","NotebookEdit","PushNotification","Read","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"pending","source":"claudeai"},{"name":"claude.ai Heliosian","status":"pending","source":"claudeai"},{"name":"claude.ai Fastmail","status":"pending","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"ffc1a61a-c868-4922-82dc-638f7abae9a2","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestInterrupt1120760215-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestInterrupt1120760215-001/8c4bd017-0d55-48c6-bb5f-c7aac3289f49/scratchpad","messaging_socket_path":"/tmp/cc-socks/2405.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"8c4bd017-0d55-48c6-bb5f-c7aac3289f49","uuid":"3c967136-6bed-4dbf-9363-2d5c7b92b5c7"}} +{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.01,"resetsAt":1792054200},"seven_day":{"utilization":0.34,"resetsAt":1792270800}}},"uuid":"45657ee0-b90d-47ce-b71f-358fbd3c6de6","session_id":"8c4bd017-0d55-48c6-bb5f-c7aac3289f49"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3MyvNxdNfJfwo7zme73","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01NSSzEwgMmCwS1pn2w6P8fW","name":"Bash","input":{"command":"ping -c 120 127.0.0.1","description":"Ping localhost 120 times","timeout":180000},"caller":{"type":"direct"}}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15267,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15267},"output_tokens":16,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"8c4bd017-0d55-48c6-bb5f-c7aac3289f49","uuid":"04f668eb-3187-4822-8c2d-ffda309747bf","timestamp":"2026-10-15T04:06:14.775Z","request_id":"req_011Cg3Myv8KiZ2kiWqNvKwpW","wire_tool_inputs":{"toolu_01NSSzEwgMmCwS1pn2w6P8fW":{"command":"ping -c 120 127.0.0.1","timeout":180000,"description":"Ping localhost 120 times"}}}} +{"dir":"send","msg":{"request":{"subtype":"interrupt"},"request_id":"req_631b884876dcfe77","type":"control_request"}} +{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_631b884876dcfe77","response":{"still_queued":[]}}}} +{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"The user doesn't want to proceed with this tool use. The tool use was rejected (eg. if it was a file edit, the new_string was NOT written to the file). STOP what you are doing and wait for the user to tell you how to proceed.\n\nNote: The user's next message may contain a correction or preference. Pay close attention — if they explain what went wrong or how they'd prefer you to work, consider saving that to memory for future sessions.","is_error":true,"tool_use_id":"toolu_01NSSzEwgMmCwS1pn2w6P8fW"}]},"parent_tool_use_id":null,"session_id":"8c4bd017-0d55-48c6-bb5f-c7aac3289f49","uuid":"a358e39a-df04-45ed-abf8-c0fca26ca320","timestamp":"2026-10-15T04:06:16.800Z","tool_use_result":"User rejected tool use","tool_result_meta":[{"id":"toolu_01NSSzEwgMmCwS1pn2w6P8fW","non_execution_kind":"user-rejected"}]}} +{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"type":"text","text":"[Request interrupted by user for tool use]"}]},"parent_tool_use_id":null,"session_id":"8c4bd017-0d55-48c6-bb5f-c7aac3289f49","uuid":"50b7a80c-fa99-4fd0-81ed-879b92f17a96","timestamp":"2026-10-15T04:06:16.802Z"}} +{"dir":"recv","msg":{"duration_api_ms":2609,"stop_reason":"tool_use","session_id":"8c4bd017-0d55-48c6-bb5f-c7aac3289f49","total_cost_usd":0.0645792,"usage":{"input_tokens":2,"cache_creation_input_tokens":15267,"cache_read_input_tokens":22367,"output_tokens":114,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":15267,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":114,"cache_read_input_tokens":22367,"cache_creation_input_tokens":15267,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15267},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1210,"outputTokens":19,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.0001305,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":2,"outputTokens":114,"cacheReadInputTokens":22367,"cacheCreationInputTokens":15267,"webSearchRequests":0,"costUSD":0.0644487,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"aborted_tools","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":true,"num_turns":3,"subtype":"error_during_execution","errors":["[ede_diagnostic] result_type=user last_content_type=n/a stop_reason=tool_use"],"type":"result","duration_ms":4112,"uuid":"03ca84d4-556c-442e-a656-82db81ada767","queued_turn_count":0,"result_index":0}} +{"dir":"send","msg":{"message":{"content":"Reply with the single word ok.","role":"user"},"parent_tool_use_id":null,"session_id":"8c4bd017-0d55-48c6-bb5f-c7aac3289f49","type":"user"}} +{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestInterrupt1120760215/001","session_id":"8c4bd017-0d55-48c6-bb5f-c7aac3289f49","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","ListMcpResourcesTool","LSP","Monitor","NotebookEdit","PushNotification","Read","ReadMcpResourceDirTool","ReadMcpResourceTool","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write","mcp__claude_ai_Claude_Docs__batch","mcp__claude_ai_Claude_Docs__create","mcp__claude_ai_Claude_Docs__delete","mcp__claude_ai_Claude_Docs__export","mcp__claude_ai_Claude_Docs__guide","mcp__claude_ai_Claude_Docs__query","mcp__claude_ai_Claude_Docs__read","mcp__claude_ai_Claude_Docs__update","mcp__claude_ai_Fastmail__list_calendars","mcp__claude_ai_Fastmail__list_identities","mcp__claude_ai_Fastmail__list_labels","mcp__claude_ai_Fastmail__read_attachment","mcp__claude_ai_Fastmail__read_email","mcp__claude_ai_Fastmail__read_note","mcp__claude_ai_Fastmail__read_thread","mcp__claude_ai_Fastmail__search_contacts","mcp__claude_ai_Fastmail__search_email","mcp__claude_ai_Fastmail__search_events","mcp__claude_ai_Fastmail__search_notes","mcp__claude_ai_Fastmail__search_org_contacts","mcp__claude_ai_Heliosian__helios_activities","mcp__claude_ai_Heliosian__helios_classroom","mcp__claude_ai_Heliosian__helios_days","mcp__claude_ai_Heliosian__helios_describe_schema","mcp__claude_ai_Heliosian__helios_describe_table","mcp__claude_ai_Heliosian__helios_events","mcp__claude_ai_Heliosian__helios_find_people","mcp__claude_ai_Heliosian__helios_get","mcp__claude_ai_Heliosian__helios_group","mcp__claude_ai_Heliosian__helios_links","mcp__claude_ai_Heliosian__helios_lists","mcp__claude_ai_Heliosian__helios_nearby_families","mcp__claude_ai_Heliosian__helios_parties","mcp__claude_ai_Heliosian__helios_policies","mcp__claude_ai_Heliosian__helios_query","mcp__claude_ai_Heliosian__helios_query_json","mcp__claude_ai_Heliosian__helios_read_document","mcp__claude_ai_Heliosian__helios_search","mcp__claude_ai_Heliosian__helios_similar","mcp__claude_ai_Heliosian__helios_whoami"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"connected","source":"claudeai"},{"name":"claude.ai Heliosian","status":"connected","source":"claudeai"},{"name":"claude.ai Fastmail","status":"connected","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"fc9f6a50-5ba2-4dc5-8035-1e872b986cac","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestInterrupt1120760215-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestInterrupt1120760215-001/8c4bd017-0d55-48c6-bb5f-c7aac3289f49/scratchpad","messaging_socket_path":"/tmp/cc-socks/2405.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"8c4bd017-0d55-48c6-bb5f-c7aac3289f49","uuid":"b3351955-a163-42c5-bb32-5e4ea4aa2438"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3MzDap3xdaid2ntXHZq","type":"message","role":"assistant","content":[{"type":"text","text":"ok"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4772,"cache_read_input_tokens":37634,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4772},"output_tokens":4,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"8c4bd017-0d55-48c6-bb5f-c7aac3289f49","uuid":"af9bc81c-0cab-490d-a5f4-43f72536cc67","timestamp":"2026-10-15T04:06:17.874Z","request_id":"req_011Cg3MzDKBxvH7Fx4sA8aSz"}} +{"dir":"recv","msg":{"duration_api_ms":3678,"stop_reason":"end_turn","session_id":"8c4bd017-0d55-48c6-bb5f-c7aac3289f49","total_cost_usd":0.0874746,"usage":{"input_tokens":2,"cache_creation_input_tokens":4772,"cache_read_input_tokens":37634,"output_tokens":4,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":4772,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":4,"cache_read_input_tokens":37634,"cache_creation_input_tokens":4772,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4772},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1210,"outputTokens":19,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.0001305,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":4,"outputTokens":118,"cacheReadInputTokens":60001,"cacheCreationInputTokens":20039,"webSearchRequests":0,"costUSD":0.0873441,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":1,"subtype":"success","api_error_status":null,"result":"ok","ttft_ms":1063,"type":"result","duration_ms":1087,"uuid":"ff5b553b-3004-4b82-bfa1-1adf349a0d46","ttft_stream_ms":1062,"time_to_request_ms":15,"first_content_frame_ms":1062,"queued_turn_count":0,"result_index":1}} diff --git a/internal/claude/testdata/transcripts/TestResume-first.jsonl b/internal/claude/testdata/transcripts/TestResume-first.jsonl index 21fea57..55b039b 100644 --- a/internal/claude/testdata/transcripts/TestResume-first.jsonl +++ b/internal/claude/testdata/transcripts/TestResume-first.jsonl @@ -1,8 +1,8 @@ -{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_79a3affeb81ca6cc","type":"control_request"}} -{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_79a3affeb81ca6cc","response":{"commands":[{"name":"deep-research","description":"Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. (dynamic workflow)","argumentHint":"","builtin":true},{"name":"design","description":"Make a new Design artifact from a brief","argumentHint":"[what to design]","builtin":true},{"name":"slides","description":"Make a new Slides deck artifact from a brief","argumentHint":"[what the deck is about]","builtin":true},{"name":"design-sync","description":"Push a React design system to claude.ai/design. This runs a converter that bundles the real component code (from Storybook or a bare package) and uploads it. Use when the user runs /design-sync or says \"sync my design system to Claude Design\".","argumentHint":"[\u003cproject hint, e.g. \"Acme DS\"\u003e]","builtin":true},{"name":"dataviz","description":"Use this skill whenever you are about to create ANY chart, graph, plot, dashboard, or data visualization, in ANY output medium — an HTML or React artifact, inline SVG, plotting code in any library (matplotlib, plotly, d3, Recharts, …), an image/PNG you will render and upload, or a chart shared into Slack. Read it BEFORE writing the first line of chart code, choosing chart colors, building a stat tile / meter / KPI row, or laying out a dashboard. When the destination is a first-party document connector (host-designated, never self-described) that renders live charts, hand it the rows (inline, or as an uploaded data file the chart cites) rather than a rendered PNG/SVG — a picture of a chart loses hover, data inspection and per-value comments. Produces visualizations that read as one system — elegant, accessible, consistent in light and dark — using a brand-neutral placeholder palette you swap for your own. Teaches a design-system-agnostic method: a form heuristic, a color formula with a runnable validator, mark specs, and interaction rules. A validated default palette is documented in `references/palette.md` — swap that file's values for your brand's. Triggers on: \"chart\", \"graph\", \"plot\", \"data viz\", \"visualization\", \"dashboard\", \"analytics\", \"visualize data\", \"categorical colors\", \"sequential / diverging palette\", \"stat tile\", \"sparkline\", \"heatmap\", \"legend\", \"axis\", \"tooltip\", \"chart colors\", \"color by series\".","argumentHint":"","builtin":true},{"name":"artifact-diagramming","description":"Diagramming know-how for Artifacts - when a picture earns its place, how to draw one that shows the real mechanism, and the inline-SVG mechanics that keep it legible in both themes.","argumentHint":"","builtin":true},{"name":"artifact-capabilities","description":"Runtime capabilities a published Artifact page can be granted — behavior static HTML cannot provide on its own, such as the page reading live or connected data, remembering what people do on it (a poll, a sign-up sheet, a checklist, a document edited in place — it saves new versions of itself), keeping state shared across viewers, knowing who is viewing, asking Claude a question of its own, storing files people add, handing the viewer a file to save, or using the viewer's camera, microphone, location, screen or device motion. Serves this user's live capability roster and the typed call definitions. Load it whenever any such runtime behavior would make an artifact more useful, before writing the page.","argumentHint":"","builtin":true},{"name":"update-config","description":"Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme/model, suggest the /config command.","argumentHint":"","builtin":true},{"name":"verify","description":"Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.","argumentHint":"","builtin":true},{"name":"debug","description":"Enable debug logging for this session and help diagnose issues","argumentHint":"[issue description]","builtin":true},{"name":"code-review","description":"Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep multi-agent review in the cloud); with no level given, it reuses the level you typed last. Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review. Pass --max-findings \u003cn\u003e to report up to n findings, or --max-findings all for every finding. The choice stays until you pass --max-findings default. For ultra on a GitHub.com PR target, --post asks to post the finished review’s findings to the PR as a single comment from the user’s GitHub account (not a review; the launch dialog still confirms in interactive sessions, while non-interactive mode posts on the flag alone) and --no-post hides that option.","argumentHint":"[low|medium|high|xhigh|max|ultra] [--fix] [--comment] [\u003cpr#\u003e|\u003cbranch\u003e|\u003cpath\u003e] [--max-findings \u003cn\u003e|all]","aliases":["review"],"builtin":true},{"name":"simplify","description":"Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.","argumentHint":"[\u003ctarget\u003e]","builtin":true},{"name":"batch","description":"Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.","argumentHint":"\u003cinstruction\u003e","builtin":true},{"name":"fewer-permission-prompts","description":"Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.","argumentHint":"","builtin":true},{"name":"doctor","description":"Health-check the user's Claude Code setup and fix issues: diagnose installation health — what the `claude doctor` terminal diagnostics cover — from local data (duplicate or leftover installs, PATH, unparseable settings files, broken or colliding agent definitions, skills whose frontmatter fails to parse); find unused skills, MCP servers, and plugins versus their context cost and disable dead weight; deduplicate local CLAUDE.md files against checked-in ones; trim checked-in CLAUDE.md files by cutting content a session could derive from the codebase (directory layouts, tech-stack lists, architecture overviews) while keeping gotchas, rationale, and non-standard conventions; migrate always-loaded CLAUDE.md guidance into lazy skills and nested CLAUDE.md files; flag slow hooks and context-heavy extensions; check the installed version is current; make auto mode the default permission mode; and pre-approve frequently denied read-only commands. Use when the user asks for a doctor run, checkup, audit, tune-up, or cleanup of their Claude Code setup or configuration.","argumentHint":"[prompt-audit [\u003cpath\u003e]]","aliases":["checkup"],"builtin":true},{"name":"loop","description":"Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.","argumentHint":"[interval] [prompt]","aliases":["proactive"],"builtin":true},{"name":"schedule","description":"Create, update, list, or run scheduled cloud agents (routines) that execute on a cron schedule.","argumentHint":"","aliases":["routines"],"builtin":true},{"name":"claude-api","description":"Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).","argumentHint":"","builtin":true},{"name":"workflow-authoring","description":"Reference for writing a Workflow tool script (script API and gotchas, resume, quality patterns, worked examples). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.","argumentHint":"","builtin":true},{"name":"run","description":"Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).","argumentHint":"","builtin":true},{"name":"run-skill-generator","description":"Author or improve the run-\u003cunit\u003e skill - a per-project skill that tells agents how to build, launch, and drive this project's app. Use when the user asks to set up the project, get it running, write run instructions, or verify build/run steps work from a clean environment.","argumentHint":"","builtin":true},{"name":"plugin-authoring","description":"Make a mod: a change to Claude's own interface or behaviour, such as a live pane or panel, a band above the prompt, a status line, a toast, a slash command, or a hook on tool calls or prompts. Use to make, change or debug a mod or its hooks module.","argumentHint":"","builtin":true},{"name":"advisor","description":"Let Claude consult a stronger model at key moments","argumentHint":"[fable|opus|sonnet|off]","builtin":true},{"name":"agents","description":"(removed) Ask Claude to create/manage subagents, or edit .claude/agents/","argumentHint":"","builtin":true},{"name":"auto-mode-setup","description":"Teach auto mode about your environment, plus optional rule tweaks","argumentHint":"[--request-id \u003cuuid\u003e] (--wizard posture=… scope=… depth=… --propose | --expect-sha256 \u003c64-hex\u003e --apply-file \u003cpath\u003e)","builtin":true},{"name":"autocompact","description":"Configure the auto-compact window size","argumentHint":"[auto|\u003ctokens\u003e]","builtin":true},{"name":"clear","description":"Start a new session with empty context; previous session stays on disk (resumable with /resume)","argumentHint":"[name]","aliases":["reset","new"],"builtin":true},{"name":"color","description":"Set the prompt bar color for this session","argumentHint":"[red|blue|green|yellow|purple|orange|pink|cyan|default]","builtin":true},{"name":"compact","description":"Free up context by summarizing the conversation so far","argumentHint":"\u003coptional custom summarization instructions\u003e","builtin":true},{"name":"config","description":"Set a setting by key","argumentHint":"key=value","aliases":["settings"],"builtin":true},{"name":"output-style","description":"List output styles or switch to one","argumentHint":"[style]","builtin":true},{"name":"context","description":"Show current context usage","argumentHint":"","builtin":true},{"name":"effort","description":"Set effort level for model usage","argumentHint":"\u003clow|medium|high|xhigh|max|auto|ultracode [on|off]\u003e","builtin":true},{"name":"fast","description":"Toggle fast mode (Opus 5.5)","argumentHint":"[on|off]","builtin":true},{"name":"focus","description":"Toggle focus view: just your prompt, summary, and response","argumentHint":"[on|off]","builtin":true},{"name":"heapdump","description":"Dump the JS heap to the Desktop; on Linux with no Desktop folder, the home directory","argumentHint":"","builtin":true},{"name":"init","description":"Initialize a new CLAUDE.md file with codebase documentation","argumentHint":"","builtin":true},{"name":"mcp","description":"Manage MCP servers","argumentHint":"[reconnect|enable|disable [\u003cserver\u003e|all]]","builtin":true},{"name":"import","description":"Import config from another AI coding agent","argumentHint":"","builtin":true},{"name":"model","description":"Set the AI model for Claude Code","argumentHint":"\u003cmodel\u003e","builtin":true},{"name":"__remote-workflow","description":"Run the workflow script delivered in this session environment (server-launched sessions only)","argumentHint":"","builtin":true},{"name":"workflow-launch-exec","description":"Execute a server-launched workflow handoff (workflow_launch event sessions only)","argumentHint":"","builtin":true},{"name":"reload-plugins","description":"Activate pending plugin changes in the current session","argumentHint":"[--force]","builtin":true},{"name":"reload-skills","description":"Pick up skills added or changed on disk during this session","argumentHint":"","builtin":true},{"name":"rename","description":"Rename the current conversation","argumentHint":"[name]","aliases":["name"],"builtin":true},{"name":"ultrareview","description":"Start a cloud agent that finds and verifies bugs in your branch (~15-25 min, $5-$25 USD) · Runs in a cloud session. See https://code.claude.com/docs/en/claude-code-on-the-web","argumentHint":"","builtin":true},{"name":"security-review","description":"Complete a security review of the pending changes on the current branch","argumentHint":"","builtin":true},{"name":"usage-credits","description":"Configure usage credits or request them from your admin when you hit a limit","argumentHint":"","builtin":true},{"name":"extra-usage","description":"Renamed to /usage-credits","argumentHint":"","builtin":true},{"name":"usage","description":"Show session cost, plan usage, and what's contributing to your limits","argumentHint":"","aliases":["cost","stats"],"builtin":true},{"name":"insights","description":"Generate a report analyzing your Claude Code sessions","argumentHint":"","builtin":true},{"name":"recap","description":"Generate a one-line session recap now","argumentHint":"","builtin":true},{"name":"skill-doctor","description":"Show which loaded skills are unused and costing context","argumentHint":"","builtin":true},{"name":"goal","description":"Set a goal — keep working until the condition is met","argumentHint":"","builtin":true},{"name":"design-consent","description":"Grant Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"design-revoke","description":"Revoke Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"list-agents","description":"List subagents, teammates, and other Claude sessions you can message","argumentHint":"","aliases":["peers"],"builtin":true},{"name":"team-onboarding","description":"Help teammates ramp on Claude Code with a guide from your usage","argumentHint":"","builtin":true},{"name":"docs","description":"docs (editable docs people share and comment on; the default for any document, named as a doc or not: a document, report, proposal, resume, cover letter, letter, contract, policy, form, template, worksheet, essay, handbook, guide, how-to, cheat sheet, SOP or other writing to keep, share, collaborate on, send, submit, print or sign; a doc exports to Word, PDF, Markdown or Google Docs, so needing a file to send, attach, upload, submit or print is no reason to pick Word, and a file nobody asked for is a doc, not Word; a plan, comparison, summary or notes asked in chat stays in chat; a pasted claude.ai artifact link may be a doc: check with docs tools first; Word or another file format named, tracked changes wanted, or a .docx to change or use as a template → that format's skill): making one → if no docs-connector instructions are in context, call its `guide` (topic.instructions) first; then create the doc (headings only, no body) before any search, file read or plan, even with files attached. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docs"]},{"name":"docx","description":"Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers include: any mention of Microsoft Word Documents, such as 'Word doc', 'word document', '.docx', '.dotx', 'microsoft doc'. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a deliverable as a Word or .docx file (to download, email or print), use this skill. However, if they ask for a document, page, report, memo, or notes WITHOUT naming a file format and the session offers Claude's own dedicated document or page skill or connector, use that instead, even if they will email or print it. Do NOT use for PDFs, spreadsheets, Google Docs, or coding unrelated to document generation. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docx"]},{"name":"google-workspace","description":"Read this before the first Google Drive, Docs, Sheets or Slides connector call whenever the task creates or changes a Google file. Use this skill whenever the user wants to create or change a Google Doc, Sheet or Slides file in their Google Drive. Triggers include: a request that names Google Docs, Sheets, Slides or Drive and asks to make, edit, format, copy or rename a file; a docs.google.com link with a request to change that file, even a one-line fix or suggested edits; and any follow-up change to a Google file from earlier in the chat, even \"change it\" or \"add a tab\". Includes helper scripts for document positions, cell ranges and slide layout. However, if the user asks for a doc, deck or spreadsheet without naming Google, or gives a Google file only as source material for something new, use Claude's own output type instead. Do NOT use for read-only questions about a Google file, or for Word, Excel, PowerPoint or PDF files. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:google-workspace"]},{"name":"import-memory","description":"Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:import-memory"]},{"name":"morning","description":"Render the user's morning brief as a styled HTML artifact, or set it up as a recurring weekday task. Use only when the user explicitly asks to run, see, or set up their morning brief, or if they invoke /morning by name. A question about their day, schedule, or calendar is not by itself a request for the brief; answer it directly instead. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:morning"]},{"name":"pdf","description":"Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pdf"]},{"name":"pptx","description":"Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations as PowerPoint (.pptx) files; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email, summary, or creating a different type of slide deck); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user asks for a PowerPoint or .pptx file, or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. However, when the user asks for a deck, slides, a slide deck, or a presentation without naming a file format, default to using a dedicated slide-deck artifact type or a separate slides skill if this session offers one; otherwise, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pptx"]},{"name":"skill-creator","description":"Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:skill-creator"]},{"name":"xlsx","description":"Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:xlsx"]}],"agents":[{"name":"claude","description":"Catch-all for any task that doesn't fit a more specific agent. FleetView's default when no agent name is typed."},{"name":"claude-code-guide","description":"Use this agent when the user asks questions (\"Can Claude...\", \"Does Claude...\", \"How do I...\") about: (1) Claude Code (the CLI tool) - features, hooks, slash commands, MCP servers, settings, IDE integrations, keyboard shortcuts; (2) Claude Agent SDK - building custom agents; (3) Claude API (formerly Anthropic API) - Messages API for directly passing messages to Claude, Tool Runner (`client.beta.messages.tool_runner`) for running an agentic loop over your own tools, manual tool-use loops, Managed Agents for server-hosted agents with a managed sandbox, prompt caching, and general Anthropic SDK usage; (4) Claude Tag (Claude in Slack) - what it is, setting it up for a Slack workspace, `/install-slack-app`; (5) `claude plugin eval` (writing and running plugin eval suites, its JSON/report, sandbox, CI) and the `/skill-doctor` report. **IMPORTANT:** Before spawning a new agent, check if there is already a running or recently completed claude-code-guide agent that you can continue via SendMessage.","model":"haiku"},{"name":"Explore","description":"Fast read-only search agent for locating code. Use it to find files by pattern (eg. \"src/components/**/*.tsx\"), grep for symbols or keywords (eg. \"API endpoints\"), or answer \"where is X defined / which files reference Y.\" Do NOT use it for code review, design-doc auditing, cross-file consistency checks, or open-ended analysis — it reads excerpts rather than whole files and will miss content past its read window. When calling, specify search breadth: \"quick\" for a single targeted lookup, \"medium\" for moderate exploration, or \"very thorough\" to search across multiple locations and naming conventions.","model":"inherit"},{"name":"general-purpose","description":"General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you."},{"name":"Plan","description":"Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs.","model":"inherit"},{"name":"statusline-setup","description":"Use this agent to configure the user's Claude Code status line setting.","model":"sonnet"}],"output_style":"default","available_output_styles":["default","Proactive","Concise","Explanatory","Learning"],"user_output_styles_dir":"/Users/flamingcow/.claude/output-styles","models":[{"value":"default","resolvedModel":"claude-opus-5-5","displayName":"Default (recommended)","description":"Opus 5.5 · Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"opus","resolvedModel":"claude-opus-5-5","displayName":"Opus 5.5","description":"For complex work and everyday tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"fable","resolvedModel":"claude-fable-5-1","displayName":"Fable 5.1","description":"For your toughest challenges","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"sonnet","resolvedModel":"claude-sonnet-5-5","displayName":"Sonnet 5.5","description":"Most efficient for simpler tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"haiku","resolvedModel":"claude-haiku-5-5","displayName":"Haiku 5.5","description":"Fastest for quick answers","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-haiku-4-5-20251001","resolvedModel":"claude-haiku-4-5-20251001","displayName":"Haiku 4.5","description":"Fastest for quick answers"},{"value":"claude-sonnet-5","resolvedModel":"claude-sonnet-5","displayName":"Sonnet 5","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-5","resolvedModel":"claude-opus-5","displayName":"Opus 5","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-fable-5","resolvedModel":"claude-fable-5","displayName":"Fable 5","description":"Most capable for your hardest and longest-running tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-8","resolvedModel":"claude-opus-4-8","displayName":"Opus 4.8","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-opus-4-7","resolvedModel":"claude-opus-4-7","displayName":"Opus 4.7","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-6","resolvedModel":"claude-opus-4-6","displayName":"Opus 4.6","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-sonnet-4-6","resolvedModel":"claude-sonnet-4-6","displayName":"Sonnet 4.6","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true}],"account":{"email":"[redacted]","organization":"[redacted]'s Organization","subscriptionType":"Claude Max","apiProvider":"firstParty"},"pid":98361,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} +{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_e222f37e5177be56","type":"control_request"}} +{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_e222f37e5177be56","response":{"commands":[{"name":"deep-research","description":"Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. (dynamic workflow)","argumentHint":"","builtin":true},{"name":"design","description":"Make a new Design artifact from a brief","argumentHint":"[what to design]","builtin":true},{"name":"slides","description":"Make a new Slides deck artifact from a brief","argumentHint":"[what the deck is about]","builtin":true},{"name":"design-sync","description":"Push a React design system to claude.ai/design. This runs a converter that bundles the real component code (from Storybook or a bare package) and uploads it. Use when the user runs /design-sync or says \"sync my design system to Claude Design\".","argumentHint":"[\u003cproject hint, e.g. \"Acme DS\"\u003e]","builtin":true},{"name":"dataviz","description":"Use this skill whenever you are about to create ANY chart, graph, plot, dashboard, or data visualization, in ANY output medium — an HTML or React artifact, inline SVG, plotting code in any library (matplotlib, plotly, d3, Recharts, …), an image/PNG you will render and upload, or a chart shared into Slack. Read it BEFORE writing the first line of chart code, choosing chart colors, building a stat tile / meter / KPI row, or laying out a dashboard. When the destination is a first-party document connector (host-designated, never self-described) that renders live charts, hand it the rows (inline, or as an uploaded data file the chart cites) rather than a rendered PNG/SVG — a picture of a chart loses hover, data inspection and per-value comments. Produces visualizations that read as one system — elegant, accessible, consistent in light and dark — using a brand-neutral placeholder palette you swap for your own. Teaches a design-system-agnostic method: a form heuristic, a color formula with a runnable validator, mark specs, and interaction rules. A validated default palette is documented in `references/palette.md` — swap that file's values for your brand's. Triggers on: \"chart\", \"graph\", \"plot\", \"data viz\", \"visualization\", \"dashboard\", \"analytics\", \"visualize data\", \"categorical colors\", \"sequential / diverging palette\", \"stat tile\", \"sparkline\", \"heatmap\", \"legend\", \"axis\", \"tooltip\", \"chart colors\", \"color by series\".","argumentHint":"","builtin":true},{"name":"artifact-diagramming","description":"Diagramming know-how for Artifacts - when a picture earns its place, how to draw one that shows the real mechanism, and the inline-SVG mechanics that keep it legible in both themes.","argumentHint":"","builtin":true},{"name":"artifact-capabilities","description":"Runtime capabilities a published Artifact page can be granted — behavior static HTML cannot provide on its own, such as the page reading live or connected data, remembering what people do on it (a poll, a sign-up sheet, a checklist, a document edited in place — it saves new versions of itself), keeping state shared across viewers, knowing who is viewing, asking Claude a question of its own, storing files people add, handing the viewer a file to save, or using the viewer's camera, microphone, location, screen or device motion. Serves this user's live capability roster and the typed call definitions. Load it whenever any such runtime behavior would make an artifact more useful, before writing the page.","argumentHint":"","builtin":true},{"name":"update-config","description":"Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme/model, suggest the /config command.","argumentHint":"","builtin":true},{"name":"verify","description":"Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.","argumentHint":"","builtin":true},{"name":"debug","description":"Enable debug logging for this session and help diagnose issues","argumentHint":"[issue description]","builtin":true},{"name":"code-review","description":"Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep multi-agent review in the cloud); with no level given, it reuses the level you typed last. Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review. Pass --max-findings \u003cn\u003e to report up to n findings, or --max-findings all for every finding. The choice stays until you pass --max-findings default. For ultra on a GitHub.com PR target, --post asks to post the finished review’s findings to the PR as a single comment from the user’s GitHub account (not a review; the launch dialog still confirms in interactive sessions, while non-interactive mode posts on the flag alone) and --no-post hides that option.","argumentHint":"[low|medium|high|xhigh|max|ultra] [--fix] [--comment] [\u003cpr#\u003e|\u003cbranch\u003e|\u003cpath\u003e] [--max-findings \u003cn\u003e|all]","aliases":["review"],"builtin":true},{"name":"simplify","description":"Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.","argumentHint":"[\u003ctarget\u003e]","builtin":true},{"name":"batch","description":"Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.","argumentHint":"\u003cinstruction\u003e","builtin":true},{"name":"fewer-permission-prompts","description":"Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.","argumentHint":"","builtin":true},{"name":"doctor","description":"Health-check the user's Claude Code setup and fix issues: diagnose installation health — what the `claude doctor` terminal diagnostics cover — from local data (duplicate or leftover installs, PATH, unparseable settings files, broken or colliding agent definitions, skills whose frontmatter fails to parse); find unused skills, MCP servers, and plugins versus their context cost and disable dead weight; deduplicate local CLAUDE.md files against checked-in ones; trim checked-in CLAUDE.md files by cutting content a session could derive from the codebase (directory layouts, tech-stack lists, architecture overviews) while keeping gotchas, rationale, and non-standard conventions; migrate always-loaded CLAUDE.md guidance into lazy skills and nested CLAUDE.md files; flag slow hooks and context-heavy extensions; check the installed version is current; make auto mode the default permission mode; and pre-approve frequently denied read-only commands. Use when the user asks for a doctor run, checkup, audit, tune-up, or cleanup of their Claude Code setup or configuration.","argumentHint":"[prompt-audit [\u003cpath\u003e]]","aliases":["checkup"],"builtin":true},{"name":"loop","description":"Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.","argumentHint":"[interval] [prompt]","aliases":["proactive"],"builtin":true},{"name":"schedule","description":"Create, update, list, or run scheduled cloud agents (routines) that execute on a cron schedule.","argumentHint":"","aliases":["routines"],"builtin":true},{"name":"claude-api","description":"Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).","argumentHint":"","builtin":true},{"name":"workflow-authoring","description":"Reference for writing a Workflow tool script (script API and gotchas, resume, quality patterns, worked examples). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.","argumentHint":"","builtin":true},{"name":"run","description":"Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).","argumentHint":"","builtin":true},{"name":"run-skill-generator","description":"Author or improve the run-\u003cunit\u003e skill - a per-project skill that tells agents how to build, launch, and drive this project's app. Use when the user asks to set up the project, get it running, write run instructions, or verify build/run steps work from a clean environment.","argumentHint":"","builtin":true},{"name":"plugin-authoring","description":"Make a mod: a change to Claude's own interface or behaviour, such as a live pane or panel, a band above the prompt, a status line, a toast, a slash command, or a hook on tool calls or prompts. Use to make, change or debug a mod or its hooks module.","argumentHint":"","builtin":true},{"name":"advisor","description":"Let Claude consult a stronger model at key moments","argumentHint":"[fable|opus|sonnet|off]","builtin":true},{"name":"agents","description":"(removed) Ask Claude to create/manage subagents, or edit .claude/agents/","argumentHint":"","builtin":true},{"name":"auto-mode-setup","description":"Teach auto mode about your environment, plus optional rule tweaks","argumentHint":"[--request-id \u003cuuid\u003e] (--wizard posture=… scope=… depth=… --propose | --expect-sha256 \u003c64-hex\u003e --apply-file \u003cpath\u003e)","builtin":true},{"name":"autocompact","description":"Configure the auto-compact window size","argumentHint":"[auto|\u003ctokens\u003e]","builtin":true},{"name":"clear","description":"Start a new session with empty context; previous session stays on disk (resumable with /resume)","argumentHint":"[name]","aliases":["reset","new"],"builtin":true},{"name":"color","description":"Set the prompt bar color for this session","argumentHint":"[red|blue|green|yellow|purple|orange|pink|cyan|default]","builtin":true},{"name":"compact","description":"Free up context by summarizing the conversation so far","argumentHint":"\u003coptional custom summarization instructions\u003e","builtin":true},{"name":"config","description":"Set a setting by key","argumentHint":"key=value","aliases":["settings"],"builtin":true},{"name":"output-style","description":"List output styles or switch to one","argumentHint":"[style]","builtin":true},{"name":"context","description":"Show current context usage","argumentHint":"","builtin":true},{"name":"effort","description":"Set effort level for model usage","argumentHint":"\u003clow|medium|high|xhigh|max|auto|ultracode [on|off]\u003e","builtin":true},{"name":"fast","description":"Toggle fast mode (Opus 5.5)","argumentHint":"[on|off]","builtin":true},{"name":"focus","description":"Toggle focus view: just your prompt, summary, and response","argumentHint":"[on|off]","builtin":true},{"name":"heapdump","description":"Dump the JS heap to the Desktop; on Linux with no Desktop folder, the home directory","argumentHint":"","builtin":true},{"name":"init","description":"Initialize a new CLAUDE.md file with codebase documentation","argumentHint":"","builtin":true},{"name":"mcp","description":"Manage MCP servers","argumentHint":"[reconnect|enable|disable [\u003cserver\u003e|all]]","builtin":true},{"name":"import","description":"Import config from another AI coding agent","argumentHint":"","builtin":true},{"name":"model","description":"Set the AI model for Claude Code","argumentHint":"\u003cmodel\u003e","builtin":true},{"name":"__remote-workflow","description":"Run the workflow script delivered in this session environment (server-launched sessions only)","argumentHint":"","builtin":true},{"name":"workflow-launch-exec","description":"Execute a server-launched workflow handoff (workflow_launch event sessions only)","argumentHint":"","builtin":true},{"name":"reload-plugins","description":"Activate pending plugin changes in the current session","argumentHint":"[--force]","builtin":true},{"name":"reload-skills","description":"Pick up skills added or changed on disk during this session","argumentHint":"","builtin":true},{"name":"rename","description":"Rename the current conversation","argumentHint":"[name]","aliases":["name"],"builtin":true},{"name":"ultrareview","description":"Start a cloud agent that finds and verifies bugs in your branch (~15-25 min, $5-$25 USD) · Runs in a cloud session. See https://code.claude.com/docs/en/claude-code-on-the-web","argumentHint":"","builtin":true},{"name":"security-review","description":"Complete a security review of the pending changes on the current branch","argumentHint":"","builtin":true},{"name":"usage-credits","description":"Configure usage credits or request them from your admin when you hit a limit","argumentHint":"","builtin":true},{"name":"extra-usage","description":"Renamed to /usage-credits","argumentHint":"","builtin":true},{"name":"usage","description":"Show session cost, plan usage, and what's contributing to your limits","argumentHint":"","aliases":["cost","stats"],"builtin":true},{"name":"insights","description":"Generate a report analyzing your Claude Code sessions","argumentHint":"","builtin":true},{"name":"recap","description":"Generate a one-line session recap now","argumentHint":"","builtin":true},{"name":"skill-doctor","description":"Show which loaded skills are unused and costing context","argumentHint":"","builtin":true},{"name":"goal","description":"Set a goal — keep working until the condition is met","argumentHint":"","builtin":true},{"name":"design-consent","description":"Grant Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"design-revoke","description":"Revoke Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"list-agents","description":"List subagents, teammates, and other Claude sessions you can message","argumentHint":"","aliases":["peers"],"builtin":true},{"name":"team-onboarding","description":"Help teammates ramp on Claude Code with a guide from your usage","argumentHint":"","builtin":true},{"name":"docs","description":"docs (editable docs people share and comment on; the default for any document, named as a doc or not: a document, report, proposal, resume, cover letter, letter, contract, policy, form, template, worksheet, essay, handbook, guide, how-to, cheat sheet, SOP or other writing to keep, share, collaborate on, send, submit, print or sign; a doc exports to Word, PDF, Markdown or Google Docs, so needing a file to send, attach, upload, submit or print is no reason to pick Word, and a file nobody asked for is a doc, not Word; a plan, comparison, summary or notes asked in chat stays in chat; a pasted claude.ai artifact link may be a doc: check with docs tools first; Word or another file format named, tracked changes wanted, or a .docx to change or use as a template → that format's skill): making one → if no docs-connector instructions are in context, call its `guide` (topic.instructions) first; then create the doc (headings only, no body) before any search, file read or plan, even with files attached. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docs"]},{"name":"docx","description":"Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers include: any mention of Microsoft Word Documents, such as 'Word doc', 'word document', '.docx', '.dotx', 'microsoft doc'. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a deliverable as a Word or .docx file (to download, email or print), use this skill. However, if they ask for a document, page, report, memo, or notes WITHOUT naming a file format and the session offers Claude's own dedicated document or page skill or connector, use that instead, even if they will email or print it. Do NOT use for PDFs, spreadsheets, Google Docs, or coding unrelated to document generation. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docx"]},{"name":"google-workspace","description":"Read this before the first Google Drive, Docs, Sheets or Slides connector call whenever the task creates or changes a Google file. Use this skill whenever the user wants to create or change a Google Doc, Sheet or Slides file in their Google Drive. Triggers include: a request that names Google Docs, Sheets, Slides or Drive and asks to make, edit, format, copy or rename a file; a docs.google.com link with a request to change that file, even a one-line fix or suggested edits; and any follow-up change to a Google file from earlier in the chat, even \"change it\" or \"add a tab\". Includes helper scripts for document positions, cell ranges and slide layout. However, if the user asks for a doc, deck or spreadsheet without naming Google, or gives a Google file only as source material for something new, use Claude's own output type instead. Do NOT use for read-only questions about a Google file, or for Word, Excel, PowerPoint or PDF files. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:google-workspace"]},{"name":"import-memory","description":"Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:import-memory"]},{"name":"morning","description":"Render the user's morning brief as a styled HTML artifact, or set it up as a recurring weekday task. Use only when the user explicitly asks to run, see, or set up their morning brief, or if they invoke /morning by name. A question about their day, schedule, or calendar is not by itself a request for the brief; answer it directly instead. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:morning"]},{"name":"pdf","description":"Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pdf"]},{"name":"pptx","description":"Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations as PowerPoint (.pptx) files; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email, summary, or creating a different type of slide deck); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user asks for a PowerPoint or .pptx file, or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. However, when the user asks for a deck, slides, a slide deck, or a presentation without naming a file format, default to using a dedicated slide-deck artifact type or a separate slides skill if this session offers one; otherwise, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pptx"]},{"name":"skill-creator","description":"Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:skill-creator"]},{"name":"xlsx","description":"Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:xlsx"]}],"agents":[{"name":"claude","description":"Catch-all for any task that doesn't fit a more specific agent. FleetView's default when no agent name is typed."},{"name":"claude-code-guide","description":"Use this agent when the user asks questions (\"Can Claude...\", \"Does Claude...\", \"How do I...\") about: (1) Claude Code (the CLI tool) - features, hooks, slash commands, MCP servers, settings, IDE integrations, keyboard shortcuts; (2) Claude Agent SDK - building custom agents; (3) Claude API (formerly Anthropic API) - Messages API for directly passing messages to Claude, Tool Runner (`client.beta.messages.tool_runner`) for running an agentic loop over your own tools, manual tool-use loops, Managed Agents for server-hosted agents with a managed sandbox, prompt caching, and general Anthropic SDK usage; (4) Claude Tag (Claude in Slack) - what it is, setting it up for a Slack workspace, `/install-slack-app`; (5) `claude plugin eval` (writing and running plugin eval suites, its JSON/report, sandbox, CI) and the `/skill-doctor` report. **IMPORTANT:** Before spawning a new agent, check if there is already a running or recently completed claude-code-guide agent that you can continue via SendMessage.","model":"haiku"},{"name":"Explore","description":"Fast read-only search agent for locating code. Use it to find files by pattern (eg. \"src/components/**/*.tsx\"), grep for symbols or keywords (eg. \"API endpoints\"), or answer \"where is X defined / which files reference Y.\" Do NOT use it for code review, design-doc auditing, cross-file consistency checks, or open-ended analysis — it reads excerpts rather than whole files and will miss content past its read window. When calling, specify search breadth: \"quick\" for a single targeted lookup, \"medium\" for moderate exploration, or \"very thorough\" to search across multiple locations and naming conventions.","model":"inherit"},{"name":"general-purpose","description":"General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you."},{"name":"Plan","description":"Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs.","model":"inherit"},{"name":"statusline-setup","description":"Use this agent to configure the user's Claude Code status line setting.","model":"sonnet"}],"output_style":"default","available_output_styles":["default","Proactive","Concise","Explanatory","Learning"],"user_output_styles_dir":"/Users/flamingcow/.claude/output-styles","models":[{"value":"default","resolvedModel":"claude-opus-5-5","displayName":"Default (recommended)","description":"Opus 5.5 · Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"opus","resolvedModel":"claude-opus-5-5","displayName":"Opus 5.5","description":"For complex work and everyday tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"fable","resolvedModel":"claude-fable-5-1","displayName":"Fable 5.1","description":"For your toughest challenges","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"sonnet","resolvedModel":"claude-sonnet-5-5","displayName":"Sonnet 5.5","description":"Most efficient for simpler tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"haiku","resolvedModel":"claude-haiku-5-5","displayName":"Haiku 5.5","description":"Fastest for quick answers","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-haiku-4-5-20251001","resolvedModel":"claude-haiku-4-5-20251001","displayName":"Haiku 4.5","description":"Fastest for quick answers"},{"value":"claude-sonnet-5","resolvedModel":"claude-sonnet-5","displayName":"Sonnet 5","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-5","resolvedModel":"claude-opus-5","displayName":"Opus 5","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-fable-5","resolvedModel":"claude-fable-5","displayName":"Fable 5","description":"Most capable for your hardest and longest-running tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-8","resolvedModel":"claude-opus-4-8","displayName":"Opus 4.8","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-opus-4-7","resolvedModel":"claude-opus-4-7","displayName":"Opus 4.7","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-6","resolvedModel":"claude-opus-4-6","displayName":"Opus 4.6","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-sonnet-4-6","resolvedModel":"claude-sonnet-4-6","displayName":"Sonnet 4.6","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true}],"account":{"email":"[redacted]","organization":"[redacted]'s Organization","subscriptionType":"Claude Max","apiProvider":"firstParty"},"pid":2402,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} {"dir":"send","msg":{"message":{"content":"Remember the codeword AZURE-17. Reply with the single word ok.","role":"user"},"parent_tool_use_id":null,"session_id":"","type":"user"}} -{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestResume329762661/001","session_id":"8d41cb35-d2d6-4384-a660-f3269b91d3fa","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","LSP","Monitor","NotebookEdit","PushNotification","Read","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"pending","source":"claudeai"},{"name":"claude.ai Heliosian","status":"pending","source":"claudeai"},{"name":"claude.ai Fastmail","status":"pending","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"2553ecd4-6e0d-463a-b8d8-98b88d68abc5","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestResume329762661-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestResume329762661-001/8d41cb35-d2d6-4384-a660-f3269b91d3fa/scratchpad","messaging_socket_path":"/tmp/cc-socks/98361.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"8d41cb35-d2d6-4384-a660-f3269b91d3fa","uuid":"dc081894-65c6-4b68-b8d8-a57d004c1d71"}} -{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.01,"resetsAt":1792054200},"seven_day":{"utilization":0.34,"resetsAt":1792270800}}},"uuid":"bc240332-8e40-469f-b278-8bfdb3566a9b","session_id":"8d41cb35-d2d6-4384-a660-f3269b91d3fa"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3Mazd3tsVvEfJ3XYgdP","type":"message","role":"assistant","content":[{"type":"text","text":"ok"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15230,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15230},"output_tokens":4,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"8d41cb35-d2d6-4384-a660-f3269b91d3fa","uuid":"50cce199-27c9-4cfd-b5b6-e5e9cceb5f23","timestamp":"2026-10-15T04:01:03.384Z","request_id":"req_011Cg3MazNvngW2CLGMcm6B2"}} -{"dir":"recv","msg":{"duration_api_ms":2309,"stop_reason":"end_turn","session_id":"8d41cb35-d2d6-4384-a660-f3269b91d3fa","total_cost_usd":0.06333,"usage":{"input_tokens":2,"cache_creation_input_tokens":15230,"cache_read_input_tokens":22367,"output_tokens":4,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":15230,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":4,"cache_read_input_tokens":22367,"cache_creation_input_tokens":15230,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15230},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1188,"outputTokens":21,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.00012930000000000003,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":2,"outputTokens":4,"cacheReadInputTokens":22367,"cacheCreationInputTokens":15230,"webSearchRequests":0,"costUSD":0.0632007,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":1,"subtype":"success","api_error_status":null,"result":"ok","ttft_ms":1714,"type":"result","duration_ms":1757,"uuid":"42e1b61e-4004-4970-a87f-c725f0a2e3ba","ttft_stream_ms":1711,"time_to_request_ms":26,"first_content_frame_ms":1711,"queued_turn_count":0,"result_index":0}} +{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestResume1583807402/001","session_id":"f2415e0e-38dd-4049-bb5f-4405d4db75da","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","LSP","Monitor","NotebookEdit","PushNotification","Read","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"pending","source":"claudeai"},{"name":"claude.ai Heliosian","status":"pending","source":"claudeai"},{"name":"claude.ai Fastmail","status":"pending","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"aa74c9e6-284f-4164-8019-e9e5dc16fd30","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestResume1583807402-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestResume1583807402-001/f2415e0e-38dd-4049-bb5f-4405d4db75da/scratchpad","messaging_socket_path":"/tmp/cc-socks/2402.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"f2415e0e-38dd-4049-bb5f-4405d4db75da","uuid":"552e52c1-ddc9-4772-8ad8-d459bafbde98"}} +{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.01,"resetsAt":1792054200},"seven_day":{"utilization":0.34,"resetsAt":1792270800}}},"uuid":"81622214-3784-40e7-ba2d-ecb8871d6ff0","session_id":"f2415e0e-38dd-4049-bb5f-4405d4db75da"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3MyvPDGcDPij6iD7KNC","type":"message","role":"assistant","content":[{"type":"text","text":"ok"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15234,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15234},"output_tokens":4,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"f2415e0e-38dd-4049-bb5f-4405d4db75da","uuid":"f6b87afd-7dde-4bcc-adb8-9175f2961983","timestamp":"2026-10-15T04:06:14.252Z","request_id":"req_011Cg3MyvAZKRGsK7x6FEJGh"}} +{"dir":"recv","msg":{"duration_api_ms":2091,"stop_reason":"end_turn","session_id":"f2415e0e-38dd-4049-bb5f-4405d4db75da","total_cost_usd":0.063346,"usage":{"input_tokens":2,"cache_creation_input_tokens":15234,"cache_read_input_tokens":22367,"output_tokens":4,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":15234,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":4,"cache_read_input_tokens":22367,"cache_creation_input_tokens":15234,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15234},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1188,"outputTokens":21,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.00012930000000000003,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":2,"outputTokens":4,"cacheReadInputTokens":22367,"cacheCreationInputTokens":15234,"webSearchRequests":0,"costUSD":0.0632167,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":1,"subtype":"success","api_error_status":null,"result":"ok","ttft_ms":1560,"type":"result","duration_ms":1578,"uuid":"004b7692-a11c-4d96-a418-8b1d52862b2d","ttft_stream_ms":1558,"time_to_request_ms":34,"first_content_frame_ms":1559,"queued_turn_count":0,"result_index":0}} diff --git a/internal/claude/testdata/transcripts/TestResume-resumed.jsonl b/internal/claude/testdata/transcripts/TestResume-resumed.jsonl index fa2542d..32cfafe 100644 --- a/internal/claude/testdata/transcripts/TestResume-resumed.jsonl +++ b/internal/claude/testdata/transcripts/TestResume-resumed.jsonl @@ -1,8 +1,8 @@ -{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_7faf36c3a900d24a","type":"control_request"}} -{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_7faf36c3a900d24a","response":{"commands":[{"name":"deep-research","description":"Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. (dynamic workflow)","argumentHint":"","builtin":true},{"name":"design","description":"Make a new Design artifact from a brief","argumentHint":"[what to design]","builtin":true},{"name":"slides","description":"Make a new Slides deck artifact from a brief","argumentHint":"[what the deck is about]","builtin":true},{"name":"design-sync","description":"Push a React design system to claude.ai/design. This runs a converter that bundles the real component code (from Storybook or a bare package) and uploads it. Use when the user runs /design-sync or says \"sync my design system to Claude Design\".","argumentHint":"[\u003cproject hint, e.g. \"Acme DS\"\u003e]","builtin":true},{"name":"dataviz","description":"Use this skill whenever you are about to create ANY chart, graph, plot, dashboard, or data visualization, in ANY output medium — an HTML or React artifact, inline SVG, plotting code in any library (matplotlib, plotly, d3, Recharts, …), an image/PNG you will render and upload, or a chart shared into Slack. Read it BEFORE writing the first line of chart code, choosing chart colors, building a stat tile / meter / KPI row, or laying out a dashboard. When the destination is a first-party document connector (host-designated, never self-described) that renders live charts, hand it the rows (inline, or as an uploaded data file the chart cites) rather than a rendered PNG/SVG — a picture of a chart loses hover, data inspection and per-value comments. Produces visualizations that read as one system — elegant, accessible, consistent in light and dark — using a brand-neutral placeholder palette you swap for your own. Teaches a design-system-agnostic method: a form heuristic, a color formula with a runnable validator, mark specs, and interaction rules. A validated default palette is documented in `references/palette.md` — swap that file's values for your brand's. Triggers on: \"chart\", \"graph\", \"plot\", \"data viz\", \"visualization\", \"dashboard\", \"analytics\", \"visualize data\", \"categorical colors\", \"sequential / diverging palette\", \"stat tile\", \"sparkline\", \"heatmap\", \"legend\", \"axis\", \"tooltip\", \"chart colors\", \"color by series\".","argumentHint":"","builtin":true},{"name":"artifact-diagramming","description":"Diagramming know-how for Artifacts - when a picture earns its place, how to draw one that shows the real mechanism, and the inline-SVG mechanics that keep it legible in both themes.","argumentHint":"","builtin":true},{"name":"artifact-capabilities","description":"Runtime capabilities a published Artifact page can be granted — behavior static HTML cannot provide on its own, such as the page reading live or connected data, remembering what people do on it (a poll, a sign-up sheet, a checklist, a document edited in place — it saves new versions of itself), keeping state shared across viewers, knowing who is viewing, asking Claude a question of its own, storing files people add, handing the viewer a file to save, or using the viewer's camera, microphone, location, screen or device motion. Serves this user's live capability roster and the typed call definitions. Load it whenever any such runtime behavior would make an artifact more useful, before writing the page.","argumentHint":"","builtin":true},{"name":"update-config","description":"Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme/model, suggest the /config command.","argumentHint":"","builtin":true},{"name":"verify","description":"Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.","argumentHint":"","builtin":true},{"name":"debug","description":"Enable debug logging for this session and help diagnose issues","argumentHint":"[issue description]","builtin":true},{"name":"code-review","description":"Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep multi-agent review in the cloud); with no level given, it reuses the level you typed last. Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review. Pass --max-findings \u003cn\u003e to report up to n findings, or --max-findings all for every finding. The choice stays until you pass --max-findings default. For ultra on a GitHub.com PR target, --post asks to post the finished review’s findings to the PR as a single comment from the user’s GitHub account (not a review; the launch dialog still confirms in interactive sessions, while non-interactive mode posts on the flag alone) and --no-post hides that option.","argumentHint":"[low|medium|high|xhigh|max|ultra] [--fix] [--comment] [\u003cpr#\u003e|\u003cbranch\u003e|\u003cpath\u003e] [--max-findings \u003cn\u003e|all]","aliases":["review"],"builtin":true},{"name":"simplify","description":"Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.","argumentHint":"[\u003ctarget\u003e]","builtin":true},{"name":"batch","description":"Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.","argumentHint":"\u003cinstruction\u003e","builtin":true},{"name":"fewer-permission-prompts","description":"Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.","argumentHint":"","builtin":true},{"name":"doctor","description":"Health-check the user's Claude Code setup and fix issues: diagnose installation health — what the `claude doctor` terminal diagnostics cover — from local data (duplicate or leftover installs, PATH, unparseable settings files, broken or colliding agent definitions, skills whose frontmatter fails to parse); find unused skills, MCP servers, and plugins versus their context cost and disable dead weight; deduplicate local CLAUDE.md files against checked-in ones; trim checked-in CLAUDE.md files by cutting content a session could derive from the codebase (directory layouts, tech-stack lists, architecture overviews) while keeping gotchas, rationale, and non-standard conventions; migrate always-loaded CLAUDE.md guidance into lazy skills and nested CLAUDE.md files; flag slow hooks and context-heavy extensions; check the installed version is current; make auto mode the default permission mode; and pre-approve frequently denied read-only commands. Use when the user asks for a doctor run, checkup, audit, tune-up, or cleanup of their Claude Code setup or configuration.","argumentHint":"[prompt-audit [\u003cpath\u003e]]","aliases":["checkup"],"builtin":true},{"name":"loop","description":"Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.","argumentHint":"[interval] [prompt]","aliases":["proactive"],"builtin":true},{"name":"schedule","description":"Create, update, list, or run scheduled cloud agents (routines) that execute on a cron schedule.","argumentHint":"","aliases":["routines"],"builtin":true},{"name":"claude-api","description":"Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).","argumentHint":"","builtin":true},{"name":"workflow-authoring","description":"Reference for writing a Workflow tool script (script API and gotchas, resume, quality patterns, worked examples). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.","argumentHint":"","builtin":true},{"name":"run","description":"Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).","argumentHint":"","builtin":true},{"name":"run-skill-generator","description":"Author or improve the run-\u003cunit\u003e skill - a per-project skill that tells agents how to build, launch, and drive this project's app. Use when the user asks to set up the project, get it running, write run instructions, or verify build/run steps work from a clean environment.","argumentHint":"","builtin":true},{"name":"plugin-authoring","description":"Make a mod: a change to Claude's own interface or behaviour, such as a live pane or panel, a band above the prompt, a status line, a toast, a slash command, or a hook on tool calls or prompts. Use to make, change or debug a mod or its hooks module.","argumentHint":"","builtin":true},{"name":"advisor","description":"Let Claude consult a stronger model at key moments","argumentHint":"[fable|opus|sonnet|off]","builtin":true},{"name":"agents","description":"(removed) Ask Claude to create/manage subagents, or edit .claude/agents/","argumentHint":"","builtin":true},{"name":"auto-mode-setup","description":"Teach auto mode about your environment, plus optional rule tweaks","argumentHint":"[--request-id \u003cuuid\u003e] (--wizard posture=… scope=… depth=… --propose | --expect-sha256 \u003c64-hex\u003e --apply-file \u003cpath\u003e)","builtin":true},{"name":"autocompact","description":"Configure the auto-compact window size","argumentHint":"[auto|\u003ctokens\u003e]","builtin":true},{"name":"clear","description":"Start a new session with empty context; previous session stays on disk (resumable with /resume)","argumentHint":"[name]","aliases":["reset","new"],"builtin":true},{"name":"color","description":"Set the prompt bar color for this session","argumentHint":"[red|blue|green|yellow|purple|orange|pink|cyan|default]","builtin":true},{"name":"compact","description":"Free up context by summarizing the conversation so far","argumentHint":"\u003coptional custom summarization instructions\u003e","builtin":true},{"name":"config","description":"Set a setting by key","argumentHint":"key=value","aliases":["settings"],"builtin":true},{"name":"output-style","description":"List output styles or switch to one","argumentHint":"[style]","builtin":true},{"name":"context","description":"Show current context usage","argumentHint":"","builtin":true},{"name":"effort","description":"Set effort level for model usage","argumentHint":"\u003clow|medium|high|xhigh|max|auto|ultracode [on|off]\u003e","builtin":true},{"name":"fast","description":"Toggle fast mode (Opus 5.5)","argumentHint":"[on|off]","builtin":true},{"name":"focus","description":"Toggle focus view: just your prompt, summary, and response","argumentHint":"[on|off]","builtin":true},{"name":"heapdump","description":"Dump the JS heap to the Desktop; on Linux with no Desktop folder, the home directory","argumentHint":"","builtin":true},{"name":"init","description":"Initialize a new CLAUDE.md file with codebase documentation","argumentHint":"","builtin":true},{"name":"mcp","description":"Manage MCP servers","argumentHint":"[reconnect|enable|disable [\u003cserver\u003e|all]]","builtin":true},{"name":"import","description":"Import config from another AI coding agent","argumentHint":"","builtin":true},{"name":"model","description":"Set the AI model for Claude Code","argumentHint":"\u003cmodel\u003e","builtin":true},{"name":"__remote-workflow","description":"Run the workflow script delivered in this session environment (server-launched sessions only)","argumentHint":"","builtin":true},{"name":"workflow-launch-exec","description":"Execute a server-launched workflow handoff (workflow_launch event sessions only)","argumentHint":"","builtin":true},{"name":"reload-plugins","description":"Activate pending plugin changes in the current session","argumentHint":"[--force]","builtin":true},{"name":"reload-skills","description":"Pick up skills added or changed on disk during this session","argumentHint":"","builtin":true},{"name":"rename","description":"Rename the current conversation","argumentHint":"[name]","aliases":["name"],"builtin":true},{"name":"ultrareview","description":"Start a cloud agent that finds and verifies bugs in your branch (~15-25 min, $5-$25 USD) · Runs in a cloud session. See https://code.claude.com/docs/en/claude-code-on-the-web","argumentHint":"","builtin":true},{"name":"security-review","description":"Complete a security review of the pending changes on the current branch","argumentHint":"","builtin":true},{"name":"usage-credits","description":"Configure usage credits or request them from your admin when you hit a limit","argumentHint":"","builtin":true},{"name":"extra-usage","description":"Renamed to /usage-credits","argumentHint":"","builtin":true},{"name":"usage","description":"Show session cost, plan usage, and what's contributing to your limits","argumentHint":"","aliases":["cost","stats"],"builtin":true},{"name":"insights","description":"Generate a report analyzing your Claude Code sessions","argumentHint":"","builtin":true},{"name":"recap","description":"Generate a one-line session recap now","argumentHint":"","builtin":true},{"name":"skill-doctor","description":"Show which loaded skills are unused and costing context","argumentHint":"","builtin":true},{"name":"goal","description":"Set a goal — keep working until the condition is met","argumentHint":"","builtin":true},{"name":"design-consent","description":"Grant Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"design-revoke","description":"Revoke Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"list-agents","description":"List subagents, teammates, and other Claude sessions you can message","argumentHint":"","aliases":["peers"],"builtin":true},{"name":"team-onboarding","description":"Help teammates ramp on Claude Code with a guide from your usage","argumentHint":"","builtin":true},{"name":"docs","description":"docs (editable docs people share and comment on; the default for any document, named as a doc or not: a document, report, proposal, resume, cover letter, letter, contract, policy, form, template, worksheet, essay, handbook, guide, how-to, cheat sheet, SOP or other writing to keep, share, collaborate on, send, submit, print or sign; a doc exports to Word, PDF, Markdown or Google Docs, so needing a file to send, attach, upload, submit or print is no reason to pick Word, and a file nobody asked for is a doc, not Word; a plan, comparison, summary or notes asked in chat stays in chat; a pasted claude.ai artifact link may be a doc: check with docs tools first; Word or another file format named, tracked changes wanted, or a .docx to change or use as a template → that format's skill): making one → if no docs-connector instructions are in context, call its `guide` (topic.instructions) first; then create the doc (headings only, no body) before any search, file read or plan, even with files attached. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docs"]},{"name":"docx","description":"Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers include: any mention of Microsoft Word Documents, such as 'Word doc', 'word document', '.docx', '.dotx', 'microsoft doc'. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a deliverable as a Word or .docx file (to download, email or print), use this skill. However, if they ask for a document, page, report, memo, or notes WITHOUT naming a file format and the session offers Claude's own dedicated document or page skill or connector, use that instead, even if they will email or print it. Do NOT use for PDFs, spreadsheets, Google Docs, or coding unrelated to document generation. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docx"]},{"name":"google-workspace","description":"Read this before the first Google Drive, Docs, Sheets or Slides connector call whenever the task creates or changes a Google file. Use this skill whenever the user wants to create or change a Google Doc, Sheet or Slides file in their Google Drive. Triggers include: a request that names Google Docs, Sheets, Slides or Drive and asks to make, edit, format, copy or rename a file; a docs.google.com link with a request to change that file, even a one-line fix or suggested edits; and any follow-up change to a Google file from earlier in the chat, even \"change it\" or \"add a tab\". Includes helper scripts for document positions, cell ranges and slide layout. However, if the user asks for a doc, deck or spreadsheet without naming Google, or gives a Google file only as source material for something new, use Claude's own output type instead. Do NOT use for read-only questions about a Google file, or for Word, Excel, PowerPoint or PDF files. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:google-workspace"]},{"name":"import-memory","description":"Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:import-memory"]},{"name":"morning","description":"Render the user's morning brief as a styled HTML artifact, or set it up as a recurring weekday task. Use only when the user explicitly asks to run, see, or set up their morning brief, or if they invoke /morning by name. A question about their day, schedule, or calendar is not by itself a request for the brief; answer it directly instead. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:morning"]},{"name":"pdf","description":"Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pdf"]},{"name":"pptx","description":"Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations as PowerPoint (.pptx) files; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email, summary, or creating a different type of slide deck); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user asks for a PowerPoint or .pptx file, or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. However, when the user asks for a deck, slides, a slide deck, or a presentation without naming a file format, default to using a dedicated slide-deck artifact type or a separate slides skill if this session offers one; otherwise, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pptx"]},{"name":"skill-creator","description":"Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:skill-creator"]},{"name":"xlsx","description":"Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:xlsx"]}],"agents":[{"name":"claude","description":"Catch-all for any task that doesn't fit a more specific agent. FleetView's default when no agent name is typed."},{"name":"claude-code-guide","description":"Use this agent when the user asks questions (\"Can Claude...\", \"Does Claude...\", \"How do I...\") about: (1) Claude Code (the CLI tool) - features, hooks, slash commands, MCP servers, settings, IDE integrations, keyboard shortcuts; (2) Claude Agent SDK - building custom agents; (3) Claude API (formerly Anthropic API) - Messages API for directly passing messages to Claude, Tool Runner (`client.beta.messages.tool_runner`) for running an agentic loop over your own tools, manual tool-use loops, Managed Agents for server-hosted agents with a managed sandbox, prompt caching, and general Anthropic SDK usage; (4) Claude Tag (Claude in Slack) - what it is, setting it up for a Slack workspace, `/install-slack-app`; (5) `claude plugin eval` (writing and running plugin eval suites, its JSON/report, sandbox, CI) and the `/skill-doctor` report. **IMPORTANT:** Before spawning a new agent, check if there is already a running or recently completed claude-code-guide agent that you can continue via SendMessage.","model":"haiku"},{"name":"Explore","description":"Fast read-only search agent for locating code. Use it to find files by pattern (eg. \"src/components/**/*.tsx\"), grep for symbols or keywords (eg. \"API endpoints\"), or answer \"where is X defined / which files reference Y.\" Do NOT use it for code review, design-doc auditing, cross-file consistency checks, or open-ended analysis — it reads excerpts rather than whole files and will miss content past its read window. When calling, specify search breadth: \"quick\" for a single targeted lookup, \"medium\" for moderate exploration, or \"very thorough\" to search across multiple locations and naming conventions.","model":"inherit"},{"name":"general-purpose","description":"General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you."},{"name":"Plan","description":"Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs.","model":"inherit"},{"name":"statusline-setup","description":"Use this agent to configure the user's Claude Code status line setting.","model":"sonnet"}],"output_style":"default","available_output_styles":["default","Proactive","Concise","Explanatory","Learning"],"user_output_styles_dir":"/Users/flamingcow/.claude/output-styles","models":[{"value":"default","resolvedModel":"claude-opus-5-5","displayName":"Default (recommended)","description":"Opus 5.5 · Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"opus","resolvedModel":"claude-opus-5-5","displayName":"Opus 5.5","description":"For complex work and everyday tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"fable","resolvedModel":"claude-fable-5-1","displayName":"Fable 5.1","description":"For your toughest challenges","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"sonnet","resolvedModel":"claude-sonnet-5-5","displayName":"Sonnet 5.5","description":"Most efficient for simpler tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"haiku","resolvedModel":"claude-haiku-5-5","displayName":"Haiku 5.5","description":"Fastest for quick answers","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-haiku-4-5-20251001","resolvedModel":"claude-haiku-4-5-20251001","displayName":"Haiku 4.5","description":"Fastest for quick answers"},{"value":"claude-sonnet-5","resolvedModel":"claude-sonnet-5","displayName":"Sonnet 5","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-5","resolvedModel":"claude-opus-5","displayName":"Opus 5","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-fable-5","resolvedModel":"claude-fable-5","displayName":"Fable 5","description":"Most capable for your hardest and longest-running tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-8","resolvedModel":"claude-opus-4-8","displayName":"Opus 4.8","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-opus-4-7","resolvedModel":"claude-opus-4-7","displayName":"Opus 4.7","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-6","resolvedModel":"claude-opus-4-6","displayName":"Opus 4.6","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-sonnet-4-6","resolvedModel":"claude-sonnet-4-6","displayName":"Sonnet 4.6","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true}],"account":{"email":"[redacted]","organization":"[redacted]'s Organization","subscriptionType":"Claude Max","apiProvider":"firstParty"},"pid":99041,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} -{"dir":"send","msg":{"message":{"content":"What was the codeword? Reply with just the codeword.","role":"user"},"parent_tool_use_id":null,"session_id":"8d41cb35-d2d6-4384-a660-f3269b91d3fa","type":"user"}} -{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestResume329762661/001","session_id":"8d41cb35-d2d6-4384-a660-f3269b91d3fa","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","LSP","Monitor","NotebookEdit","PushNotification","Read","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"pending","source":"claudeai"},{"name":"claude.ai Heliosian","status":"pending","source":"claudeai"},{"name":"claude.ai Fastmail","status":"pending","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"a204c748-dc92-43a1-91d2-8c04fa4e55d8","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestResume329762661-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestResume329762661-001/8d41cb35-d2d6-4384-a660-f3269b91d3fa/scratchpad","messaging_socket_path":"/tmp/cc-socks/99041.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"8d41cb35-d2d6-4384-a660-f3269b91d3fa","uuid":"67920b18-eeaf-487d-a245-8af0fd3f8af3"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3MbEw2gyH73f6h7CkRh","type":"message","role":"assistant","content":[{"type":"text","text":"AZURE-17"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":7016,"cache_read_input_tokens":30628,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":7016},"output_tokens":8,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":{"cache_miss_reason":{"type":"messages_changed","cache_missed_input_tokens":13150}},"context_management":null},"parent_tool_use_id":null,"session_id":"8d41cb35-d2d6-4384-a660-f3269b91d3fa","uuid":"1ec5bc63-058f-4472-b247-18c19cab9e67","timestamp":"2026-10-15T04:01:06.986Z","request_id":"req_011Cg3MbEgA9kCbtrnAGZ65v"}} -{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.01,"resetsAt":1792054200},"seven_day":{"utilization":0.34,"resetsAt":1792270800}}},"uuid":"9ce1779b-6b8b-482c-89f2-397a0abe7a15","session_id":"8d41cb35-d2d6-4384-a660-f3269b91d3fa"}} -{"dir":"recv","msg":{"duration_api_ms":4207,"stop_reason":"end_turn","session_id":"8d41cb35-d2d6-4384-a660-f3269b91d3fa","total_cost_usd":0.0945408,"usage":{"input_tokens":2,"cache_creation_input_tokens":7016,"cache_read_input_tokens":30628,"output_tokens":8,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":7016,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":8,"cache_read_input_tokens":30628,"cache_creation_input_tokens":7016,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":7016},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1188,"outputTokens":21,"thinkingTokens":0,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.00012930000000000003,"contextWindow":1000000,"maxOutputTokens":128000},"claude-sonnet-5-5":{"inputTokens":4,"outputTokens":12,"thinkingTokens":0,"cacheReadInputTokens":52995,"cacheCreationInputTokens":22246,"webSearchRequests":0,"costUSD":0.0944115,"contextWindow":1000000,"maxOutputTokens":128000,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":1,"subtype":"success","api_error_status":null,"result":"AZURE-17","ttft_ms":1913,"type":"result","duration_ms":1931,"uuid":"08d749fd-b929-42dd-a5f3-fa114688fbeb","ttft_stream_ms":1907,"time_to_request_ms":33,"first_content_frame_ms":1908,"queued_turn_count":0,"result_index":0}} +{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_bf45df653f7069d4","type":"control_request"}} +{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_bf45df653f7069d4","response":{"commands":[{"name":"deep-research","description":"Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. (dynamic workflow)","argumentHint":"","builtin":true},{"name":"design","description":"Make a new Design artifact from a brief","argumentHint":"[what to design]","builtin":true},{"name":"slides","description":"Make a new Slides deck artifact from a brief","argumentHint":"[what the deck is about]","builtin":true},{"name":"design-sync","description":"Push a React design system to claude.ai/design. This runs a converter that bundles the real component code (from Storybook or a bare package) and uploads it. Use when the user runs /design-sync or says \"sync my design system to Claude Design\".","argumentHint":"[\u003cproject hint, e.g. \"Acme DS\"\u003e]","builtin":true},{"name":"dataviz","description":"Use this skill whenever you are about to create ANY chart, graph, plot, dashboard, or data visualization, in ANY output medium — an HTML or React artifact, inline SVG, plotting code in any library (matplotlib, plotly, d3, Recharts, …), an image/PNG you will render and upload, or a chart shared into Slack. Read it BEFORE writing the first line of chart code, choosing chart colors, building a stat tile / meter / KPI row, or laying out a dashboard. When the destination is a first-party document connector (host-designated, never self-described) that renders live charts, hand it the rows (inline, or as an uploaded data file the chart cites) rather than a rendered PNG/SVG — a picture of a chart loses hover, data inspection and per-value comments. Produces visualizations that read as one system — elegant, accessible, consistent in light and dark — using a brand-neutral placeholder palette you swap for your own. Teaches a design-system-agnostic method: a form heuristic, a color formula with a runnable validator, mark specs, and interaction rules. A validated default palette is documented in `references/palette.md` — swap that file's values for your brand's. Triggers on: \"chart\", \"graph\", \"plot\", \"data viz\", \"visualization\", \"dashboard\", \"analytics\", \"visualize data\", \"categorical colors\", \"sequential / diverging palette\", \"stat tile\", \"sparkline\", \"heatmap\", \"legend\", \"axis\", \"tooltip\", \"chart colors\", \"color by series\".","argumentHint":"","builtin":true},{"name":"artifact-diagramming","description":"Diagramming know-how for Artifacts - when a picture earns its place, how to draw one that shows the real mechanism, and the inline-SVG mechanics that keep it legible in both themes.","argumentHint":"","builtin":true},{"name":"artifact-capabilities","description":"Runtime capabilities a published Artifact page can be granted — behavior static HTML cannot provide on its own, such as the page reading live or connected data, remembering what people do on it (a poll, a sign-up sheet, a checklist, a document edited in place — it saves new versions of itself), keeping state shared across viewers, knowing who is viewing, asking Claude a question of its own, storing files people add, handing the viewer a file to save, or using the viewer's camera, microphone, location, screen or device motion. Serves this user's live capability roster and the typed call definitions. Load it whenever any such runtime behavior would make an artifact more useful, before writing the page.","argumentHint":"","builtin":true},{"name":"update-config","description":"Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme/model, suggest the /config command.","argumentHint":"","builtin":true},{"name":"verify","description":"Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.","argumentHint":"","builtin":true},{"name":"debug","description":"Enable debug logging for this session and help diagnose issues","argumentHint":"[issue description]","builtin":true},{"name":"code-review","description":"Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep multi-agent review in the cloud); with no level given, it reuses the level you typed last. Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review. Pass --max-findings \u003cn\u003e to report up to n findings, or --max-findings all for every finding. The choice stays until you pass --max-findings default. For ultra on a GitHub.com PR target, --post asks to post the finished review’s findings to the PR as a single comment from the user’s GitHub account (not a review; the launch dialog still confirms in interactive sessions, while non-interactive mode posts on the flag alone) and --no-post hides that option.","argumentHint":"[low|medium|high|xhigh|max|ultra] [--fix] [--comment] [\u003cpr#\u003e|\u003cbranch\u003e|\u003cpath\u003e] [--max-findings \u003cn\u003e|all]","aliases":["review"],"builtin":true},{"name":"simplify","description":"Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.","argumentHint":"[\u003ctarget\u003e]","builtin":true},{"name":"batch","description":"Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.","argumentHint":"\u003cinstruction\u003e","builtin":true},{"name":"fewer-permission-prompts","description":"Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.","argumentHint":"","builtin":true},{"name":"doctor","description":"Health-check the user's Claude Code setup and fix issues: diagnose installation health — what the `claude doctor` terminal diagnostics cover — from local data (duplicate or leftover installs, PATH, unparseable settings files, broken or colliding agent definitions, skills whose frontmatter fails to parse); find unused skills, MCP servers, and plugins versus their context cost and disable dead weight; deduplicate local CLAUDE.md files against checked-in ones; trim checked-in CLAUDE.md files by cutting content a session could derive from the codebase (directory layouts, tech-stack lists, architecture overviews) while keeping gotchas, rationale, and non-standard conventions; migrate always-loaded CLAUDE.md guidance into lazy skills and nested CLAUDE.md files; flag slow hooks and context-heavy extensions; check the installed version is current; make auto mode the default permission mode; and pre-approve frequently denied read-only commands. Use when the user asks for a doctor run, checkup, audit, tune-up, or cleanup of their Claude Code setup or configuration.","argumentHint":"[prompt-audit [\u003cpath\u003e]]","aliases":["checkup"],"builtin":true},{"name":"loop","description":"Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.","argumentHint":"[interval] [prompt]","aliases":["proactive"],"builtin":true},{"name":"schedule","description":"Create, update, list, or run scheduled cloud agents (routines) that execute on a cron schedule.","argumentHint":"","aliases":["routines"],"builtin":true},{"name":"claude-api","description":"Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).","argumentHint":"","builtin":true},{"name":"workflow-authoring","description":"Reference for writing a Workflow tool script (script API and gotchas, resume, quality patterns, worked examples). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.","argumentHint":"","builtin":true},{"name":"run","description":"Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).","argumentHint":"","builtin":true},{"name":"run-skill-generator","description":"Author or improve the run-\u003cunit\u003e skill - a per-project skill that tells agents how to build, launch, and drive this project's app. Use when the user asks to set up the project, get it running, write run instructions, or verify build/run steps work from a clean environment.","argumentHint":"","builtin":true},{"name":"plugin-authoring","description":"Make a mod: a change to Claude's own interface or behaviour, such as a live pane or panel, a band above the prompt, a status line, a toast, a slash command, or a hook on tool calls or prompts. Use to make, change or debug a mod or its hooks module.","argumentHint":"","builtin":true},{"name":"advisor","description":"Let Claude consult a stronger model at key moments","argumentHint":"[fable|opus|sonnet|off]","builtin":true},{"name":"agents","description":"(removed) Ask Claude to create/manage subagents, or edit .claude/agents/","argumentHint":"","builtin":true},{"name":"auto-mode-setup","description":"Teach auto mode about your environment, plus optional rule tweaks","argumentHint":"[--request-id \u003cuuid\u003e] (--wizard posture=… scope=… depth=… --propose | --expect-sha256 \u003c64-hex\u003e --apply-file \u003cpath\u003e)","builtin":true},{"name":"autocompact","description":"Configure the auto-compact window size","argumentHint":"[auto|\u003ctokens\u003e]","builtin":true},{"name":"clear","description":"Start a new session with empty context; previous session stays on disk (resumable with /resume)","argumentHint":"[name]","aliases":["reset","new"],"builtin":true},{"name":"color","description":"Set the prompt bar color for this session","argumentHint":"[red|blue|green|yellow|purple|orange|pink|cyan|default]","builtin":true},{"name":"compact","description":"Free up context by summarizing the conversation so far","argumentHint":"\u003coptional custom summarization instructions\u003e","builtin":true},{"name":"config","description":"Set a setting by key","argumentHint":"key=value","aliases":["settings"],"builtin":true},{"name":"output-style","description":"List output styles or switch to one","argumentHint":"[style]","builtin":true},{"name":"context","description":"Show current context usage","argumentHint":"","builtin":true},{"name":"effort","description":"Set effort level for model usage","argumentHint":"\u003clow|medium|high|xhigh|max|auto|ultracode [on|off]\u003e","builtin":true},{"name":"fast","description":"Toggle fast mode (Opus 5.5)","argumentHint":"[on|off]","builtin":true},{"name":"focus","description":"Toggle focus view: just your prompt, summary, and response","argumentHint":"[on|off]","builtin":true},{"name":"heapdump","description":"Dump the JS heap to the Desktop; on Linux with no Desktop folder, the home directory","argumentHint":"","builtin":true},{"name":"init","description":"Initialize a new CLAUDE.md file with codebase documentation","argumentHint":"","builtin":true},{"name":"mcp","description":"Manage MCP servers","argumentHint":"[reconnect|enable|disable [\u003cserver\u003e|all]]","builtin":true},{"name":"import","description":"Import config from another AI coding agent","argumentHint":"","builtin":true},{"name":"model","description":"Set the AI model for Claude Code","argumentHint":"\u003cmodel\u003e","builtin":true},{"name":"__remote-workflow","description":"Run the workflow script delivered in this session environment (server-launched sessions only)","argumentHint":"","builtin":true},{"name":"workflow-launch-exec","description":"Execute a server-launched workflow handoff (workflow_launch event sessions only)","argumentHint":"","builtin":true},{"name":"reload-plugins","description":"Activate pending plugin changes in the current session","argumentHint":"[--force]","builtin":true},{"name":"reload-skills","description":"Pick up skills added or changed on disk during this session","argumentHint":"","builtin":true},{"name":"rename","description":"Rename the current conversation","argumentHint":"[name]","aliases":["name"],"builtin":true},{"name":"ultrareview","description":"Start a cloud agent that finds and verifies bugs in your branch (~15-25 min, $5-$25 USD) · Runs in a cloud session. See https://code.claude.com/docs/en/claude-code-on-the-web","argumentHint":"","builtin":true},{"name":"security-review","description":"Complete a security review of the pending changes on the current branch","argumentHint":"","builtin":true},{"name":"usage-credits","description":"Configure usage credits or request them from your admin when you hit a limit","argumentHint":"","builtin":true},{"name":"extra-usage","description":"Renamed to /usage-credits","argumentHint":"","builtin":true},{"name":"usage","description":"Show session cost, plan usage, and what's contributing to your limits","argumentHint":"","aliases":["cost","stats"],"builtin":true},{"name":"insights","description":"Generate a report analyzing your Claude Code sessions","argumentHint":"","builtin":true},{"name":"recap","description":"Generate a one-line session recap now","argumentHint":"","builtin":true},{"name":"skill-doctor","description":"Show which loaded skills are unused and costing context","argumentHint":"","builtin":true},{"name":"goal","description":"Set a goal — keep working until the condition is met","argumentHint":"","builtin":true},{"name":"design-consent","description":"Grant Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"design-revoke","description":"Revoke Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"list-agents","description":"List subagents, teammates, and other Claude sessions you can message","argumentHint":"","aliases":["peers"],"builtin":true},{"name":"team-onboarding","description":"Help teammates ramp on Claude Code with a guide from your usage","argumentHint":"","builtin":true},{"name":"docs","description":"docs (editable docs people share and comment on; the default for any document, named as a doc or not: a document, report, proposal, resume, cover letter, letter, contract, policy, form, template, worksheet, essay, handbook, guide, how-to, cheat sheet, SOP or other writing to keep, share, collaborate on, send, submit, print or sign; a doc exports to Word, PDF, Markdown or Google Docs, so needing a file to send, attach, upload, submit or print is no reason to pick Word, and a file nobody asked for is a doc, not Word; a plan, comparison, summary or notes asked in chat stays in chat; a pasted claude.ai artifact link may be a doc: check with docs tools first; Word or another file format named, tracked changes wanted, or a .docx to change or use as a template → that format's skill): making one → if no docs-connector instructions are in context, call its `guide` (topic.instructions) first; then create the doc (headings only, no body) before any search, file read or plan, even with files attached. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docs"]},{"name":"docx","description":"Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers include: any mention of Microsoft Word Documents, such as 'Word doc', 'word document', '.docx', '.dotx', 'microsoft doc'. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a deliverable as a Word or .docx file (to download, email or print), use this skill. However, if they ask for a document, page, report, memo, or notes WITHOUT naming a file format and the session offers Claude's own dedicated document or page skill or connector, use that instead, even if they will email or print it. Do NOT use for PDFs, spreadsheets, Google Docs, or coding unrelated to document generation. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docx"]},{"name":"google-workspace","description":"Read this before the first Google Drive, Docs, Sheets or Slides connector call whenever the task creates or changes a Google file. Use this skill whenever the user wants to create or change a Google Doc, Sheet or Slides file in their Google Drive. Triggers include: a request that names Google Docs, Sheets, Slides or Drive and asks to make, edit, format, copy or rename a file; a docs.google.com link with a request to change that file, even a one-line fix or suggested edits; and any follow-up change to a Google file from earlier in the chat, even \"change it\" or \"add a tab\". Includes helper scripts for document positions, cell ranges and slide layout. However, if the user asks for a doc, deck or spreadsheet without naming Google, or gives a Google file only as source material for something new, use Claude's own output type instead. Do NOT use for read-only questions about a Google file, or for Word, Excel, PowerPoint or PDF files. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:google-workspace"]},{"name":"import-memory","description":"Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:import-memory"]},{"name":"morning","description":"Render the user's morning brief as a styled HTML artifact, or set it up as a recurring weekday task. Use only when the user explicitly asks to run, see, or set up their morning brief, or if they invoke /morning by name. A question about their day, schedule, or calendar is not by itself a request for the brief; answer it directly instead. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:morning"]},{"name":"pdf","description":"Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pdf"]},{"name":"pptx","description":"Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations as PowerPoint (.pptx) files; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email, summary, or creating a different type of slide deck); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user asks for a PowerPoint or .pptx file, or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. However, when the user asks for a deck, slides, a slide deck, or a presentation without naming a file format, default to using a dedicated slide-deck artifact type or a separate slides skill if this session offers one; otherwise, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pptx"]},{"name":"skill-creator","description":"Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:skill-creator"]},{"name":"xlsx","description":"Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:xlsx"]}],"agents":[{"name":"claude","description":"Catch-all for any task that doesn't fit a more specific agent. FleetView's default when no agent name is typed."},{"name":"claude-code-guide","description":"Use this agent when the user asks questions (\"Can Claude...\", \"Does Claude...\", \"How do I...\") about: (1) Claude Code (the CLI tool) - features, hooks, slash commands, MCP servers, settings, IDE integrations, keyboard shortcuts; (2) Claude Agent SDK - building custom agents; (3) Claude API (formerly Anthropic API) - Messages API for directly passing messages to Claude, Tool Runner (`client.beta.messages.tool_runner`) for running an agentic loop over your own tools, manual tool-use loops, Managed Agents for server-hosted agents with a managed sandbox, prompt caching, and general Anthropic SDK usage; (4) Claude Tag (Claude in Slack) - what it is, setting it up for a Slack workspace, `/install-slack-app`; (5) `claude plugin eval` (writing and running plugin eval suites, its JSON/report, sandbox, CI) and the `/skill-doctor` report. **IMPORTANT:** Before spawning a new agent, check if there is already a running or recently completed claude-code-guide agent that you can continue via SendMessage.","model":"haiku"},{"name":"Explore","description":"Fast read-only search agent for locating code. Use it to find files by pattern (eg. \"src/components/**/*.tsx\"), grep for symbols or keywords (eg. \"API endpoints\"), or answer \"where is X defined / which files reference Y.\" Do NOT use it for code review, design-doc auditing, cross-file consistency checks, or open-ended analysis — it reads excerpts rather than whole files and will miss content past its read window. When calling, specify search breadth: \"quick\" for a single targeted lookup, \"medium\" for moderate exploration, or \"very thorough\" to search across multiple locations and naming conventions.","model":"inherit"},{"name":"general-purpose","description":"General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you."},{"name":"Plan","description":"Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs.","model":"inherit"},{"name":"statusline-setup","description":"Use this agent to configure the user's Claude Code status line setting.","model":"sonnet"}],"output_style":"default","available_output_styles":["default","Proactive","Concise","Explanatory","Learning"],"user_output_styles_dir":"/Users/flamingcow/.claude/output-styles","models":[{"value":"default","resolvedModel":"claude-opus-5-5","displayName":"Default (recommended)","description":"Opus 5.5 · Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"opus","resolvedModel":"claude-opus-5-5","displayName":"Opus 5.5","description":"For complex work and everyday tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"fable","resolvedModel":"claude-fable-5-1","displayName":"Fable 5.1","description":"For your toughest challenges","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"sonnet","resolvedModel":"claude-sonnet-5-5","displayName":"Sonnet 5.5","description":"Most efficient for simpler tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"haiku","resolvedModel":"claude-haiku-5-5","displayName":"Haiku 5.5","description":"Fastest for quick answers","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-haiku-4-5-20251001","resolvedModel":"claude-haiku-4-5-20251001","displayName":"Haiku 4.5","description":"Fastest for quick answers"},{"value":"claude-sonnet-5","resolvedModel":"claude-sonnet-5","displayName":"Sonnet 5","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-5","resolvedModel":"claude-opus-5","displayName":"Opus 5","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-fable-5","resolvedModel":"claude-fable-5","displayName":"Fable 5","description":"Most capable for your hardest and longest-running tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-8","resolvedModel":"claude-opus-4-8","displayName":"Opus 4.8","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-opus-4-7","resolvedModel":"claude-opus-4-7","displayName":"Opus 4.7","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-6","resolvedModel":"claude-opus-4-6","displayName":"Opus 4.6","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-sonnet-4-6","resolvedModel":"claude-sonnet-4-6","displayName":"Sonnet 4.6","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true}],"account":{"email":"[redacted]","organization":"[redacted]'s Organization","subscriptionType":"Claude Max","apiProvider":"firstParty"},"pid":2571,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} +{"dir":"send","msg":{"message":{"content":"What was the codeword? Reply with just the codeword.","role":"user"},"parent_tool_use_id":null,"session_id":"f2415e0e-38dd-4049-bb5f-4405d4db75da","type":"user"}} +{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestResume1583807402/001","session_id":"f2415e0e-38dd-4049-bb5f-4405d4db75da","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","LSP","Monitor","NotebookEdit","PushNotification","Read","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"pending","source":"claudeai"},{"name":"claude.ai Heliosian","status":"pending","source":"claudeai"},{"name":"claude.ai Fastmail","status":"pending","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"6234a3fe-2392-447a-afed-4bf90ae6a5df","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestResume1583807402-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestResume1583807402-001/f2415e0e-38dd-4049-bb5f-4405d4db75da/scratchpad","messaging_socket_path":"/tmp/cc-socks/2571.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"f2415e0e-38dd-4049-bb5f-4405d4db75da","uuid":"0fe7bc72-61d8-45ec-ab74-50d8dc5da5fe"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3MzA9vwndpWWu8siq9Q","type":"message","role":"assistant","content":[{"type":"text","text":"AZURE-17"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":7017,"cache_read_input_tokens":30631,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":7017},"output_tokens":8,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":{"cache_miss_reason":{"type":"messages_changed","cache_missed_input_tokens":13150}},"context_management":null},"parent_tool_use_id":null,"session_id":"f2415e0e-38dd-4049-bb5f-4405d4db75da","uuid":"e8cf317b-8be9-4d62-9575-08ed3433a922","timestamp":"2026-10-15T04:06:17.482Z","request_id":"req_011Cg3Mz9unx6VfURef7E1Uf"}} +{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.01,"resetsAt":1792054200},"seven_day":{"utilization":0.34,"resetsAt":1792270800}}},"uuid":"2dc49c10-97e2-4c55-bdbb-3ccaca34ce4a","session_id":"f2415e0e-38dd-4049-bb5f-4405d4db75da"}} +{"dir":"recv","msg":{"duration_api_ms":3586,"stop_reason":"end_turn","session_id":"f2415e0e-38dd-4049-bb5f-4405d4db75da","total_cost_usd":0.0945611,"usage":{"input_tokens":2,"cache_creation_input_tokens":7017,"cache_read_input_tokens":30631,"output_tokens":8,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":7017,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":8,"cache_read_input_tokens":30631,"cache_creation_input_tokens":7017,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":7017},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1188,"outputTokens":21,"thinkingTokens":0,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.00012930000000000003,"contextWindow":1000000,"maxOutputTokens":128000},"claude-sonnet-5-5":{"inputTokens":4,"outputTokens":12,"thinkingTokens":0,"cacheReadInputTokens":52998,"cacheCreationInputTokens":22251,"webSearchRequests":0,"costUSD":0.0944318,"contextWindow":1000000,"maxOutputTokens":128000,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":1,"subtype":"success","api_error_status":null,"result":"AZURE-17","ttft_ms":1515,"type":"result","duration_ms":1533,"uuid":"9935d142-285d-4eb7-bc54-22f374d743b2","ttft_stream_ms":1502,"time_to_request_ms":33,"first_content_frame_ms":1502,"queued_turn_count":0,"result_index":0}} diff --git a/internal/claude/testdata/transcripts/TestStopHookBlocks.jsonl b/internal/claude/testdata/transcripts/TestStopHookBlocks.jsonl index 9044a88..be48574 100644 --- a/internal/claude/testdata/transcripts/TestStopHookBlocks.jsonl +++ b/internal/claude/testdata/transcripts/TestStopHookBlocks.jsonl @@ -1,16 +1,16 @@ -{"dir":"send","msg":{"request":{"hooks":{"Stop":[{"hookCallbackIds":["hook_0"],"matcher":""}]},"subtype":"initialize"},"request_id":"req_02d1ad1c4ac551df","type":"control_request"}} -{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_02d1ad1c4ac551df","response":{"commands":[{"name":"deep-research","description":"Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. (dynamic workflow)","argumentHint":"","builtin":true},{"name":"design","description":"Make a new Design artifact from a brief","argumentHint":"[what to design]","builtin":true},{"name":"slides","description":"Make a new Slides deck artifact from a brief","argumentHint":"[what the deck is about]","builtin":true},{"name":"design-sync","description":"Push a React design system to claude.ai/design. This runs a converter that bundles the real component code (from Storybook or a bare package) and uploads it. Use when the user runs /design-sync or says \"sync my design system to Claude Design\".","argumentHint":"[\u003cproject hint, e.g. \"Acme DS\"\u003e]","builtin":true},{"name":"dataviz","description":"Use this skill whenever you are about to create ANY chart, graph, plot, dashboard, or data visualization, in ANY output medium — an HTML or React artifact, inline SVG, plotting code in any library (matplotlib, plotly, d3, Recharts, …), an image/PNG you will render and upload, or a chart shared into Slack. Read it BEFORE writing the first line of chart code, choosing chart colors, building a stat tile / meter / KPI row, or laying out a dashboard. When the destination is a first-party document connector (host-designated, never self-described) that renders live charts, hand it the rows (inline, or as an uploaded data file the chart cites) rather than a rendered PNG/SVG — a picture of a chart loses hover, data inspection and per-value comments. Produces visualizations that read as one system — elegant, accessible, consistent in light and dark — using a brand-neutral placeholder palette you swap for your own. Teaches a design-system-agnostic method: a form heuristic, a color formula with a runnable validator, mark specs, and interaction rules. A validated default palette is documented in `references/palette.md` — swap that file's values for your brand's. Triggers on: \"chart\", \"graph\", \"plot\", \"data viz\", \"visualization\", \"dashboard\", \"analytics\", \"visualize data\", \"categorical colors\", \"sequential / diverging palette\", \"stat tile\", \"sparkline\", \"heatmap\", \"legend\", \"axis\", \"tooltip\", \"chart colors\", \"color by series\".","argumentHint":"","builtin":true},{"name":"artifact-diagramming","description":"Diagramming know-how for Artifacts - when a picture earns its place, how to draw one that shows the real mechanism, and the inline-SVG mechanics that keep it legible in both themes.","argumentHint":"","builtin":true},{"name":"artifact-capabilities","description":"Runtime capabilities a published Artifact page can be granted — behavior static HTML cannot provide on its own, such as the page reading live or connected data, remembering what people do on it (a poll, a sign-up sheet, a checklist, a document edited in place — it saves new versions of itself), keeping state shared across viewers, knowing who is viewing, asking Claude a question of its own, storing files people add, handing the viewer a file to save, or using the viewer's camera, microphone, location, screen or device motion. Serves this user's live capability roster and the typed call definitions. Load it whenever any such runtime behavior would make an artifact more useful, before writing the page.","argumentHint":"","builtin":true},{"name":"update-config","description":"Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme/model, suggest the /config command.","argumentHint":"","builtin":true},{"name":"verify","description":"Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.","argumentHint":"","builtin":true},{"name":"debug","description":"Enable debug logging for this session and help diagnose issues","argumentHint":"[issue description]","builtin":true},{"name":"code-review","description":"Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep multi-agent review in the cloud); with no level given, it reuses the level you typed last. Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review. Pass --max-findings \u003cn\u003e to report up to n findings, or --max-findings all for every finding. The choice stays until you pass --max-findings default. For ultra on a GitHub.com PR target, --post asks to post the finished review’s findings to the PR as a single comment from the user’s GitHub account (not a review; the launch dialog still confirms in interactive sessions, while non-interactive mode posts on the flag alone) and --no-post hides that option.","argumentHint":"[low|medium|high|xhigh|max|ultra] [--fix] [--comment] [\u003cpr#\u003e|\u003cbranch\u003e|\u003cpath\u003e] [--max-findings \u003cn\u003e|all]","aliases":["review"],"builtin":true},{"name":"simplify","description":"Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.","argumentHint":"[\u003ctarget\u003e]","builtin":true},{"name":"batch","description":"Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.","argumentHint":"\u003cinstruction\u003e","builtin":true},{"name":"fewer-permission-prompts","description":"Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.","argumentHint":"","builtin":true},{"name":"doctor","description":"Health-check the user's Claude Code setup and fix issues: diagnose installation health — what the `claude doctor` terminal diagnostics cover — from local data (duplicate or leftover installs, PATH, unparseable settings files, broken or colliding agent definitions, skills whose frontmatter fails to parse); find unused skills, MCP servers, and plugins versus their context cost and disable dead weight; deduplicate local CLAUDE.md files against checked-in ones; trim checked-in CLAUDE.md files by cutting content a session could derive from the codebase (directory layouts, tech-stack lists, architecture overviews) while keeping gotchas, rationale, and non-standard conventions; migrate always-loaded CLAUDE.md guidance into lazy skills and nested CLAUDE.md files; flag slow hooks and context-heavy extensions; check the installed version is current; make auto mode the default permission mode; and pre-approve frequently denied read-only commands. Use when the user asks for a doctor run, checkup, audit, tune-up, or cleanup of their Claude Code setup or configuration.","argumentHint":"[prompt-audit [\u003cpath\u003e]]","aliases":["checkup"],"builtin":true},{"name":"loop","description":"Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.","argumentHint":"[interval] [prompt]","aliases":["proactive"],"builtin":true},{"name":"schedule","description":"Create, update, list, or run scheduled cloud agents (routines) that execute on a cron schedule.","argumentHint":"","aliases":["routines"],"builtin":true},{"name":"claude-api","description":"Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).","argumentHint":"","builtin":true},{"name":"workflow-authoring","description":"Reference for writing a Workflow tool script (script API and gotchas, resume, quality patterns, worked examples). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.","argumentHint":"","builtin":true},{"name":"run","description":"Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).","argumentHint":"","builtin":true},{"name":"run-skill-generator","description":"Author or improve the run-\u003cunit\u003e skill - a per-project skill that tells agents how to build, launch, and drive this project's app. Use when the user asks to set up the project, get it running, write run instructions, or verify build/run steps work from a clean environment.","argumentHint":"","builtin":true},{"name":"plugin-authoring","description":"Make a mod: a change to Claude's own interface or behaviour, such as a live pane or panel, a band above the prompt, a status line, a toast, a slash command, or a hook on tool calls or prompts. Use to make, change or debug a mod or its hooks module.","argumentHint":"","builtin":true},{"name":"advisor","description":"Let Claude consult a stronger model at key moments","argumentHint":"[fable|opus|sonnet|off]","builtin":true},{"name":"agents","description":"(removed) Ask Claude to create/manage subagents, or edit .claude/agents/","argumentHint":"","builtin":true},{"name":"auto-mode-setup","description":"Teach auto mode about your environment, plus optional rule tweaks","argumentHint":"[--request-id \u003cuuid\u003e] (--wizard posture=… scope=… depth=… --propose | --expect-sha256 \u003c64-hex\u003e --apply-file \u003cpath\u003e)","builtin":true},{"name":"autocompact","description":"Configure the auto-compact window size","argumentHint":"[auto|\u003ctokens\u003e]","builtin":true},{"name":"clear","description":"Start a new session with empty context; previous session stays on disk (resumable with /resume)","argumentHint":"[name]","aliases":["reset","new"],"builtin":true},{"name":"color","description":"Set the prompt bar color for this session","argumentHint":"[red|blue|green|yellow|purple|orange|pink|cyan|default]","builtin":true},{"name":"compact","description":"Free up context by summarizing the conversation so far","argumentHint":"\u003coptional custom summarization instructions\u003e","builtin":true},{"name":"config","description":"Set a setting by key","argumentHint":"key=value","aliases":["settings"],"builtin":true},{"name":"output-style","description":"List output styles or switch to one","argumentHint":"[style]","builtin":true},{"name":"context","description":"Show current context usage","argumentHint":"","builtin":true},{"name":"effort","description":"Set effort level for model usage","argumentHint":"\u003clow|medium|high|xhigh|max|auto|ultracode [on|off]\u003e","builtin":true},{"name":"fast","description":"Toggle fast mode (Opus 5.5)","argumentHint":"[on|off]","builtin":true},{"name":"focus","description":"Toggle focus view: just your prompt, summary, and response","argumentHint":"[on|off]","builtin":true},{"name":"heapdump","description":"Dump the JS heap to the Desktop; on Linux with no Desktop folder, the home directory","argumentHint":"","builtin":true},{"name":"init","description":"Initialize a new CLAUDE.md file with codebase documentation","argumentHint":"","builtin":true},{"name":"mcp","description":"Manage MCP servers","argumentHint":"[reconnect|enable|disable [\u003cserver\u003e|all]]","builtin":true},{"name":"import","description":"Import config from another AI coding agent","argumentHint":"","builtin":true},{"name":"model","description":"Set the AI model for Claude Code","argumentHint":"\u003cmodel\u003e","builtin":true},{"name":"__remote-workflow","description":"Run the workflow script delivered in this session environment (server-launched sessions only)","argumentHint":"","builtin":true},{"name":"workflow-launch-exec","description":"Execute a server-launched workflow handoff (workflow_launch event sessions only)","argumentHint":"","builtin":true},{"name":"reload-plugins","description":"Activate pending plugin changes in the current session","argumentHint":"[--force]","builtin":true},{"name":"reload-skills","description":"Pick up skills added or changed on disk during this session","argumentHint":"","builtin":true},{"name":"rename","description":"Rename the current conversation","argumentHint":"[name]","aliases":["name"],"builtin":true},{"name":"ultrareview","description":"Start a cloud agent that finds and verifies bugs in your branch (~15-25 min, $5-$25 USD) · Runs in a cloud session. See https://code.claude.com/docs/en/claude-code-on-the-web","argumentHint":"","builtin":true},{"name":"security-review","description":"Complete a security review of the pending changes on the current branch","argumentHint":"","builtin":true},{"name":"usage-credits","description":"Configure usage credits or request them from your admin when you hit a limit","argumentHint":"","builtin":true},{"name":"extra-usage","description":"Renamed to /usage-credits","argumentHint":"","builtin":true},{"name":"usage","description":"Show session cost, plan usage, and what's contributing to your limits","argumentHint":"","aliases":["cost","stats"],"builtin":true},{"name":"insights","description":"Generate a report analyzing your Claude Code sessions","argumentHint":"","builtin":true},{"name":"recap","description":"Generate a one-line session recap now","argumentHint":"","builtin":true},{"name":"skill-doctor","description":"Show which loaded skills are unused and costing context","argumentHint":"","builtin":true},{"name":"goal","description":"Set a goal — keep working until the condition is met","argumentHint":"","builtin":true},{"name":"design-consent","description":"Grant Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"design-revoke","description":"Revoke Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"list-agents","description":"List subagents, teammates, and other Claude sessions you can message","argumentHint":"","aliases":["peers"],"builtin":true},{"name":"team-onboarding","description":"Help teammates ramp on Claude Code with a guide from your usage","argumentHint":"","builtin":true},{"name":"docs","description":"docs (editable docs people share and comment on; the default for any document, named as a doc or not: a document, report, proposal, resume, cover letter, letter, contract, policy, form, template, worksheet, essay, handbook, guide, how-to, cheat sheet, SOP or other writing to keep, share, collaborate on, send, submit, print or sign; a doc exports to Word, PDF, Markdown or Google Docs, so needing a file to send, attach, upload, submit or print is no reason to pick Word, and a file nobody asked for is a doc, not Word; a plan, comparison, summary or notes asked in chat stays in chat; a pasted claude.ai artifact link may be a doc: check with docs tools first; Word or another file format named, tracked changes wanted, or a .docx to change or use as a template → that format's skill): making one → if no docs-connector instructions are in context, call its `guide` (topic.instructions) first; then create the doc (headings only, no body) before any search, file read or plan, even with files attached. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docs"]},{"name":"docx","description":"Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers include: any mention of Microsoft Word Documents, such as 'Word doc', 'word document', '.docx', '.dotx', 'microsoft doc'. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a deliverable as a Word or .docx file (to download, email or print), use this skill. However, if they ask for a document, page, report, memo, or notes WITHOUT naming a file format and the session offers Claude's own dedicated document or page skill or connector, use that instead, even if they will email or print it. Do NOT use for PDFs, spreadsheets, Google Docs, or coding unrelated to document generation. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docx"]},{"name":"google-workspace","description":"Read this before the first Google Drive, Docs, Sheets or Slides connector call whenever the task creates or changes a Google file. Use this skill whenever the user wants to create or change a Google Doc, Sheet or Slides file in their Google Drive. Triggers include: a request that names Google Docs, Sheets, Slides or Drive and asks to make, edit, format, copy or rename a file; a docs.google.com link with a request to change that file, even a one-line fix or suggested edits; and any follow-up change to a Google file from earlier in the chat, even \"change it\" or \"add a tab\". Includes helper scripts for document positions, cell ranges and slide layout. However, if the user asks for a doc, deck or spreadsheet without naming Google, or gives a Google file only as source material for something new, use Claude's own output type instead. Do NOT use for read-only questions about a Google file, or for Word, Excel, PowerPoint or PDF files. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:google-workspace"]},{"name":"import-memory","description":"Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:import-memory"]},{"name":"morning","description":"Render the user's morning brief as a styled HTML artifact, or set it up as a recurring weekday task. Use only when the user explicitly asks to run, see, or set up their morning brief, or if they invoke /morning by name. A question about their day, schedule, or calendar is not by itself a request for the brief; answer it directly instead. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:morning"]},{"name":"pdf","description":"Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pdf"]},{"name":"pptx","description":"Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations as PowerPoint (.pptx) files; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email, summary, or creating a different type of slide deck); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user asks for a PowerPoint or .pptx file, or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. However, when the user asks for a deck, slides, a slide deck, or a presentation without naming a file format, default to using a dedicated slide-deck artifact type or a separate slides skill if this session offers one; otherwise, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pptx"]},{"name":"skill-creator","description":"Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:skill-creator"]},{"name":"xlsx","description":"Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:xlsx"]}],"agents":[{"name":"claude","description":"Catch-all for any task that doesn't fit a more specific agent. FleetView's default when no agent name is typed."},{"name":"claude-code-guide","description":"Use this agent when the user asks questions (\"Can Claude...\", \"Does Claude...\", \"How do I...\") about: (1) Claude Code (the CLI tool) - features, hooks, slash commands, MCP servers, settings, IDE integrations, keyboard shortcuts; (2) Claude Agent SDK - building custom agents; (3) Claude API (formerly Anthropic API) - Messages API for directly passing messages to Claude, Tool Runner (`client.beta.messages.tool_runner`) for running an agentic loop over your own tools, manual tool-use loops, Managed Agents for server-hosted agents with a managed sandbox, prompt caching, and general Anthropic SDK usage; (4) Claude Tag (Claude in Slack) - what it is, setting it up for a Slack workspace, `/install-slack-app`; (5) `claude plugin eval` (writing and running plugin eval suites, its JSON/report, sandbox, CI) and the `/skill-doctor` report. **IMPORTANT:** Before spawning a new agent, check if there is already a running or recently completed claude-code-guide agent that you can continue via SendMessage.","model":"haiku"},{"name":"Explore","description":"Fast read-only search agent for locating code. Use it to find files by pattern (eg. \"src/components/**/*.tsx\"), grep for symbols or keywords (eg. \"API endpoints\"), or answer \"where is X defined / which files reference Y.\" Do NOT use it for code review, design-doc auditing, cross-file consistency checks, or open-ended analysis — it reads excerpts rather than whole files and will miss content past its read window. When calling, specify search breadth: \"quick\" for a single targeted lookup, \"medium\" for moderate exploration, or \"very thorough\" to search across multiple locations and naming conventions.","model":"inherit"},{"name":"general-purpose","description":"General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you."},{"name":"Plan","description":"Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs.","model":"inherit"},{"name":"statusline-setup","description":"Use this agent to configure the user's Claude Code status line setting.","model":"sonnet"}],"output_style":"default","available_output_styles":["default","Proactive","Concise","Explanatory","Learning"],"user_output_styles_dir":"/Users/flamingcow/.claude/output-styles","models":[{"value":"default","resolvedModel":"claude-opus-5-5","displayName":"Default (recommended)","description":"Opus 5.5 · Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"opus","resolvedModel":"claude-opus-5-5","displayName":"Opus 5.5","description":"For complex work and everyday tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"fable","resolvedModel":"claude-fable-5-1","displayName":"Fable 5.1","description":"For your toughest challenges","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"sonnet","resolvedModel":"claude-sonnet-5-5","displayName":"Sonnet 5.5","description":"Most efficient for simpler tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"haiku","resolvedModel":"claude-haiku-5-5","displayName":"Haiku 5.5","description":"Fastest for quick answers","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-haiku-4-5-20251001","resolvedModel":"claude-haiku-4-5-20251001","displayName":"Haiku 4.5","description":"Fastest for quick answers"},{"value":"claude-sonnet-5","resolvedModel":"claude-sonnet-5","displayName":"Sonnet 5","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-5","resolvedModel":"claude-opus-5","displayName":"Opus 5","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-fable-5","resolvedModel":"claude-fable-5","displayName":"Fable 5","description":"Most capable for your hardest and longest-running tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-8","resolvedModel":"claude-opus-4-8","displayName":"Opus 4.8","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-opus-4-7","resolvedModel":"claude-opus-4-7","displayName":"Opus 4.7","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-6","resolvedModel":"claude-opus-4-6","displayName":"Opus 4.6","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-sonnet-4-6","resolvedModel":"claude-sonnet-4-6","displayName":"Sonnet 4.6","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true}],"account":{"email":"[redacted]","organization":"[redacted]'s Organization","subscriptionType":"Claude Max","apiProvider":"firstParty"},"pid":98364,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","hooks_applied":true,"feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} +{"dir":"send","msg":{"request":{"hooks":{"Stop":[{"hookCallbackIds":["hook_0"],"matcher":""}]},"subtype":"initialize"},"request_id":"req_f0d07ceccb2ddb95","type":"control_request"}} +{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_f0d07ceccb2ddb95","response":{"commands":[{"name":"deep-research","description":"Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. (dynamic workflow)","argumentHint":"","builtin":true},{"name":"design","description":"Make a new Design artifact from a brief","argumentHint":"[what to design]","builtin":true},{"name":"slides","description":"Make a new Slides deck artifact from a brief","argumentHint":"[what the deck is about]","builtin":true},{"name":"design-sync","description":"Push a React design system to claude.ai/design. This runs a converter that bundles the real component code (from Storybook or a bare package) and uploads it. Use when the user runs /design-sync or says \"sync my design system to Claude Design\".","argumentHint":"[\u003cproject hint, e.g. \"Acme DS\"\u003e]","builtin":true},{"name":"dataviz","description":"Use this skill whenever you are about to create ANY chart, graph, plot, dashboard, or data visualization, in ANY output medium — an HTML or React artifact, inline SVG, plotting code in any library (matplotlib, plotly, d3, Recharts, …), an image/PNG you will render and upload, or a chart shared into Slack. Read it BEFORE writing the first line of chart code, choosing chart colors, building a stat tile / meter / KPI row, or laying out a dashboard. When the destination is a first-party document connector (host-designated, never self-described) that renders live charts, hand it the rows (inline, or as an uploaded data file the chart cites) rather than a rendered PNG/SVG — a picture of a chart loses hover, data inspection and per-value comments. Produces visualizations that read as one system — elegant, accessible, consistent in light and dark — using a brand-neutral placeholder palette you swap for your own. Teaches a design-system-agnostic method: a form heuristic, a color formula with a runnable validator, mark specs, and interaction rules. A validated default palette is documented in `references/palette.md` — swap that file's values for your brand's. Triggers on: \"chart\", \"graph\", \"plot\", \"data viz\", \"visualization\", \"dashboard\", \"analytics\", \"visualize data\", \"categorical colors\", \"sequential / diverging palette\", \"stat tile\", \"sparkline\", \"heatmap\", \"legend\", \"axis\", \"tooltip\", \"chart colors\", \"color by series\".","argumentHint":"","builtin":true},{"name":"artifact-diagramming","description":"Diagramming know-how for Artifacts - when a picture earns its place, how to draw one that shows the real mechanism, and the inline-SVG mechanics that keep it legible in both themes.","argumentHint":"","builtin":true},{"name":"artifact-capabilities","description":"Runtime capabilities a published Artifact page can be granted — behavior static HTML cannot provide on its own, such as the page reading live or connected data, remembering what people do on it (a poll, a sign-up sheet, a checklist, a document edited in place — it saves new versions of itself), keeping state shared across viewers, knowing who is viewing, asking Claude a question of its own, storing files people add, handing the viewer a file to save, or using the viewer's camera, microphone, location, screen or device motion. Serves this user's live capability roster and the typed call definitions. Load it whenever any such runtime behavior would make an artifact more useful, before writing the page.","argumentHint":"","builtin":true},{"name":"update-config","description":"Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme/model, suggest the /config command.","argumentHint":"","builtin":true},{"name":"verify","description":"Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.","argumentHint":"","builtin":true},{"name":"debug","description":"Enable debug logging for this session and help diagnose issues","argumentHint":"[issue description]","builtin":true},{"name":"code-review","description":"Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep multi-agent review in the cloud); with no level given, it reuses the level you typed last. Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review. Pass --max-findings \u003cn\u003e to report up to n findings, or --max-findings all for every finding. The choice stays until you pass --max-findings default. For ultra on a GitHub.com PR target, --post asks to post the finished review’s findings to the PR as a single comment from the user’s GitHub account (not a review; the launch dialog still confirms in interactive sessions, while non-interactive mode posts on the flag alone) and --no-post hides that option.","argumentHint":"[low|medium|high|xhigh|max|ultra] [--fix] [--comment] [\u003cpr#\u003e|\u003cbranch\u003e|\u003cpath\u003e] [--max-findings \u003cn\u003e|all]","aliases":["review"],"builtin":true},{"name":"simplify","description":"Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.","argumentHint":"[\u003ctarget\u003e]","builtin":true},{"name":"batch","description":"Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.","argumentHint":"\u003cinstruction\u003e","builtin":true},{"name":"fewer-permission-prompts","description":"Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.","argumentHint":"","builtin":true},{"name":"doctor","description":"Health-check the user's Claude Code setup and fix issues: diagnose installation health — what the `claude doctor` terminal diagnostics cover — from local data (duplicate or leftover installs, PATH, unparseable settings files, broken or colliding agent definitions, skills whose frontmatter fails to parse); find unused skills, MCP servers, and plugins versus their context cost and disable dead weight; deduplicate local CLAUDE.md files against checked-in ones; trim checked-in CLAUDE.md files by cutting content a session could derive from the codebase (directory layouts, tech-stack lists, architecture overviews) while keeping gotchas, rationale, and non-standard conventions; migrate always-loaded CLAUDE.md guidance into lazy skills and nested CLAUDE.md files; flag slow hooks and context-heavy extensions; check the installed version is current; make auto mode the default permission mode; and pre-approve frequently denied read-only commands. Use when the user asks for a doctor run, checkup, audit, tune-up, or cleanup of their Claude Code setup or configuration.","argumentHint":"[prompt-audit [\u003cpath\u003e]]","aliases":["checkup"],"builtin":true},{"name":"loop","description":"Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.","argumentHint":"[interval] [prompt]","aliases":["proactive"],"builtin":true},{"name":"schedule","description":"Create, update, list, or run scheduled cloud agents (routines) that execute on a cron schedule.","argumentHint":"","aliases":["routines"],"builtin":true},{"name":"claude-api","description":"Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).","argumentHint":"","builtin":true},{"name":"workflow-authoring","description":"Reference for writing a Workflow tool script (script API and gotchas, resume, quality patterns, worked examples). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.","argumentHint":"","builtin":true},{"name":"run","description":"Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).","argumentHint":"","builtin":true},{"name":"run-skill-generator","description":"Author or improve the run-\u003cunit\u003e skill - a per-project skill that tells agents how to build, launch, and drive this project's app. Use when the user asks to set up the project, get it running, write run instructions, or verify build/run steps work from a clean environment.","argumentHint":"","builtin":true},{"name":"plugin-authoring","description":"Make a mod: a change to Claude's own interface or behaviour, such as a live pane or panel, a band above the prompt, a status line, a toast, a slash command, or a hook on tool calls or prompts. Use to make, change or debug a mod or its hooks module.","argumentHint":"","builtin":true},{"name":"advisor","description":"Let Claude consult a stronger model at key moments","argumentHint":"[fable|opus|sonnet|off]","builtin":true},{"name":"agents","description":"(removed) Ask Claude to create/manage subagents, or edit .claude/agents/","argumentHint":"","builtin":true},{"name":"auto-mode-setup","description":"Teach auto mode about your environment, plus optional rule tweaks","argumentHint":"[--request-id \u003cuuid\u003e] (--wizard posture=… scope=… depth=… --propose | --expect-sha256 \u003c64-hex\u003e --apply-file \u003cpath\u003e)","builtin":true},{"name":"autocompact","description":"Configure the auto-compact window size","argumentHint":"[auto|\u003ctokens\u003e]","builtin":true},{"name":"clear","description":"Start a new session with empty context; previous session stays on disk (resumable with /resume)","argumentHint":"[name]","aliases":["reset","new"],"builtin":true},{"name":"color","description":"Set the prompt bar color for this session","argumentHint":"[red|blue|green|yellow|purple|orange|pink|cyan|default]","builtin":true},{"name":"compact","description":"Free up context by summarizing the conversation so far","argumentHint":"\u003coptional custom summarization instructions\u003e","builtin":true},{"name":"config","description":"Set a setting by key","argumentHint":"key=value","aliases":["settings"],"builtin":true},{"name":"output-style","description":"List output styles or switch to one","argumentHint":"[style]","builtin":true},{"name":"context","description":"Show current context usage","argumentHint":"","builtin":true},{"name":"effort","description":"Set effort level for model usage","argumentHint":"\u003clow|medium|high|xhigh|max|auto|ultracode [on|off]\u003e","builtin":true},{"name":"fast","description":"Toggle fast mode (Opus 5.5)","argumentHint":"[on|off]","builtin":true},{"name":"focus","description":"Toggle focus view: just your prompt, summary, and response","argumentHint":"[on|off]","builtin":true},{"name":"heapdump","description":"Dump the JS heap to the Desktop; on Linux with no Desktop folder, the home directory","argumentHint":"","builtin":true},{"name":"init","description":"Initialize a new CLAUDE.md file with codebase documentation","argumentHint":"","builtin":true},{"name":"mcp","description":"Manage MCP servers","argumentHint":"[reconnect|enable|disable [\u003cserver\u003e|all]]","builtin":true},{"name":"import","description":"Import config from another AI coding agent","argumentHint":"","builtin":true},{"name":"model","description":"Set the AI model for Claude Code","argumentHint":"\u003cmodel\u003e","builtin":true},{"name":"__remote-workflow","description":"Run the workflow script delivered in this session environment (server-launched sessions only)","argumentHint":"","builtin":true},{"name":"workflow-launch-exec","description":"Execute a server-launched workflow handoff (workflow_launch event sessions only)","argumentHint":"","builtin":true},{"name":"reload-plugins","description":"Activate pending plugin changes in the current session","argumentHint":"[--force]","builtin":true},{"name":"reload-skills","description":"Pick up skills added or changed on disk during this session","argumentHint":"","builtin":true},{"name":"rename","description":"Rename the current conversation","argumentHint":"[name]","aliases":["name"],"builtin":true},{"name":"ultrareview","description":"Start a cloud agent that finds and verifies bugs in your branch (~15-25 min, $5-$25 USD) · Runs in a cloud session. See https://code.claude.com/docs/en/claude-code-on-the-web","argumentHint":"","builtin":true},{"name":"security-review","description":"Complete a security review of the pending changes on the current branch","argumentHint":"","builtin":true},{"name":"usage-credits","description":"Configure usage credits or request them from your admin when you hit a limit","argumentHint":"","builtin":true},{"name":"extra-usage","description":"Renamed to /usage-credits","argumentHint":"","builtin":true},{"name":"usage","description":"Show session cost, plan usage, and what's contributing to your limits","argumentHint":"","aliases":["cost","stats"],"builtin":true},{"name":"insights","description":"Generate a report analyzing your Claude Code sessions","argumentHint":"","builtin":true},{"name":"recap","description":"Generate a one-line session recap now","argumentHint":"","builtin":true},{"name":"skill-doctor","description":"Show which loaded skills are unused and costing context","argumentHint":"","builtin":true},{"name":"goal","description":"Set a goal — keep working until the condition is met","argumentHint":"","builtin":true},{"name":"design-consent","description":"Grant Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"design-revoke","description":"Revoke Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"list-agents","description":"List subagents, teammates, and other Claude sessions you can message","argumentHint":"","aliases":["peers"],"builtin":true},{"name":"team-onboarding","description":"Help teammates ramp on Claude Code with a guide from your usage","argumentHint":"","builtin":true},{"name":"docs","description":"docs (editable docs people share and comment on; the default for any document, named as a doc or not: a document, report, proposal, resume, cover letter, letter, contract, policy, form, template, worksheet, essay, handbook, guide, how-to, cheat sheet, SOP or other writing to keep, share, collaborate on, send, submit, print or sign; a doc exports to Word, PDF, Markdown or Google Docs, so needing a file to send, attach, upload, submit or print is no reason to pick Word, and a file nobody asked for is a doc, not Word; a plan, comparison, summary or notes asked in chat stays in chat; a pasted claude.ai artifact link may be a doc: check with docs tools first; Word or another file format named, tracked changes wanted, or a .docx to change or use as a template → that format's skill): making one → if no docs-connector instructions are in context, call its `guide` (topic.instructions) first; then create the doc (headings only, no body) before any search, file read or plan, even with files attached. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docs"]},{"name":"docx","description":"Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers include: any mention of Microsoft Word Documents, such as 'Word doc', 'word document', '.docx', '.dotx', 'microsoft doc'. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a deliverable as a Word or .docx file (to download, email or print), use this skill. However, if they ask for a document, page, report, memo, or notes WITHOUT naming a file format and the session offers Claude's own dedicated document or page skill or connector, use that instead, even if they will email or print it. Do NOT use for PDFs, spreadsheets, Google Docs, or coding unrelated to document generation. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docx"]},{"name":"google-workspace","description":"Read this before the first Google Drive, Docs, Sheets or Slides connector call whenever the task creates or changes a Google file. Use this skill whenever the user wants to create or change a Google Doc, Sheet or Slides file in their Google Drive. Triggers include: a request that names Google Docs, Sheets, Slides or Drive and asks to make, edit, format, copy or rename a file; a docs.google.com link with a request to change that file, even a one-line fix or suggested edits; and any follow-up change to a Google file from earlier in the chat, even \"change it\" or \"add a tab\". Includes helper scripts for document positions, cell ranges and slide layout. However, if the user asks for a doc, deck or spreadsheet without naming Google, or gives a Google file only as source material for something new, use Claude's own output type instead. Do NOT use for read-only questions about a Google file, or for Word, Excel, PowerPoint or PDF files. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:google-workspace"]},{"name":"import-memory","description":"Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:import-memory"]},{"name":"morning","description":"Render the user's morning brief as a styled HTML artifact, or set it up as a recurring weekday task. Use only when the user explicitly asks to run, see, or set up their morning brief, or if they invoke /morning by name. A question about their day, schedule, or calendar is not by itself a request for the brief; answer it directly instead. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:morning"]},{"name":"pdf","description":"Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pdf"]},{"name":"pptx","description":"Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations as PowerPoint (.pptx) files; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email, summary, or creating a different type of slide deck); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user asks for a PowerPoint or .pptx file, or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. However, when the user asks for a deck, slides, a slide deck, or a presentation without naming a file format, default to using a dedicated slide-deck artifact type or a separate slides skill if this session offers one; otherwise, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pptx"]},{"name":"skill-creator","description":"Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:skill-creator"]},{"name":"xlsx","description":"Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:xlsx"]}],"agents":[{"name":"claude","description":"Catch-all for any task that doesn't fit a more specific agent. FleetView's default when no agent name is typed."},{"name":"claude-code-guide","description":"Use this agent when the user asks questions (\"Can Claude...\", \"Does Claude...\", \"How do I...\") about: (1) Claude Code (the CLI tool) - features, hooks, slash commands, MCP servers, settings, IDE integrations, keyboard shortcuts; (2) Claude Agent SDK - building custom agents; (3) Claude API (formerly Anthropic API) - Messages API for directly passing messages to Claude, Tool Runner (`client.beta.messages.tool_runner`) for running an agentic loop over your own tools, manual tool-use loops, Managed Agents for server-hosted agents with a managed sandbox, prompt caching, and general Anthropic SDK usage; (4) Claude Tag (Claude in Slack) - what it is, setting it up for a Slack workspace, `/install-slack-app`; (5) `claude plugin eval` (writing and running plugin eval suites, its JSON/report, sandbox, CI) and the `/skill-doctor` report. **IMPORTANT:** Before spawning a new agent, check if there is already a running or recently completed claude-code-guide agent that you can continue via SendMessage.","model":"haiku"},{"name":"Explore","description":"Fast read-only search agent for locating code. Use it to find files by pattern (eg. \"src/components/**/*.tsx\"), grep for symbols or keywords (eg. \"API endpoints\"), or answer \"where is X defined / which files reference Y.\" Do NOT use it for code review, design-doc auditing, cross-file consistency checks, or open-ended analysis — it reads excerpts rather than whole files and will miss content past its read window. When calling, specify search breadth: \"quick\" for a single targeted lookup, \"medium\" for moderate exploration, or \"very thorough\" to search across multiple locations and naming conventions.","model":"inherit"},{"name":"general-purpose","description":"General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you."},{"name":"Plan","description":"Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs.","model":"inherit"},{"name":"statusline-setup","description":"Use this agent to configure the user's Claude Code status line setting.","model":"sonnet"}],"output_style":"default","available_output_styles":["default","Proactive","Concise","Explanatory","Learning"],"user_output_styles_dir":"/Users/flamingcow/.claude/output-styles","models":[{"value":"default","resolvedModel":"claude-opus-5-5","displayName":"Default (recommended)","description":"Opus 5.5 · Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"opus","resolvedModel":"claude-opus-5-5","displayName":"Opus 5.5","description":"For complex work and everyday tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"fable","resolvedModel":"claude-fable-5-1","displayName":"Fable 5.1","description":"For your toughest challenges","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"sonnet","resolvedModel":"claude-sonnet-5-5","displayName":"Sonnet 5.5","description":"Most efficient for simpler tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"haiku","resolvedModel":"claude-haiku-5-5","displayName":"Haiku 5.5","description":"Fastest for quick answers","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-haiku-4-5-20251001","resolvedModel":"claude-haiku-4-5-20251001","displayName":"Haiku 4.5","description":"Fastest for quick answers"},{"value":"claude-sonnet-5","resolvedModel":"claude-sonnet-5","displayName":"Sonnet 5","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-5","resolvedModel":"claude-opus-5","displayName":"Opus 5","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-fable-5","resolvedModel":"claude-fable-5","displayName":"Fable 5","description":"Most capable for your hardest and longest-running tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-8","resolvedModel":"claude-opus-4-8","displayName":"Opus 4.8","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-opus-4-7","resolvedModel":"claude-opus-4-7","displayName":"Opus 4.7","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-6","resolvedModel":"claude-opus-4-6","displayName":"Opus 4.6","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-sonnet-4-6","resolvedModel":"claude-sonnet-4-6","displayName":"Sonnet 4.6","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true}],"account":{"email":"[redacted]","organization":"[redacted]'s Organization","subscriptionType":"Claude Max","apiProvider":"firstParty"},"pid":2403,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","hooks_applied":true,"feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} {"dir":"send","msg":{"message":{"content":"Reply with the single word ok.","role":"user"},"parent_tool_use_id":null,"session_id":"","type":"user"}} -{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestStopHookBlocks582294929/001","session_id":"3a5eb510-b78c-4f3b-bc01-b15807f70003","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","LSP","Monitor","NotebookEdit","PushNotification","Read","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"pending","source":"claudeai"},{"name":"claude.ai Heliosian","status":"pending","source":"claudeai"},{"name":"claude.ai Fastmail","status":"pending","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"b2b436bc-fe36-4809-a1ad-824239b4408a","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks582294929-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks582294929-001/3a5eb510-b78c-4f3b-bc01-b15807f70003/scratchpad","messaging_socket_path":"/tmp/cc-socks/98364.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"3a5eb510-b78c-4f3b-bc01-b15807f70003","uuid":"18cf8903-3877-4d59-b9e3-6b87b7cf1559"}} -{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.01,"resetsAt":1792054200},"seven_day":{"utilization":0.34,"resetsAt":1792270800}}},"uuid":"5c9914da-3ac9-4e6f-b863-5708567463e0","session_id":"3a5eb510-b78c-4f3b-bc01-b15807f70003"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3MazufpKaWg1rWUNvs5","type":"message","role":"assistant","content":[{"type":"text","text":"ok"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15233,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15233},"output_tokens":4,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"3a5eb510-b78c-4f3b-bc01-b15807f70003","uuid":"cc712600-aad9-43a5-a7cb-57ab2fb9600b","timestamp":"2026-10-15T04:01:03.441Z","request_id":"req_011Cg3MazXMngPm6MEkboQhL"}} -{"dir":"recv","msg":{"type":"control_request","request_id":"1581cbd8-4d8b-4459-bdee-5931bf7efc3e","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"3a5eb510-b78c-4f3b-bc01-b15807f70003","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks582294929-001/3a5eb510-b78c-4f3b-bc01-b15807f70003.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestStopHookBlocks582294929/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks582294929-001/3a5eb510-b78c-4f3b-bc01-b15807f70003/scratchpad","prompt_id":"8e4c4b7c-16fc-4b76-9352-f889570d8de2","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"Stop","stop_hook_active":false,"last_assistant_message":"ok","background_tasks":[],"session_crons":[]},"tool_use_id":"b32ba246-fa7c-45dd-b67c-b0a441ec331a"}}} -{"dir":"send","msg":{"response":{"request_id":"1581cbd8-4d8b-4459-bdee-5931bf7efc3e","response":{"decision":"block","reason":"Before stopping, reply with the single word PINEAPPLE."},"subtype":"success"},"type":"control_response"}} -{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"type":"text","text":"Stop hook feedback:\nBefore stopping, reply with the single word PINEAPPLE."}]},"parent_tool_use_id":null,"session_id":"3a5eb510-b78c-4f3b-bc01-b15807f70003","uuid":"91ccf118-5b3b-42a3-9d6f-400ac2cee0fe","timestamp":"2026-10-15T04:01:03.467Z","isSynthetic":true}} -{"dir":"recv","msg":{"type":"system","subtype":"notification","key":"stop-hook-error","text":"Stop hook error occurred · ctrl+o to see","priority":"immediate","session_id":"3a5eb510-b78c-4f3b-bc01-b15807f70003","uuid":"24bfc79c-50b4-4be6-8ddd-942cc626f607"}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"3a5eb510-b78c-4f3b-bc01-b15807f70003","uuid":"f87132cf-6c29-404a-be79-1287757e5519"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3Mb7x5cs8by4chcpqws","type":"message","role":"assistant","content":[{"type":"text","text":"PINEAPPLE"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":7060,"cache_read_input_tokens":30620,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":7060},"output_tokens":8,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":{"cache_miss_reason":{"type":"messages_changed","cache_missed_input_tokens":13144}},"context_management":null},"parent_tool_use_id":null,"session_id":"3a5eb510-b78c-4f3b-bc01-b15807f70003","uuid":"dfe97aca-77da-494e-9255-ac5939df1d2c","timestamp":"2026-10-15T04:01:05.136Z","request_id":"req_011Cg3Mb7fTzGgZZFbTLvAwk"}} -{"dir":"recv","msg":{"type":"control_request","request_id":"3925aa2e-872e-456e-8e2e-9331f00b3285","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"3a5eb510-b78c-4f3b-bc01-b15807f70003","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks582294929-001/3a5eb510-b78c-4f3b-bc01-b15807f70003.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestStopHookBlocks582294929/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks582294929-001/3a5eb510-b78c-4f3b-bc01-b15807f70003/scratchpad","prompt_id":"8e4c4b7c-16fc-4b76-9352-f889570d8de2","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"Stop","stop_hook_active":true,"last_assistant_message":"PINEAPPLE","background_tasks":[],"session_crons":[]},"tool_use_id":"c75ff38d-8b07-4e8a-bf60-e90c21d81367"}}} -{"dir":"send","msg":{"response":{"request_id":"3925aa2e-872e-456e-8e2e-9331f00b3285","response":{},"subtype":"success"},"type":"control_response"}} -{"dir":"recv","msg":{"duration_api_ms":4175,"stop_reason":"end_turn","session_id":"3a5eb510-b78c-4f3b-bc01-b15807f70003","total_cost_usd":0.0947431,"usage":{"input_tokens":4,"cache_creation_input_tokens":22293,"cache_read_input_tokens":52987,"output_tokens":14,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":22293,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":10,"cache_read_input_tokens":30620,"cache_creation_input_tokens":7060,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":7060},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1174,"outputTokens":14,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.0001244,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":4,"outputTokens":14,"cacheReadInputTokens":52987,"cacheCreationInputTokens":22293,"webSearchRequests":0,"costUSD":0.0946187,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":2,"subtype":"success","api_error_status":null,"result":"PINEAPPLE","ttft_ms":1748,"type":"result","duration_ms":3466,"uuid":"a6060220-2220-4305-bcb0-b12291b5904d","ttft_stream_ms":1742,"time_to_request_ms":31,"first_content_frame_ms":1743,"queued_turn_count":0,"result_index":0}} +{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestStopHookBlocks1543832283/001","session_id":"f2eb3675-359b-41c1-b184-2852a9cb50d3","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","LSP","Monitor","NotebookEdit","PushNotification","Read","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"pending","source":"claudeai"},{"name":"claude.ai Heliosian","status":"pending","source":"claudeai"},{"name":"claude.ai Fastmail","status":"pending","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"deeab340-09ad-4d01-8621-e5bd84b71678","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks1543832283-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks1543832283-001/f2eb3675-359b-41c1-b184-2852a9cb50d3/scratchpad","messaging_socket_path":"/tmp/cc-socks/2403.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"f2eb3675-359b-41c1-b184-2852a9cb50d3","uuid":"9040b94d-c6c8-4b0e-b65a-2ce381b2b1d4"}} +{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.01,"resetsAt":1792054200},"seven_day":{"utilization":0.34,"resetsAt":1792270800}}},"uuid":"8dc25014-4c78-434f-ab5e-d495f03323e0","session_id":"f2eb3675-359b-41c1-b184-2852a9cb50d3"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3MyvSgSeP3AdfkzTRth","type":"message","role":"assistant","content":[{"type":"text","text":"ok"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15238,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15238},"output_tokens":4,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"f2eb3675-359b-41c1-b184-2852a9cb50d3","uuid":"dff1cf80-4176-4553-ba47-fd3c906e84bb","timestamp":"2026-10-15T04:06:14.219Z","request_id":"req_011Cg3Myv7L7KZt8GVzLzgZ6"}} +{"dir":"recv","msg":{"type":"control_request","request_id":"bb5e1965-536d-4a79-b36f-ed1940d49551","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"f2eb3675-359b-41c1-b184-2852a9cb50d3","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks1543832283-001/f2eb3675-359b-41c1-b184-2852a9cb50d3.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestStopHookBlocks1543832283/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks1543832283-001/f2eb3675-359b-41c1-b184-2852a9cb50d3/scratchpad","prompt_id":"2be7c8a0-3cb9-4dc7-aea6-9c00a115b277","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"Stop","stop_hook_active":false,"last_assistant_message":"ok","background_tasks":[],"session_crons":[]},"tool_use_id":"261b7db1-6ad9-4d40-81a9-d1a775ed43ae"}}} +{"dir":"send","msg":{"response":{"request_id":"bb5e1965-536d-4a79-b36f-ed1940d49551","response":{"decision":"block","reason":"Before stopping, reply with the single word PINEAPPLE."},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"type":"text","text":"Stop hook feedback:\nBefore stopping, reply with the single word PINEAPPLE."}]},"parent_tool_use_id":null,"session_id":"f2eb3675-359b-41c1-b184-2852a9cb50d3","uuid":"1900e8ec-ea80-4e61-b30b-b630fc9b3e3f","timestamp":"2026-10-15T04:06:14.248Z","isSynthetic":true}} +{"dir":"recv","msg":{"type":"system","subtype":"notification","key":"stop-hook-error","text":"Stop hook error occurred · ctrl+o to see","priority":"immediate","session_id":"f2eb3675-359b-41c1-b184-2852a9cb50d3","uuid":"edc79401-9d03-4a72-b70a-ed273ea03a7c"}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"f2eb3675-359b-41c1-b184-2852a9cb50d3","uuid":"f5f7deb1-abe5-489c-82f0-7b887d9c5861"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3Mz2c1Ng58SbmBKJ8Gz","type":"message","role":"assistant","content":[{"type":"text","text":"PINEAPPLE"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":7062,"cache_read_input_tokens":30623,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":7062},"output_tokens":8,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":{"cache_miss_reason":{"type":"messages_changed","cache_missed_input_tokens":13145}},"context_management":null},"parent_tool_use_id":null,"session_id":"f2eb3675-359b-41c1-b184-2852a9cb50d3","uuid":"14d78250-5c44-431b-b780-2d54019eb291","timestamp":"2026-10-15T04:06:15.707Z","request_id":"req_011Cg3Mz2LPqQxXcpceL4dZu"}} +{"dir":"recv","msg":{"type":"control_request","request_id":"98cbb8e3-5b39-4455-8aff-8444d126845f","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"f2eb3675-359b-41c1-b184-2852a9cb50d3","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks1543832283-001/f2eb3675-359b-41c1-b184-2852a9cb50d3.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestStopHookBlocks1543832283/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks1543832283-001/f2eb3675-359b-41c1-b184-2852a9cb50d3/scratchpad","prompt_id":"2be7c8a0-3cb9-4dc7-aea6-9c00a115b277","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"Stop","stop_hook_active":true,"last_assistant_message":"PINEAPPLE","background_tasks":[],"session_crons":[]},"tool_use_id":"2f61f7ad-ea3d-4898-bc6a-9895cace693b"}}} +{"dir":"send","msg":{"response":{"request_id":"98cbb8e3-5b39-4455-8aff-8444d126845f","response":{},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"duration_api_ms":3534,"stop_reason":"end_turn","session_id":"f2eb3675-359b-41c1-b184-2852a9cb50d3","total_cost_usd":0.0947714,"usage":{"input_tokens":4,"cache_creation_input_tokens":22300,"cache_read_input_tokens":52990,"output_tokens":14,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":22300,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":10,"cache_read_input_tokens":30623,"cache_creation_input_tokens":7062,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":7062},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1174,"outputTokens":14,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.0001244,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":4,"outputTokens":14,"cacheReadInputTokens":52990,"cacheCreationInputTokens":22300,"webSearchRequests":0,"costUSD":0.09464700000000001,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":2,"subtype":"success","api_error_status":null,"result":"PINEAPPLE","ttft_ms":1549,"type":"result","duration_ms":3055,"uuid":"89c8d99a-4fd5-43a5-97bb-6da3e9834d4c","ttft_stream_ms":1547,"time_to_request_ms":35,"first_content_frame_ms":1547,"queued_turn_count":0,"result_index":0}} diff --git a/internal/claude/testdata/transcripts/TestTextDeltas.jsonl b/internal/claude/testdata/transcripts/TestTextDeltas.jsonl index 9437e54..eec920d 100644 --- a/internal/claude/testdata/transcripts/TestTextDeltas.jsonl +++ b/internal/claude/testdata/transcripts/TestTextDeltas.jsonl @@ -1,8 +1,8 @@ -{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_21a0463a8f168dbc","type":"control_request"}} -{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_21a0463a8f168dbc","response":{"commands":[{"name":"deep-research","description":"Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. (dynamic workflow)","argumentHint":"","builtin":true},{"name":"design","description":"Make a new Design artifact from a brief","argumentHint":"[what to design]","builtin":true},{"name":"slides","description":"Make a new Slides deck artifact from a brief","argumentHint":"[what the deck is about]","builtin":true},{"name":"design-sync","description":"Push a React design system to claude.ai/design. This runs a converter that bundles the real component code (from Storybook or a bare package) and uploads it. Use when the user runs /design-sync or says \"sync my design system to Claude Design\".","argumentHint":"[\u003cproject hint, e.g. \"Acme DS\"\u003e]","builtin":true},{"name":"dataviz","description":"Use this skill whenever you are about to create ANY chart, graph, plot, dashboard, or data visualization, in ANY output medium — an HTML or React artifact, inline SVG, plotting code in any library (matplotlib, plotly, d3, Recharts, …), an image/PNG you will render and upload, or a chart shared into Slack. Read it BEFORE writing the first line of chart code, choosing chart colors, building a stat tile / meter / KPI row, or laying out a dashboard. When the destination is a first-party document connector (host-designated, never self-described) that renders live charts, hand it the rows (inline, or as an uploaded data file the chart cites) rather than a rendered PNG/SVG — a picture of a chart loses hover, data inspection and per-value comments. Produces visualizations that read as one system — elegant, accessible, consistent in light and dark — using a brand-neutral placeholder palette you swap for your own. Teaches a design-system-agnostic method: a form heuristic, a color formula with a runnable validator, mark specs, and interaction rules. A validated default palette is documented in `references/palette.md` — swap that file's values for your brand's. Triggers on: \"chart\", \"graph\", \"plot\", \"data viz\", \"visualization\", \"dashboard\", \"analytics\", \"visualize data\", \"categorical colors\", \"sequential / diverging palette\", \"stat tile\", \"sparkline\", \"heatmap\", \"legend\", \"axis\", \"tooltip\", \"chart colors\", \"color by series\".","argumentHint":"","builtin":true},{"name":"artifact-diagramming","description":"Diagramming know-how for Artifacts - when a picture earns its place, how to draw one that shows the real mechanism, and the inline-SVG mechanics that keep it legible in both themes.","argumentHint":"","builtin":true},{"name":"artifact-capabilities","description":"Runtime capabilities a published Artifact page can be granted — behavior static HTML cannot provide on its own, such as the page reading live or connected data, remembering what people do on it (a poll, a sign-up sheet, a checklist, a document edited in place — it saves new versions of itself), keeping state shared across viewers, knowing who is viewing, asking Claude a question of its own, storing files people add, handing the viewer a file to save, or using the viewer's camera, microphone, location, screen or device motion. Serves this user's live capability roster and the typed call definitions. Load it whenever any such runtime behavior would make an artifact more useful, before writing the page.","argumentHint":"","builtin":true},{"name":"update-config","description":"Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme/model, suggest the /config command.","argumentHint":"","builtin":true},{"name":"verify","description":"Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.","argumentHint":"","builtin":true},{"name":"debug","description":"Enable debug logging for this session and help diagnose issues","argumentHint":"[issue description]","builtin":true},{"name":"code-review","description":"Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep multi-agent review in the cloud); with no level given, it reuses the level you typed last. Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review. Pass --max-findings \u003cn\u003e to report up to n findings, or --max-findings all for every finding. The choice stays until you pass --max-findings default. For ultra on a GitHub.com PR target, --post asks to post the finished review’s findings to the PR as a single comment from the user’s GitHub account (not a review; the launch dialog still confirms in interactive sessions, while non-interactive mode posts on the flag alone) and --no-post hides that option.","argumentHint":"[low|medium|high|xhigh|max|ultra] [--fix] [--comment] [\u003cpr#\u003e|\u003cbranch\u003e|\u003cpath\u003e] [--max-findings \u003cn\u003e|all]","aliases":["review"],"builtin":true},{"name":"simplify","description":"Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.","argumentHint":"[\u003ctarget\u003e]","builtin":true},{"name":"batch","description":"Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.","argumentHint":"\u003cinstruction\u003e","builtin":true},{"name":"fewer-permission-prompts","description":"Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.","argumentHint":"","builtin":true},{"name":"doctor","description":"Health-check the user's Claude Code setup and fix issues: diagnose installation health — what the `claude doctor` terminal diagnostics cover — from local data (duplicate or leftover installs, PATH, unparseable settings files, broken or colliding agent definitions, skills whose frontmatter fails to parse); find unused skills, MCP servers, and plugins versus their context cost and disable dead weight; deduplicate local CLAUDE.md files against checked-in ones; trim checked-in CLAUDE.md files by cutting content a session could derive from the codebase (directory layouts, tech-stack lists, architecture overviews) while keeping gotchas, rationale, and non-standard conventions; migrate always-loaded CLAUDE.md guidance into lazy skills and nested CLAUDE.md files; flag slow hooks and context-heavy extensions; check the installed version is current; make auto mode the default permission mode; and pre-approve frequently denied read-only commands. Use when the user asks for a doctor run, checkup, audit, tune-up, or cleanup of their Claude Code setup or configuration.","argumentHint":"[prompt-audit [\u003cpath\u003e]]","aliases":["checkup"],"builtin":true},{"name":"loop","description":"Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.","argumentHint":"[interval] [prompt]","aliases":["proactive"],"builtin":true},{"name":"schedule","description":"Create, update, list, or run scheduled cloud agents (routines) that execute on a cron schedule.","argumentHint":"","aliases":["routines"],"builtin":true},{"name":"claude-api","description":"Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).","argumentHint":"","builtin":true},{"name":"workflow-authoring","description":"Reference for writing a Workflow tool script (script API and gotchas, resume, quality patterns, worked examples). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.","argumentHint":"","builtin":true},{"name":"run","description":"Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).","argumentHint":"","builtin":true},{"name":"run-skill-generator","description":"Author or improve the run-\u003cunit\u003e skill - a per-project skill that tells agents how to build, launch, and drive this project's app. Use when the user asks to set up the project, get it running, write run instructions, or verify build/run steps work from a clean environment.","argumentHint":"","builtin":true},{"name":"plugin-authoring","description":"Make a mod: a change to Claude's own interface or behaviour, such as a live pane or panel, a band above the prompt, a status line, a toast, a slash command, or a hook on tool calls or prompts. Use to make, change or debug a mod or its hooks module.","argumentHint":"","builtin":true},{"name":"advisor","description":"Let Claude consult a stronger model at key moments","argumentHint":"[fable|opus|sonnet|off]","builtin":true},{"name":"agents","description":"(removed) Ask Claude to create/manage subagents, or edit .claude/agents/","argumentHint":"","builtin":true},{"name":"auto-mode-setup","description":"Teach auto mode about your environment, plus optional rule tweaks","argumentHint":"[--request-id \u003cuuid\u003e] (--wizard posture=… scope=… depth=… --propose | --expect-sha256 \u003c64-hex\u003e --apply-file \u003cpath\u003e)","builtin":true},{"name":"autocompact","description":"Configure the auto-compact window size","argumentHint":"[auto|\u003ctokens\u003e]","builtin":true},{"name":"clear","description":"Start a new session with empty context; previous session stays on disk (resumable with /resume)","argumentHint":"[name]","aliases":["reset","new"],"builtin":true},{"name":"color","description":"Set the prompt bar color for this session","argumentHint":"[red|blue|green|yellow|purple|orange|pink|cyan|default]","builtin":true},{"name":"compact","description":"Free up context by summarizing the conversation so far","argumentHint":"\u003coptional custom summarization instructions\u003e","builtin":true},{"name":"config","description":"Set a setting by key","argumentHint":"key=value","aliases":["settings"],"builtin":true},{"name":"output-style","description":"List output styles or switch to one","argumentHint":"[style]","builtin":true},{"name":"context","description":"Show current context usage","argumentHint":"","builtin":true},{"name":"effort","description":"Set effort level for model usage","argumentHint":"\u003clow|medium|high|xhigh|max|auto|ultracode [on|off]\u003e","builtin":true},{"name":"fast","description":"Toggle fast mode (Opus 5.5)","argumentHint":"[on|off]","builtin":true},{"name":"focus","description":"Toggle focus view: just your prompt, summary, and response","argumentHint":"[on|off]","builtin":true},{"name":"heapdump","description":"Dump the JS heap to the Desktop; on Linux with no Desktop folder, the home directory","argumentHint":"","builtin":true},{"name":"init","description":"Initialize a new CLAUDE.md file with codebase documentation","argumentHint":"","builtin":true},{"name":"mcp","description":"Manage MCP servers","argumentHint":"[reconnect|enable|disable [\u003cserver\u003e|all]]","builtin":true},{"name":"import","description":"Import config from another AI coding agent","argumentHint":"","builtin":true},{"name":"model","description":"Set the AI model for Claude Code","argumentHint":"\u003cmodel\u003e","builtin":true},{"name":"__remote-workflow","description":"Run the workflow script delivered in this session environment (server-launched sessions only)","argumentHint":"","builtin":true},{"name":"workflow-launch-exec","description":"Execute a server-launched workflow handoff (workflow_launch event sessions only)","argumentHint":"","builtin":true},{"name":"reload-plugins","description":"Activate pending plugin changes in the current session","argumentHint":"[--force]","builtin":true},{"name":"reload-skills","description":"Pick up skills added or changed on disk during this session","argumentHint":"","builtin":true},{"name":"rename","description":"Rename the current conversation","argumentHint":"[name]","aliases":["name"],"builtin":true},{"name":"ultrareview","description":"Start a cloud agent that finds and verifies bugs in your branch (~15-25 min, $5-$25 USD) · Runs in a cloud session. See https://code.claude.com/docs/en/claude-code-on-the-web","argumentHint":"","builtin":true},{"name":"security-review","description":"Complete a security review of the pending changes on the current branch","argumentHint":"","builtin":true},{"name":"usage-credits","description":"Configure usage credits or request them from your admin when you hit a limit","argumentHint":"","builtin":true},{"name":"extra-usage","description":"Renamed to /usage-credits","argumentHint":"","builtin":true},{"name":"usage","description":"Show session cost, plan usage, and what's contributing to your limits","argumentHint":"","aliases":["cost","stats"],"builtin":true},{"name":"insights","description":"Generate a report analyzing your Claude Code sessions","argumentHint":"","builtin":true},{"name":"recap","description":"Generate a one-line session recap now","argumentHint":"","builtin":true},{"name":"skill-doctor","description":"Show which loaded skills are unused and costing context","argumentHint":"","builtin":true},{"name":"goal","description":"Set a goal — keep working until the condition is met","argumentHint":"","builtin":true},{"name":"design-consent","description":"Grant Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"design-revoke","description":"Revoke Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"list-agents","description":"List subagents, teammates, and other Claude sessions you can message","argumentHint":"","aliases":["peers"],"builtin":true},{"name":"team-onboarding","description":"Help teammates ramp on Claude Code with a guide from your usage","argumentHint":"","builtin":true},{"name":"docs","description":"docs (editable docs people share and comment on; the default for any document, named as a doc or not: a document, report, proposal, resume, cover letter, letter, contract, policy, form, template, worksheet, essay, handbook, guide, how-to, cheat sheet, SOP or other writing to keep, share, collaborate on, send, submit, print or sign; a doc exports to Word, PDF, Markdown or Google Docs, so needing a file to send, attach, upload, submit or print is no reason to pick Word, and a file nobody asked for is a doc, not Word; a plan, comparison, summary or notes asked in chat stays in chat; a pasted claude.ai artifact link may be a doc: check with docs tools first; Word or another file format named, tracked changes wanted, or a .docx to change or use as a template → that format's skill): making one → if no docs-connector instructions are in context, call its `guide` (topic.instructions) first; then create the doc (headings only, no body) before any search, file read or plan, even with files attached. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docs"]},{"name":"docx","description":"Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers include: any mention of Microsoft Word Documents, such as 'Word doc', 'word document', '.docx', '.dotx', 'microsoft doc'. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a deliverable as a Word or .docx file (to download, email or print), use this skill. However, if they ask for a document, page, report, memo, or notes WITHOUT naming a file format and the session offers Claude's own dedicated document or page skill or connector, use that instead, even if they will email or print it. Do NOT use for PDFs, spreadsheets, Google Docs, or coding unrelated to document generation. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docx"]},{"name":"google-workspace","description":"Read this before the first Google Drive, Docs, Sheets or Slides connector call whenever the task creates or changes a Google file. Use this skill whenever the user wants to create or change a Google Doc, Sheet or Slides file in their Google Drive. Triggers include: a request that names Google Docs, Sheets, Slides or Drive and asks to make, edit, format, copy or rename a file; a docs.google.com link with a request to change that file, even a one-line fix or suggested edits; and any follow-up change to a Google file from earlier in the chat, even \"change it\" or \"add a tab\". Includes helper scripts for document positions, cell ranges and slide layout. However, if the user asks for a doc, deck or spreadsheet without naming Google, or gives a Google file only as source material for something new, use Claude's own output type instead. Do NOT use for read-only questions about a Google file, or for Word, Excel, PowerPoint or PDF files. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:google-workspace"]},{"name":"import-memory","description":"Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:import-memory"]},{"name":"morning","description":"Render the user's morning brief as a styled HTML artifact, or set it up as a recurring weekday task. Use only when the user explicitly asks to run, see, or set up their morning brief, or if they invoke /morning by name. A question about their day, schedule, or calendar is not by itself a request for the brief; answer it directly instead. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:morning"]},{"name":"pdf","description":"Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pdf"]},{"name":"pptx","description":"Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations as PowerPoint (.pptx) files; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email, summary, or creating a different type of slide deck); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user asks for a PowerPoint or .pptx file, or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. However, when the user asks for a deck, slides, a slide deck, or a presentation without naming a file format, default to using a dedicated slide-deck artifact type or a separate slides skill if this session offers one; otherwise, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pptx"]},{"name":"skill-creator","description":"Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:skill-creator"]},{"name":"xlsx","description":"Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:xlsx"]}],"agents":[{"name":"claude","description":"Catch-all for any task that doesn't fit a more specific agent. FleetView's default when no agent name is typed."},{"name":"claude-code-guide","description":"Use this agent when the user asks questions (\"Can Claude...\", \"Does Claude...\", \"How do I...\") about: (1) Claude Code (the CLI tool) - features, hooks, slash commands, MCP servers, settings, IDE integrations, keyboard shortcuts; (2) Claude Agent SDK - building custom agents; (3) Claude API (formerly Anthropic API) - Messages API for directly passing messages to Claude, Tool Runner (`client.beta.messages.tool_runner`) for running an agentic loop over your own tools, manual tool-use loops, Managed Agents for server-hosted agents with a managed sandbox, prompt caching, and general Anthropic SDK usage; (4) Claude Tag (Claude in Slack) - what it is, setting it up for a Slack workspace, `/install-slack-app`; (5) `claude plugin eval` (writing and running plugin eval suites, its JSON/report, sandbox, CI) and the `/skill-doctor` report. **IMPORTANT:** Before spawning a new agent, check if there is already a running or recently completed claude-code-guide agent that you can continue via SendMessage.","model":"haiku"},{"name":"Explore","description":"Fast read-only search agent for locating code. Use it to find files by pattern (eg. \"src/components/**/*.tsx\"), grep for symbols or keywords (eg. \"API endpoints\"), or answer \"where is X defined / which files reference Y.\" Do NOT use it for code review, design-doc auditing, cross-file consistency checks, or open-ended analysis — it reads excerpts rather than whole files and will miss content past its read window. When calling, specify search breadth: \"quick\" for a single targeted lookup, \"medium\" for moderate exploration, or \"very thorough\" to search across multiple locations and naming conventions.","model":"inherit"},{"name":"general-purpose","description":"General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you."},{"name":"Plan","description":"Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs.","model":"inherit"},{"name":"statusline-setup","description":"Use this agent to configure the user's Claude Code status line setting.","model":"sonnet"}],"output_style":"default","available_output_styles":["default","Proactive","Concise","Explanatory","Learning"],"user_output_styles_dir":"/Users/flamingcow/.claude/output-styles","models":[{"value":"default","resolvedModel":"claude-opus-5-5","displayName":"Default (recommended)","description":"Opus 5.5 · Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"opus","resolvedModel":"claude-opus-5-5","displayName":"Opus 5.5","description":"For complex work and everyday tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"fable","resolvedModel":"claude-fable-5-1","displayName":"Fable 5.1","description":"For your toughest challenges","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"sonnet","resolvedModel":"claude-sonnet-5-5","displayName":"Sonnet 5.5","description":"Most efficient for simpler tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"haiku","resolvedModel":"claude-haiku-5-5","displayName":"Haiku 5.5","description":"Fastest for quick answers","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-haiku-4-5-20251001","resolvedModel":"claude-haiku-4-5-20251001","displayName":"Haiku 4.5","description":"Fastest for quick answers"},{"value":"claude-sonnet-5","resolvedModel":"claude-sonnet-5","displayName":"Sonnet 5","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-5","resolvedModel":"claude-opus-5","displayName":"Opus 5","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-fable-5","resolvedModel":"claude-fable-5","displayName":"Fable 5","description":"Most capable for your hardest and longest-running tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-8","resolvedModel":"claude-opus-4-8","displayName":"Opus 4.8","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-opus-4-7","resolvedModel":"claude-opus-4-7","displayName":"Opus 4.7","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-6","resolvedModel":"claude-opus-4-6","displayName":"Opus 4.6","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-sonnet-4-6","resolvedModel":"claude-sonnet-4-6","displayName":"Sonnet 4.6","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true}],"account":{"email":"[redacted]","organization":"[redacted]'s Organization","subscriptionType":"Claude Max","apiProvider":"firstParty"},"pid":98362,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} +{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_5c4bebb00fde9754","type":"control_request"}} +{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_5c4bebb00fde9754","response":{"commands":[{"name":"deep-research","description":"Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. (dynamic workflow)","argumentHint":"","builtin":true},{"name":"design","description":"Make a new Design artifact from a brief","argumentHint":"[what to design]","builtin":true},{"name":"slides","description":"Make a new Slides deck artifact from a brief","argumentHint":"[what the deck is about]","builtin":true},{"name":"design-sync","description":"Push a React design system to claude.ai/design. This runs a converter that bundles the real component code (from Storybook or a bare package) and uploads it. Use when the user runs /design-sync or says \"sync my design system to Claude Design\".","argumentHint":"[\u003cproject hint, e.g. \"Acme DS\"\u003e]","builtin":true},{"name":"dataviz","description":"Use this skill whenever you are about to create ANY chart, graph, plot, dashboard, or data visualization, in ANY output medium — an HTML or React artifact, inline SVG, plotting code in any library (matplotlib, plotly, d3, Recharts, …), an image/PNG you will render and upload, or a chart shared into Slack. Read it BEFORE writing the first line of chart code, choosing chart colors, building a stat tile / meter / KPI row, or laying out a dashboard. When the destination is a first-party document connector (host-designated, never self-described) that renders live charts, hand it the rows (inline, or as an uploaded data file the chart cites) rather than a rendered PNG/SVG — a picture of a chart loses hover, data inspection and per-value comments. Produces visualizations that read as one system — elegant, accessible, consistent in light and dark — using a brand-neutral placeholder palette you swap for your own. Teaches a design-system-agnostic method: a form heuristic, a color formula with a runnable validator, mark specs, and interaction rules. A validated default palette is documented in `references/palette.md` — swap that file's values for your brand's. Triggers on: \"chart\", \"graph\", \"plot\", \"data viz\", \"visualization\", \"dashboard\", \"analytics\", \"visualize data\", \"categorical colors\", \"sequential / diverging palette\", \"stat tile\", \"sparkline\", \"heatmap\", \"legend\", \"axis\", \"tooltip\", \"chart colors\", \"color by series\".","argumentHint":"","builtin":true},{"name":"artifact-diagramming","description":"Diagramming know-how for Artifacts - when a picture earns its place, how to draw one that shows the real mechanism, and the inline-SVG mechanics that keep it legible in both themes.","argumentHint":"","builtin":true},{"name":"artifact-capabilities","description":"Runtime capabilities a published Artifact page can be granted — behavior static HTML cannot provide on its own, such as the page reading live or connected data, remembering what people do on it (a poll, a sign-up sheet, a checklist, a document edited in place — it saves new versions of itself), keeping state shared across viewers, knowing who is viewing, asking Claude a question of its own, storing files people add, handing the viewer a file to save, or using the viewer's camera, microphone, location, screen or device motion. Serves this user's live capability roster and the typed call definitions. Load it whenever any such runtime behavior would make an artifact more useful, before writing the page.","argumentHint":"","builtin":true},{"name":"update-config","description":"Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme/model, suggest the /config command.","argumentHint":"","builtin":true},{"name":"verify","description":"Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.","argumentHint":"","builtin":true},{"name":"debug","description":"Enable debug logging for this session and help diagnose issues","argumentHint":"[issue description]","builtin":true},{"name":"code-review","description":"Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep multi-agent review in the cloud); with no level given, it reuses the level you typed last. Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review. Pass --max-findings \u003cn\u003e to report up to n findings, or --max-findings all for every finding. The choice stays until you pass --max-findings default. For ultra on a GitHub.com PR target, --post asks to post the finished review’s findings to the PR as a single comment from the user’s GitHub account (not a review; the launch dialog still confirms in interactive sessions, while non-interactive mode posts on the flag alone) and --no-post hides that option.","argumentHint":"[low|medium|high|xhigh|max|ultra] [--fix] [--comment] [\u003cpr#\u003e|\u003cbranch\u003e|\u003cpath\u003e] [--max-findings \u003cn\u003e|all]","aliases":["review"],"builtin":true},{"name":"simplify","description":"Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.","argumentHint":"[\u003ctarget\u003e]","builtin":true},{"name":"batch","description":"Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.","argumentHint":"\u003cinstruction\u003e","builtin":true},{"name":"fewer-permission-prompts","description":"Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.","argumentHint":"","builtin":true},{"name":"doctor","description":"Health-check the user's Claude Code setup and fix issues: diagnose installation health — what the `claude doctor` terminal diagnostics cover — from local data (duplicate or leftover installs, PATH, unparseable settings files, broken or colliding agent definitions, skills whose frontmatter fails to parse); find unused skills, MCP servers, and plugins versus their context cost and disable dead weight; deduplicate local CLAUDE.md files against checked-in ones; trim checked-in CLAUDE.md files by cutting content a session could derive from the codebase (directory layouts, tech-stack lists, architecture overviews) while keeping gotchas, rationale, and non-standard conventions; migrate always-loaded CLAUDE.md guidance into lazy skills and nested CLAUDE.md files; flag slow hooks and context-heavy extensions; check the installed version is current; make auto mode the default permission mode; and pre-approve frequently denied read-only commands. Use when the user asks for a doctor run, checkup, audit, tune-up, or cleanup of their Claude Code setup or configuration.","argumentHint":"[prompt-audit [\u003cpath\u003e]]","aliases":["checkup"],"builtin":true},{"name":"loop","description":"Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.","argumentHint":"[interval] [prompt]","aliases":["proactive"],"builtin":true},{"name":"schedule","description":"Create, update, list, or run scheduled cloud agents (routines) that execute on a cron schedule.","argumentHint":"","aliases":["routines"],"builtin":true},{"name":"claude-api","description":"Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).","argumentHint":"","builtin":true},{"name":"workflow-authoring","description":"Reference for writing a Workflow tool script (script API and gotchas, resume, quality patterns, worked examples). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.","argumentHint":"","builtin":true},{"name":"run","description":"Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).","argumentHint":"","builtin":true},{"name":"run-skill-generator","description":"Author or improve the run-\u003cunit\u003e skill - a per-project skill that tells agents how to build, launch, and drive this project's app. Use when the user asks to set up the project, get it running, write run instructions, or verify build/run steps work from a clean environment.","argumentHint":"","builtin":true},{"name":"plugin-authoring","description":"Make a mod: a change to Claude's own interface or behaviour, such as a live pane or panel, a band above the prompt, a status line, a toast, a slash command, or a hook on tool calls or prompts. Use to make, change or debug a mod or its hooks module.","argumentHint":"","builtin":true},{"name":"advisor","description":"Let Claude consult a stronger model at key moments","argumentHint":"[fable|opus|sonnet|off]","builtin":true},{"name":"agents","description":"(removed) Ask Claude to create/manage subagents, or edit .claude/agents/","argumentHint":"","builtin":true},{"name":"auto-mode-setup","description":"Teach auto mode about your environment, plus optional rule tweaks","argumentHint":"[--request-id \u003cuuid\u003e] (--wizard posture=… scope=… depth=… --propose | --expect-sha256 \u003c64-hex\u003e --apply-file \u003cpath\u003e)","builtin":true},{"name":"autocompact","description":"Configure the auto-compact window size","argumentHint":"[auto|\u003ctokens\u003e]","builtin":true},{"name":"clear","description":"Start a new session with empty context; previous session stays on disk (resumable with /resume)","argumentHint":"[name]","aliases":["reset","new"],"builtin":true},{"name":"color","description":"Set the prompt bar color for this session","argumentHint":"[red|blue|green|yellow|purple|orange|pink|cyan|default]","builtin":true},{"name":"compact","description":"Free up context by summarizing the conversation so far","argumentHint":"\u003coptional custom summarization instructions\u003e","builtin":true},{"name":"config","description":"Set a setting by key","argumentHint":"key=value","aliases":["settings"],"builtin":true},{"name":"output-style","description":"List output styles or switch to one","argumentHint":"[style]","builtin":true},{"name":"context","description":"Show current context usage","argumentHint":"","builtin":true},{"name":"effort","description":"Set effort level for model usage","argumentHint":"\u003clow|medium|high|xhigh|max|auto|ultracode [on|off]\u003e","builtin":true},{"name":"fast","description":"Toggle fast mode (Opus 5.5)","argumentHint":"[on|off]","builtin":true},{"name":"focus","description":"Toggle focus view: just your prompt, summary, and response","argumentHint":"[on|off]","builtin":true},{"name":"heapdump","description":"Dump the JS heap to the Desktop; on Linux with no Desktop folder, the home directory","argumentHint":"","builtin":true},{"name":"init","description":"Initialize a new CLAUDE.md file with codebase documentation","argumentHint":"","builtin":true},{"name":"mcp","description":"Manage MCP servers","argumentHint":"[reconnect|enable|disable [\u003cserver\u003e|all]]","builtin":true},{"name":"import","description":"Import config from another AI coding agent","argumentHint":"","builtin":true},{"name":"model","description":"Set the AI model for Claude Code","argumentHint":"\u003cmodel\u003e","builtin":true},{"name":"__remote-workflow","description":"Run the workflow script delivered in this session environment (server-launched sessions only)","argumentHint":"","builtin":true},{"name":"workflow-launch-exec","description":"Execute a server-launched workflow handoff (workflow_launch event sessions only)","argumentHint":"","builtin":true},{"name":"reload-plugins","description":"Activate pending plugin changes in the current session","argumentHint":"[--force]","builtin":true},{"name":"reload-skills","description":"Pick up skills added or changed on disk during this session","argumentHint":"","builtin":true},{"name":"rename","description":"Rename the current conversation","argumentHint":"[name]","aliases":["name"],"builtin":true},{"name":"ultrareview","description":"Start a cloud agent that finds and verifies bugs in your branch (~15-25 min, $5-$25 USD) · Runs in a cloud session. See https://code.claude.com/docs/en/claude-code-on-the-web","argumentHint":"","builtin":true},{"name":"security-review","description":"Complete a security review of the pending changes on the current branch","argumentHint":"","builtin":true},{"name":"usage-credits","description":"Configure usage credits or request them from your admin when you hit a limit","argumentHint":"","builtin":true},{"name":"extra-usage","description":"Renamed to /usage-credits","argumentHint":"","builtin":true},{"name":"usage","description":"Show session cost, plan usage, and what's contributing to your limits","argumentHint":"","aliases":["cost","stats"],"builtin":true},{"name":"insights","description":"Generate a report analyzing your Claude Code sessions","argumentHint":"","builtin":true},{"name":"recap","description":"Generate a one-line session recap now","argumentHint":"","builtin":true},{"name":"skill-doctor","description":"Show which loaded skills are unused and costing context","argumentHint":"","builtin":true},{"name":"goal","description":"Set a goal — keep working until the condition is met","argumentHint":"","builtin":true},{"name":"design-consent","description":"Grant Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"design-revoke","description":"Revoke Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"list-agents","description":"List subagents, teammates, and other Claude sessions you can message","argumentHint":"","aliases":["peers"],"builtin":true},{"name":"team-onboarding","description":"Help teammates ramp on Claude Code with a guide from your usage","argumentHint":"","builtin":true},{"name":"docs","description":"docs (editable docs people share and comment on; the default for any document, named as a doc or not: a document, report, proposal, resume, cover letter, letter, contract, policy, form, template, worksheet, essay, handbook, guide, how-to, cheat sheet, SOP or other writing to keep, share, collaborate on, send, submit, print or sign; a doc exports to Word, PDF, Markdown or Google Docs, so needing a file to send, attach, upload, submit or print is no reason to pick Word, and a file nobody asked for is a doc, not Word; a plan, comparison, summary or notes asked in chat stays in chat; a pasted claude.ai artifact link may be a doc: check with docs tools first; Word or another file format named, tracked changes wanted, or a .docx to change or use as a template → that format's skill): making one → if no docs-connector instructions are in context, call its `guide` (topic.instructions) first; then create the doc (headings only, no body) before any search, file read or plan, even with files attached. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docs"]},{"name":"docx","description":"Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers include: any mention of Microsoft Word Documents, such as 'Word doc', 'word document', '.docx', '.dotx', 'microsoft doc'. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a deliverable as a Word or .docx file (to download, email or print), use this skill. However, if they ask for a document, page, report, memo, or notes WITHOUT naming a file format and the session offers Claude's own dedicated document or page skill or connector, use that instead, even if they will email or print it. Do NOT use for PDFs, spreadsheets, Google Docs, or coding unrelated to document generation. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docx"]},{"name":"google-workspace","description":"Read this before the first Google Drive, Docs, Sheets or Slides connector call whenever the task creates or changes a Google file. Use this skill whenever the user wants to create or change a Google Doc, Sheet or Slides file in their Google Drive. Triggers include: a request that names Google Docs, Sheets, Slides or Drive and asks to make, edit, format, copy or rename a file; a docs.google.com link with a request to change that file, even a one-line fix or suggested edits; and any follow-up change to a Google file from earlier in the chat, even \"change it\" or \"add a tab\". Includes helper scripts for document positions, cell ranges and slide layout. However, if the user asks for a doc, deck or spreadsheet without naming Google, or gives a Google file only as source material for something new, use Claude's own output type instead. Do NOT use for read-only questions about a Google file, or for Word, Excel, PowerPoint or PDF files. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:google-workspace"]},{"name":"import-memory","description":"Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:import-memory"]},{"name":"morning","description":"Render the user's morning brief as a styled HTML artifact, or set it up as a recurring weekday task. Use only when the user explicitly asks to run, see, or set up their morning brief, or if they invoke /morning by name. A question about their day, schedule, or calendar is not by itself a request for the brief; answer it directly instead. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:morning"]},{"name":"pdf","description":"Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pdf"]},{"name":"pptx","description":"Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations as PowerPoint (.pptx) files; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email, summary, or creating a different type of slide deck); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user asks for a PowerPoint or .pptx file, or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. However, when the user asks for a deck, slides, a slide deck, or a presentation without naming a file format, default to using a dedicated slide-deck artifact type or a separate slides skill if this session offers one; otherwise, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pptx"]},{"name":"skill-creator","description":"Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:skill-creator"]},{"name":"xlsx","description":"Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:xlsx"]}],"agents":[{"name":"claude","description":"Catch-all for any task that doesn't fit a more specific agent. FleetView's default when no agent name is typed."},{"name":"claude-code-guide","description":"Use this agent when the user asks questions (\"Can Claude...\", \"Does Claude...\", \"How do I...\") about: (1) Claude Code (the CLI tool) - features, hooks, slash commands, MCP servers, settings, IDE integrations, keyboard shortcuts; (2) Claude Agent SDK - building custom agents; (3) Claude API (formerly Anthropic API) - Messages API for directly passing messages to Claude, Tool Runner (`client.beta.messages.tool_runner`) for running an agentic loop over your own tools, manual tool-use loops, Managed Agents for server-hosted agents with a managed sandbox, prompt caching, and general Anthropic SDK usage; (4) Claude Tag (Claude in Slack) - what it is, setting it up for a Slack workspace, `/install-slack-app`; (5) `claude plugin eval` (writing and running plugin eval suites, its JSON/report, sandbox, CI) and the `/skill-doctor` report. **IMPORTANT:** Before spawning a new agent, check if there is already a running or recently completed claude-code-guide agent that you can continue via SendMessage.","model":"haiku"},{"name":"Explore","description":"Fast read-only search agent for locating code. Use it to find files by pattern (eg. \"src/components/**/*.tsx\"), grep for symbols or keywords (eg. \"API endpoints\"), or answer \"where is X defined / which files reference Y.\" Do NOT use it for code review, design-doc auditing, cross-file consistency checks, or open-ended analysis — it reads excerpts rather than whole files and will miss content past its read window. When calling, specify search breadth: \"quick\" for a single targeted lookup, \"medium\" for moderate exploration, or \"very thorough\" to search across multiple locations and naming conventions.","model":"inherit"},{"name":"general-purpose","description":"General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you."},{"name":"Plan","description":"Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs.","model":"inherit"},{"name":"statusline-setup","description":"Use this agent to configure the user's Claude Code status line setting.","model":"sonnet"}],"output_style":"default","available_output_styles":["default","Proactive","Concise","Explanatory","Learning"],"user_output_styles_dir":"/Users/flamingcow/.claude/output-styles","models":[{"value":"default","resolvedModel":"claude-opus-5-5","displayName":"Default (recommended)","description":"Opus 5.5 · Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"opus","resolvedModel":"claude-opus-5-5","displayName":"Opus 5.5","description":"For complex work and everyday tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"fable","resolvedModel":"claude-fable-5-1","displayName":"Fable 5.1","description":"For your toughest challenges","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"sonnet","resolvedModel":"claude-sonnet-5-5","displayName":"Sonnet 5.5","description":"Most efficient for simpler tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"haiku","resolvedModel":"claude-haiku-5-5","displayName":"Haiku 5.5","description":"Fastest for quick answers","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-haiku-4-5-20251001","resolvedModel":"claude-haiku-4-5-20251001","displayName":"Haiku 4.5","description":"Fastest for quick answers"},{"value":"claude-sonnet-5","resolvedModel":"claude-sonnet-5","displayName":"Sonnet 5","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-5","resolvedModel":"claude-opus-5","displayName":"Opus 5","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-fable-5","resolvedModel":"claude-fable-5","displayName":"Fable 5","description":"Most capable for your hardest and longest-running tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-8","resolvedModel":"claude-opus-4-8","displayName":"Opus 4.8","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-opus-4-7","resolvedModel":"claude-opus-4-7","displayName":"Opus 4.7","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-6","resolvedModel":"claude-opus-4-6","displayName":"Opus 4.6","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-sonnet-4-6","resolvedModel":"claude-sonnet-4-6","displayName":"Sonnet 4.6","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true}],"account":{"email":"[redacted]","organization":"[redacted]'s Organization","subscriptionType":"Claude Max","apiProvider":"firstParty"},"pid":2401,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} {"dir":"send","msg":{"message":{"content":"Without using any tools, count from one to twenty in words, separated by spaces.","role":"user"},"parent_tool_use_id":null,"session_id":"","type":"user"}} -{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestTextDeltas4122698565/001","session_id":"3810dedc-a024-4c36-8e67-709b70a35ca1","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","LSP","Monitor","NotebookEdit","PushNotification","Read","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"pending","source":"claudeai"},{"name":"claude.ai Heliosian","status":"pending","source":"claudeai"},{"name":"claude.ai Fastmail","status":"pending","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"9518a43e-d524-445b-bf36-98778bc0b54e","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestTextDeltas4122698565-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestTextDeltas4122698565-001/3810dedc-a024-4c36-8e67-709b70a35ca1/scratchpad","messaging_socket_path":"/tmp/cc-socks/98362.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"3810dedc-a024-4c36-8e67-709b70a35ca1","uuid":"6e521520-557c-4e08-9f14-4264a9ebcf67"}} -{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.01,"resetsAt":1792054200},"seven_day":{"utilization":0.34,"resetsAt":1792270800}}},"uuid":"6ca939e1-49c7-4c92-89c7-0def6b066465","session_id":"3810dedc-a024-4c36-8e67-709b70a35ca1"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3MazUdfUdYYNqPGyMsW","type":"message","role":"assistant","content":[{"type":"text","text":"one two three four five six seven eight nine ten eleven twelve thirteen fourteen fifteen sixteen seventeen eighteen nineteen twenty"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15243,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15243},"output_tokens":2,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"3810dedc-a024-4c36-8e67-709b70a35ca1","uuid":"87c3e680-b78e-4869-9187-1676d99c86ae","timestamp":"2026-10-15T04:01:03.458Z","request_id":"req_011Cg3MazEjVz7knkKKpTZoZ"}} -{"dir":"recv","msg":{"duration_api_ms":2369,"stop_reason":"end_turn","session_id":"3810dedc-a024-4c36-8e67-709b70a35ca1","total_cost_usd":0.063871,"usage":{"input_tokens":2,"cache_creation_input_tokens":15243,"cache_read_input_tokens":22367,"output_tokens":53,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":15243,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":53,"cache_read_input_tokens":22367,"cache_creation_input_tokens":15243,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15243},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1188,"outputTokens":19,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.00012830000000000003,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":2,"outputTokens":53,"cacheReadInputTokens":22367,"cacheCreationInputTokens":15243,"webSearchRequests":0,"costUSD":0.0637427,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":1,"subtype":"success","api_error_status":null,"result":"one two three four five six seven eight nine ten eleven twelve thirteen fourteen fifteen sixteen seventeen eighteen nineteen twenty","ttft_ms":1816,"type":"result","duration_ms":1833,"uuid":"13a1f2b5-5a4c-4007-821d-3e7894e8e5a5","ttft_stream_ms":1103,"time_to_request_ms":28,"first_content_frame_ms":1104,"queued_turn_count":0,"result_index":0}} +{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestTextDeltas1176882613/001","session_id":"8d0b4a1b-7f58-4158-a26c-5c522cd26e93","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","LSP","Monitor","NotebookEdit","PushNotification","Read","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"pending","source":"claudeai"},{"name":"claude.ai Heliosian","status":"pending","source":"claudeai"},{"name":"claude.ai Fastmail","status":"pending","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"0878ac9e-4607-4cd7-9689-243a41d297ea","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestTextDeltas1176882613-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestTextDeltas1176882613-001/8d0b4a1b-7f58-4158-a26c-5c522cd26e93/scratchpad","messaging_socket_path":"/tmp/cc-socks/2401.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"8d0b4a1b-7f58-4158-a26c-5c522cd26e93","uuid":"897a08b5-48a4-4204-a505-ba6c19a56812"}} +{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.01,"resetsAt":1792054200},"seven_day":{"utilization":0.34,"resetsAt":1792270800}}},"uuid":"ec46b604-feb3-4c5d-b3d2-2768782c1e43","session_id":"8d0b4a1b-7f58-4158-a26c-5c522cd26e93"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3MyvNTnhRe9Dh8RnmnT","type":"message","role":"assistant","content":[{"type":"text","text":"one two three four five six seven eight nine ten eleven twelve thirteen fourteen fifteen sixteen seventeen eighteen nineteen twenty"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15248,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15248},"output_tokens":2,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"8d0b4a1b-7f58-4158-a26c-5c522cd26e93","uuid":"b2f41578-d0c2-4b41-8b75-019961e0292b","timestamp":"2026-10-15T04:06:14.654Z","request_id":"req_011Cg3Myv8ahmZJXmNmS5Vpm"}} +{"dir":"recv","msg":{"duration_api_ms":2536,"stop_reason":"end_turn","session_id":"8d0b4a1b-7f58-4158-a26c-5c522cd26e93","total_cost_usd":0.06389099999999999,"usage":{"input_tokens":2,"cache_creation_input_tokens":15248,"cache_read_input_tokens":22367,"output_tokens":53,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":15248,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":53,"cache_read_input_tokens":22367,"cache_creation_input_tokens":15248,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15248},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1188,"outputTokens":19,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.00012830000000000003,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":2,"outputTokens":53,"cacheReadInputTokens":22367,"cacheCreationInputTokens":15248,"webSearchRequests":0,"costUSD":0.06376269999999999,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":1,"subtype":"success","api_error_status":null,"result":"one two three four five six seven eight nine ten eleven twelve thirteen fourteen fifteen sixteen seventeen eighteen nineteen twenty","ttft_ms":1970,"type":"result","duration_ms":1995,"uuid":"a99821cc-2af3-4f7f-92ab-8edadf5299be","ttft_stream_ms":1368,"time_to_request_ms":28,"first_content_frame_ms":1368,"queued_turn_count":0,"result_index":0}} diff --git a/internal/server/server.go b/internal/server/server.go index acdc681..350d3d9 100644 --- a/internal/server/server.go +++ b/internal/server/server.go @@ -391,6 +391,7 @@ func (s *Server) GetStatus(w http.ResponseWriter, r *http.Request) { LiveAgents: s.agents.LiveCount(), RunningTurns: usage.Running, QueuedTurns: usage.Queued, + Caps: usage.Caps, RateLimits: usage.RateLimits, }) } diff --git a/internal/store/queue.go b/internal/store/queue.go index a612cc8..a18b214 100644 --- a/internal/store/queue.go +++ b/internal/store/queue.go @@ -12,6 +12,7 @@ import ( type QueuedTurn struct { SessionID string + TaskID string Vendor api.AgentSessionVendor Actor string Text string @@ -59,7 +60,7 @@ func (s *Store) EnqueueTurn(ctx context.Context, q QueuedTurn) error { func (s *Store) QueuedTurns(ctx context.Context) ([]QueuedTurn, error) { rows, err := s.db.QueryContext(ctx, ` - SELECT q.session_id, s.vendor, q.actor, q.text, q.images, q.created_at + SELECT q.session_id, s.task_id, s.vendor, q.actor, q.text, q.images, q.created_at FROM turn_queue q JOIN agent_sessions s ON s.id = q.session_id ORDER BY q.created_at `) @@ -74,7 +75,7 @@ func (s *Store) QueuedTurns(ctx context.Context) ([]QueuedTurn, error) { vendor := "" images := "" createdAt := "" - err = rows.Scan(&q.SessionID, &vendor, &q.Actor, &q.Text, &images, &createdAt) + err = rows.Scan(&q.SessionID, &q.TaskID, &vendor, &q.Actor, &q.Text, &images, &createdAt) if err != nil { return nil, err } diff --git a/web/dist/admin.js b/web/dist/admin.js new file mode 100644 index 0000000..ab2ae02 --- /dev/null +++ b/web/dist/admin.js @@ -0,0 +1,144 @@ +import { get } from "./api.js"; +import { ago, errorText, h, replace } from "./dom.js"; +import { findTask, on, onEach, state } from "./state.js"; +const refreshKinds = new Set(["session.created", "session.state", "task.created", "task.merged", "task.discarded", "project.created"]); +export function mountAdmin(root) { + let status; + let error = ""; + let inFlight = false; + let again = false; + let disposed = false; + const render = () => { + if (!status) { + replace(root, h("div", { class: error ? "empty error-text" : "empty" }, error || "Loading…")); + return; + } + replace(root, h("div", { class: "admin-view" }, error && h("p", { class: "error-text" }, error), turnsSection(status), rateLimitsSection(status.rate_limits), serverSection(status))); + }; + const refresh = async () => { + if (inFlight) { + again = true; + return; + } + inFlight = true; + try { + const next = await get("/api/admin/status"); + if (disposed) { + return; + } + status = next; + error = ""; + } + catch (err) { + error = `Couldn't load status: ${errorText(err)}`; + } + inFlight = false; + render(); + if (again && !disposed) { + again = false; + void refresh(); + } + }; + const onEvent = (detail) => { + const ev = detail; + if (refreshKinds.has(ev.kind) || (ev.kind === "agent.vendor" && ev.payload["type"] === "rate_limit_event")) { + void refresh(); + return; + } + if (status && ev.seq > status.last_event_seq) { + status.last_event_seq = ev.seq; + render(); + } + }; + const offs = [ + on("event", onEvent), + on("connection", () => { + if (state.connected) { + void refresh(); + } + }), + onEach(["projects", "tasks"], render), + ]; + render(); + void refresh(); + return () => { + disposed = true; + for (const off of offs) { + off(); + } + }; +} +function turnsSection(s) { + const vendors = [...new Set([...Object.keys(s.caps.per_vendor), ...s.running_turns.map((t) => t.vendor), ...s.queued_turns.map((t) => t.vendor)])].sort(); + const runningFor = (vendor) => s.running_turns.filter((t) => t.vendor === vendor).length; + return h("section", { class: "admin-section" }, h("h2", {}, "Turns"), h("div", { class: "caps" }, capTile("All vendors", s.running_turns.length, s.caps.global), ...vendors.map((v) => capTile(v, runningFor(v), s.caps.per_vendor[v])), h("div", { class: "cap-tile" }, h("div", { class: "cap-label" }, "Queued"), h("div", { class: s.queued_turns.length > 0 ? "cap-value warn" : "cap-value" }, s.queued_turns.length))), h("h3", {}, "Running"), turnList(s.running_turns, "running", "No turns running."), h("h3", {}, "Queued"), turnList(s.queued_turns, "queued", "Nothing queued.")); +} +function capTile(label, running, cap) { + const full = cap !== undefined && running >= cap; + return h("div", { class: "cap-tile" }, h("div", { class: "cap-label" }, label), h("div", { class: full ? "cap-value warn" : "cap-value" }, running, h("span", { class: "cap-max" }, cap === undefined ? " / no cap" : ` / ${cap}`))); +} +function turnList(turns, kind, empty) { + return h("ul", { class: "task-list" }, ...turns.map((t, i) => { + const task = findTask(t.task_id); + const project = task ? state.projects.find((p) => p.id === task.project_id) : undefined; + return h("li", {}, h("a", { href: `#/task/${t.task_id}` }, kind === "queued" ? h("span", { class: "queue-pos" }, `${i + 1}.`) : h("span", { class: "dot running", title: "running" }), h("span", { class: "task-title" }, project && h("span", { class: "project-name" }, `${project.name} ▸ `), task?.title ?? t.task_id), h("span", { class: "task-state" }, t.vendor))); + }), turns.length === 0 && h("li", { class: "empty-row" }, empty)); +} +function rateLimitsSection(limits) { + const vendors = Object.keys(limits).sort(); + return h("section", { class: "admin-section" }, h("h2", {}, "Rate limits"), ...vendors.map((v) => rateLimitCard(v, limits[v] ?? {})), vendors.length === 0 && h("p", { class: "hint" }, "No vendor has reported a rate-limit status since byre started.")); +} +function rateLimitCard(vendor, info) { + const { status, rateLimitType, resetsAt, unifiedWindows, ...rest } = info; + const statusText = String(status ?? "unknown"); + const tone = statusText === "allowed" ? "ok" : statusText === "rejected" ? "danger" : "warn"; + const windows = (unifiedWindows ?? {}); + return h("div", { class: "card rate-limit" }, h("header", {}, h("span", { class: "vendor" }, vendor), h("span", { class: `rl-status ${tone}` }, statusText), rateLimitType !== undefined && h("span", {}, String(rateLimitType)), typeof resetsAt === "number" && h("span", { class: "resets" }, "resets ", resetText(resetsAt))), Object.keys(windows).length > 0 && + h("table", { class: "rl-windows" }, h("tr", {}, h("th", {}, "Window"), h("th", {}, "Used"), h("th", {}, "Resets")), ...Object.entries(windows).map(([name, w]) => h("tr", {}, h("td", {}, name), h("td", { class: utilizationClass(w.utilization) }, w.utilization === undefined ? "—" : `${Math.round(w.utilization * 100)}%`), h("td", {}, w.resetsAt === undefined ? "—" : resetText(w.resetsAt))))), Object.keys(rest).length > 0 && + h("dl", { class: "kv" }, ...Object.entries(rest).flatMap(([k, v]) => [h("dt", {}, k), h("dd", {}, typeof v === "object" ? JSON.stringify(v) : String(v))]))); +} +function utilizationClass(u) { + if (u === undefined) { + return ""; + } + if (u >= 0.9) { + return "danger"; + } + if (u >= 0.7) { + return "warn"; + } + return ""; +} +function resetText(unixSeconds) { + const at = new Date(unixSeconds * 1000); + const time = at.toLocaleString(undefined, { weekday: "short", hour: "numeric", minute: "2-digit" }); + const minutes = Math.round((at.getTime() - Date.now()) / 60000); + if (minutes <= 0) { + return `${time} (passed)`; + } + const rel = minutes < 60 ? `${minutes}m` : minutes < 1440 ? `${Math.floor(minutes / 60)}h ${minutes % 60}m` : `${Math.floor(minutes / 1440)}d ${Math.floor((minutes % 1440) / 60)}h`; + return `${time} (in ${rel})`; +} +function serverSection(s) { + const rows = [ + ["Started", `${new Date(s.started_at).toLocaleString()} (${ago(s.started_at)})`], + ["Agent processes", String(s.live_agents)], + ["Projects", String(s.projects)], + ["Active tasks", String(s.active_tasks)], + ["Live clients", String(s.sse_clients)], + ["Database", bytes(s.db_bytes)], + ["Last event", `#${s.last_event_seq}`], + ]; + return h("section", { class: "admin-section" }, h("h2", {}, "Server"), h("dl", { class: "kv" }, ...rows.flatMap(([k, v]) => [h("dt", {}, k), h("dd", {}, v)]))); +} +function bytes(n) { + const units = ["B", "KB", "MB", "GB", "TB"]; + let i = 0; + let v = n; + while (v >= 1024 && i < units.length - 1) { + v /= 1024; + i++; + } + return `${v.toFixed(i === 0 ? 0 : 1)} ${units[i]}`; +} +//# sourceMappingURL=admin.js.map \ No newline at end of file diff --git a/web/dist/admin.js.map b/web/dist/admin.js.map new file mode 100644 index 0000000..df6af72 --- /dev/null +++ b/web/dist/admin.js.map @@ -0,0 +1 @@ +{"version":3,"file":"admin.js","sourceRoot":"","sources":["../src/admin.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,GAAG,EAA6C,MAAM,UAAU,CAAC;AAC1E,OAAO,EAAE,GAAG,EAAE,SAAS,EAAE,CAAC,EAAE,OAAO,EAAE,MAAM,UAAU,CAAC;AACtD,OAAO,EAAE,QAAQ,EAAE,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,YAAY,CAAC;AAEzD,MAAM,YAAY,GAAG,IAAI,GAAG,CAAC,CAAC,iBAAiB,EAAE,eAAe,EAAE,cAAc,EAAE,aAAa,EAAE,gBAAgB,EAAE,iBAAiB,CAAC,CAAC,CAAC;AAEvI,MAAM,UAAU,UAAU,CAAC,IAAiB;IAC1C,IAAI,MAA0B,CAAC;IAC/B,IAAI,KAAK,GAAG,EAAE,CAAC;IACf,IAAI,QAAQ,GAAG,KAAK,CAAC;IACrB,IAAI,KAAK,GAAG,KAAK,CAAC;IAClB,IAAI,QAAQ,GAAG,KAAK,CAAC;IAErB,MAAM,MAAM,GAAG,GAAG,EAAE;QAClB,IAAI,CAAC,MAAM,EAAE,CAAC;YACZ,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,KAAK,CAAC,CAAC,CAAC,kBAAkB,CAAC,CAAC,CAAC,OAAO,EAAE,EAAE,KAAK,IAAI,UAAU,CAAC,CAAC,CAAC;YAC9F,OAAO;QACT,CAAC;QACD,OAAO,CACL,IAAI,EACJ,CAAC,CACC,KAAK,EACL,EAAE,KAAK,EAAE,YAAY,EAAE,EACvB,KAAK,IAAI,CAAC,CAAC,GAAG,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,KAAK,CAAC,EAC/C,YAAY,CAAC,MAAM,CAAC,EACpB,iBAAiB,CAAC,MAAM,CAAC,WAAW,CAAC,EACrC,aAAa,CAAC,MAAM,CAAC,CACtB,CACF,CAAC;IACJ,CAAC,CAAC;IAEF,MAAM,OAAO,GAAG,KAAK,IAAI,EAAE;QACzB,IAAI,QAAQ,EAAE,CAAC;YACb,KAAK,GAAG,IAAI,CAAC;YACb,OAAO;QACT,CAAC;QACD,QAAQ,GAAG,IAAI,CAAC;QAChB,IAAI,CAAC;YACH,MAAM,IAAI,GAAG,MAAM,GAAG,CAAC,mBAAmB,CAAC,CAAC;YAC5C,IAAI,QAAQ,EAAE,CAAC;gBACb,OAAO;YACT,CAAC;YACD,MAAM,GAAG,IAAI,CAAC;YACd,KAAK,GAAG,EAAE,CAAC;QACb,CAAC;QAAC,OAAO,GAAG,EAAE,CAAC;YACb,KAAK,GAAG,yBAAyB,SAAS,CAAC,GAAG,CAAC,EAAE,CAAC;QACpD,CAAC;QACD,QAAQ,GAAG,KAAK,CAAC;QACjB,MAAM,EAAE,CAAC;QACT,IAAI,KAAK,IAAI,CAAC,QAAQ,EAAE,CAAC;YACvB,KAAK,GAAG,KAAK,CAAC;YACd,KAAK,OAAO,EAAE,CAAC;QACjB,CAAC;IACH,CAAC,CAAC;IAEF,MAAM,OAAO,GAAG,CAAC,MAAgB,EAAE,EAAE;QACnC,MAAM,EAAE,GAAG,MAAmB,CAAC;QAC/B,IAAI,YAAY,CAAC,GAAG,CAAC,EAAE,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,IAAI,KAAK,cAAc,IAAI,EAAE,CAAC,OAAO,CAAC,MAAM,CAAC,KAAK,kBAAkB,CAAC,EAAE,CAAC;YAC3G,KAAK,OAAO,EAAE,CAAC;YACf,OAAO;QACT,CAAC;QACD,IAAI,MAAM,IAAI,EAAE,CAAC,GAAG,GAAG,MAAM,CAAC,cAAc,EAAE,CAAC;YAC7C,MAAM,CAAC,cAAc,GAAG,EAAE,CAAC,GAAG,CAAC;YAC/B,MAAM,EAAE,CAAC;QACX,CAAC;IACH,CAAC,CAAC;IAEF,MAAM,IAAI,GAAG;QACX,EAAE,CAAC,OAAO,EAAE,OAAO,CAAC;QACpB,EAAE,CAAC,YAAY,EAAE,GAAG,EAAE;YACpB,IAAI,KAAK,CAAC,SAAS,EAAE,CAAC;gBACpB,KAAK,OAAO,EAAE,CAAC;YACjB,CAAC;QACH,CAAC,CAAC;QACF,MAAM,CAAC,CAAC,UAAU,EAAE,OAAO,CAAC,EAAE,MAAM,CAAC;KACtC,CAAC;IAEF,MAAM,EAAE,CAAC;IACT,KAAK,OAAO,EAAE,CAAC;IAEf,OAAO,GAAG,EAAE;QACV,QAAQ,GAAG,IAAI,CAAC;QAChB,KAAK,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;YACvB,GAAG,EAAE,CAAC;QACR,CAAC;IACH,CAAC,CAAC;AACJ,CAAC;AAED,SAAS,YAAY,CAAC,CAAS;IAC7B,MAAM,OAAO,GAAG,CAAC,GAAG,IAAI,GAAG,CAAC,CAAC,GAAG,MAAM,CAAC,IAAI,CAAC,CAAC,CAAC,IAAI,CAAC,UAAU,CAAC,EAAE,GAAG,CAAC,CAAC,aAAa,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,CAAC,EAAE,GAAG,CAAC,CAAC,YAAY,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;IAC1J,MAAM,UAAU,GAAG,CAAC,MAAc,EAAE,EAAE,CAAC,CAAC,CAAC,aAAa,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,KAAK,MAAM,CAAC,CAAC,MAAM,CAAC;IAEjG,OAAO,CAAC,CACN,SAAS,EACT,EAAE,KAAK,EAAE,eAAe,EAAE,EAC1B,CAAC,CAAC,IAAI,EAAE,EAAE,EAAE,OAAO,CAAC,EACpB,CAAC,CACC,KAAK,EACL,EAAE,KAAK,EAAE,MAAM,EAAE,EACjB,OAAO,CAAC,aAAa,EAAE,CAAC,CAAC,aAAa,CAAC,MAAM,EAAE,CAAC,CAAC,IAAI,CAAC,MAAM,CAAC,EAC7D,GAAG,OAAO,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,OAAO,CAAC,CAAC,EAAE,UAAU,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,CAAC,EACtE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,UAAU,EAAE,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,EAAE,QAAQ,CAAC,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,CAAC,CAAC,YAAY,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC,gBAAgB,CAAC,CAAC,CAAC,WAAW,EAAE,EAAE,CAAC,CAAC,YAAY,CAAC,MAAM,CAAC,CAAC,CACpL,EACD,CAAC,CAAC,IAAI,EAAE,EAAE,EAAE,SAAS,CAAC,EACtB,QAAQ,CAAC,CAAC,CAAC,aAAa,EAAE,SAAS,EAAE,mBAAmB,CAAC,EACzD,CAAC,CAAC,IAAI,EAAE,EAAE,EAAE,QAAQ,CAAC,EACrB,QAAQ,CAAC,CAAC,CAAC,YAAY,EAAE,QAAQ,EAAE,iBAAiB,CAAC,CACtD,CAAC;AACJ,CAAC;AAED,SAAS,OAAO,CAAC,KAAa,EAAE,OAAe,EAAE,GAAuB;IACtE,MAAM,IAAI,GAAG,GAAG,KAAK,SAAS,IAAI,OAAO,IAAI,GAAG,CAAC;IACjD,OAAO,CAAC,CACN,KAAK,EACL,EAAE,KAAK,EAAE,UAAU,EAAE,EACrB,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,EAAE,KAAK,CAAC,EACvC,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,IAAI,CAAC,CAAC,CAAC,gBAAgB,CAAC,CAAC,CAAC,WAAW,EAAE,EAAE,OAAO,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,SAAS,EAAE,EAAE,GAAG,KAAK,SAAS,CAAC,CAAC,CAAC,WAAW,CAAC,CAAC,CAAC,MAAM,GAAG,EAAE,CAAC,CAAC,CACpJ,CAAC;AACJ,CAAC;AAED,SAAS,QAAQ,CAAC,KAAgB,EAAE,IAA0B,EAAE,KAAa;IAC3E,OAAO,CAAC,CACN,IAAI,EACJ,EAAE,KAAK,EAAE,WAAW,EAAE,EACtB,GAAG,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE;QACpB,MAAM,IAAI,GAAG,QAAQ,CAAC,CAAC,CAAC,OAAO,CAAC,CAAC;QACjC,MAAM,OAAO,GAAG,IAAI,CAAC,CAAC,CAAC,KAAK,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,EAAE,KAAK,IAAI,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;QACxF,OAAO,CAAC,CACN,IAAI,EACJ,EAAE,EACF,CAAC,CACC,GAAG,EACH,EAAE,IAAI,EAAE,UAAU,CAAC,CAAC,OAAO,EAAE,EAAE,EAC/B,IAAI,KAAK,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,EAAE,GAAG,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,aAAa,EAAE,KAAK,EAAE,SAAS,EAAE,CAAC,EAC1H,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,OAAO,IAAI,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,cAAc,EAAE,EAAE,GAAG,OAAO,CAAC,IAAI,KAAK,CAAC,EAAE,IAAI,EAAE,KAAK,IAAI,CAAC,CAAC,OAAO,CAAC,EACnI,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,CAAC,CAAC,MAAM,CAAC,CAC7C,CACF,CAAC;IACJ,CAAC,CAAC,EACF,KAAK,CAAC,MAAM,KAAK,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,EAAE,KAAK,CAAC,CAC7D,CAAC;AACJ,CAAC;AAED,SAAS,iBAAiB,CAAC,MAA6B;IACtD,MAAM,OAAO,GAAG,MAAM,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,CAAC;IAC3C,OAAO,CAAC,CACN,SAAS,EACT,EAAE,KAAK,EAAE,eAAe,EAAE,EAC1B,CAAC,CAAC,IAAI,EAAE,EAAE,EAAE,aAAa,CAAC,EAC1B,GAAG,OAAO,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,aAAa,CAAC,CAAC,EAAE,MAAM,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,EACxD,OAAO,CAAC,MAAM,KAAK,CAAC,IAAI,CAAC,CAAC,GAAG,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,gEAAgE,CAAC,CACpH,CAAC;AACJ,CAAC;AAED,SAAS,aAAa,CAAC,MAAc,EAAE,IAA6B;IAClE,MAAM,EAAE,MAAM,EAAE,aAAa,EAAE,QAAQ,EAAE,cAAc,EAAE,GAAG,IAAI,EAAE,GAAG,IAAI,CAAC;IAC1E,MAAM,UAAU,GAAG,MAAM,CAAC,MAAM,IAAI,SAAS,CAAC,CAAC;IAC/C,MAAM,IAAI,GAAG,UAAU,KAAK,SAAS,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,UAAU,KAAK,UAAU,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,MAAM,CAAC;IAC7F,MAAM,OAAO,GAAG,CAAC,cAAc,IAAI,EAAE,CAAgE,CAAC;IAEtG,OAAO,CAAC,CACN,KAAK,EACL,EAAE,KAAK,EAAE,iBAAiB,EAAE,EAC5B,CAAC,CACC,QAAQ,EACR,EAAE,EACF,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,QAAQ,EAAE,EAAE,MAAM,CAAC,EACtC,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,aAAa,IAAI,EAAE,EAAE,EAAE,UAAU,CAAC,EACrD,aAAa,KAAK,SAAS,IAAI,CAAC,CAAC,MAAM,EAAE,EAAE,EAAE,MAAM,CAAC,aAAa,CAAC,CAAC,EACnE,OAAO,QAAQ,KAAK,QAAQ,IAAI,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,QAAQ,EAAE,EAAE,SAAS,EAAE,SAAS,CAAC,QAAQ,CAAC,CAAC,CAC/F,EACD,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC,MAAM,GAAG,CAAC;QAC7B,CAAC,CACC,OAAO,EACP,EAAE,KAAK,EAAE,YAAY,EAAE,EACvB,CAAC,CAAC,IAAI,EAAE,EAAE,EAAE,CAAC,CAAC,IAAI,EAAE,EAAE,EAAE,QAAQ,CAAC,EAAE,CAAC,CAAC,IAAI,EAAE,EAAE,EAAE,MAAM,CAAC,EAAE,CAAC,CAAC,IAAI,EAAE,EAAE,EAAE,QAAQ,CAAC,CAAC,EAC9E,GAAG,MAAM,CAAC,OAAO,CAAC,OAAO,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,EAAE,EAAE,CAC3C,CAAC,CACC,IAAI,EACJ,EAAE,EACF,CAAC,CAAC,IAAI,EAAE,EAAE,EAAE,IAAI,CAAC,EACjB,CAAC,CAAC,IAAI,EAAE,EAAE,KAAK,EAAE,gBAAgB,CAAC,CAAC,CAAC,WAAW,CAAC,EAAE,EAAE,CAAC,CAAC,WAAW,KAAK,SAAS,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC,CAAC,WAAW,GAAG,GAAG,CAAC,GAAG,CAAC,EAC9H,CAAC,CAAC,IAAI,EAAE,EAAE,EAAE,CAAC,CAAC,QAAQ,KAAK,SAAS,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CACpE,CACF,CACF,EACH,MAAM,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,MAAM,GAAG,CAAC;QAC1B,CAAC,CACC,IAAI,EACJ,EAAE,KAAK,EAAE,IAAI,EAAE,EACf,GAAG,MAAM,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE,EAAE,EAAE,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,EAAE,EAAE,EAAE,OAAO,CAAC,KAAK,QAAQ,CAAC,CAAC,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAClI,CACJ,CAAC;AACJ,CAAC;AAED,SAAS,gBAAgB,CAAC,CAAqB;IAC7C,IAAI,CAAC,KAAK,SAAS,EAAE,CAAC;QACpB,OAAO,EAAE,CAAC;IACZ,CAAC;IACD,IAAI,CAAC,IAAI,GAAG,EAAE,CAAC;QACb,OAAO,QAAQ,CAAC;IAClB,CAAC;IACD,IAAI,CAAC,IAAI,GAAG,EAAE,CAAC;QACb,OAAO,MAAM,CAAC;IAChB,CAAC;IACD,OAAO,EAAE,CAAC;AACZ,CAAC;AAED,SAAS,SAAS,CAAC,WAAmB;IACpC,MAAM,EAAE,GAAG,IAAI,IAAI,CAAC,WAAW,GAAG,IAAI,CAAC,CAAC;IACxC,MAAM,IAAI,GAAG,EAAE,CAAC,cAAc,CAAC,SAAS,EAAE,EAAE,OAAO,EAAE,OAAO,EAAE,IAAI,EAAE,SAAS,EAAE,MAAM,EAAE,SAAS,EAAE,CAAC,CAAC;IACpG,MAAM,OAAO,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,OAAO,EAAE,GAAG,IAAI,CAAC,GAAG,EAAE,CAAC,GAAG,KAAK,CAAC,CAAC;IAChE,IAAI,OAAO,IAAI,CAAC,EAAE,CAAC;QACjB,OAAO,GAAG,IAAI,WAAW,CAAC;IAC5B,CAAC;IACD,MAAM,GAAG,GAAG,OAAO,GAAG,EAAE,CAAC,CAAC,CAAC,GAAG,OAAO,GAAG,CAAC,CAAC,CAAC,OAAO,GAAG,IAAI,CAAC,CAAC,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,OAAO,GAAG,EAAE,CAAC,KAAK,OAAO,GAAG,EAAE,GAAG,CAAC,CAAC,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,OAAO,GAAG,IAAI,CAAC,KAAK,IAAI,CAAC,KAAK,CAAC,CAAC,OAAO,GAAG,IAAI,CAAC,GAAG,EAAE,CAAC,GAAG,CAAC;IACrL,OAAO,GAAG,IAAI,QAAQ,GAAG,GAAG,CAAC;AAC/B,CAAC;AAED,SAAS,aAAa,CAAC,CAAS;IAC9B,MAAM,IAAI,GAAuB;QAC/B,CAAC,SAAS,EAAE,GAAG,IAAI,IAAI,CAAC,CAAC,CAAC,UAAU,CAAC,CAAC,cAAc,EAAE,KAAK,GAAG,CAAC,CAAC,CAAC,UAAU,CAAC,GAAG,CAAC;QAChF,CAAC,iBAAiB,EAAE,MAAM,CAAC,CAAC,CAAC,WAAW,CAAC,CAAC;QAC1C,CAAC,UAAU,EAAE,MAAM,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC;QAChC,CAAC,cAAc,EAAE,MAAM,CAAC,CAAC,CAAC,YAAY,CAAC,CAAC;QACxC,CAAC,cAAc,EAAE,MAAM,CAAC,CAAC,CAAC,WAAW,CAAC,CAAC;QACvC,CAAC,UAAU,EAAE,KAAK,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC;QAC/B,CAAC,YAAY,EAAE,IAAI,CAAC,CAAC,cAAc,EAAE,CAAC;KACvC,CAAC;IACF,OAAO,CAAC,CAAC,SAAS,EAAE,EAAE,KAAK,EAAE,eAAe,EAAE,EAAE,CAAC,CAAC,IAAI,EAAE,EAAE,EAAE,QAAQ,CAAC,EAAE,CAAC,CAAC,IAAI,EAAE,EAAE,KAAK,EAAE,IAAI,EAAE,EAAE,GAAG,IAAI,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE,EAAE,EAAE,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,EAAE,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC;AAClK,CAAC;AAED,SAAS,KAAK,CAAC,CAAS;IACtB,MAAM,KAAK,GAAG,CAAC,GAAG,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,CAAC,CAAC;IAC5C,IAAI,CAAC,GAAG,CAAC,CAAC;IACV,IAAI,CAAC,GAAG,CAAC,CAAC;IACV,OAAO,CAAC,IAAI,IAAI,IAAI,CAAC,GAAG,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QACzC,CAAC,IAAI,IAAI,CAAC;QACV,CAAC,EAAE,CAAC;IACN,CAAC;IACD,OAAO,GAAG,CAAC,CAAC,OAAO,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI,KAAK,CAAC,CAAC,CAAC,EAAE,CAAC;AACrD,CAAC"} \ No newline at end of file diff --git a/web/dist/api.js.map b/web/dist/api.js.map index 81b3546..8a4a4a7 100644 --- a/web/dist/api.js.map +++ b/web/dist/api.js.map @@ -1 +1 @@ -{"version":3,"file":"api.js","sourceRoot":"","sources":["../src/api.ts"],"names":[],"mappings":"AAuCA,MAAM,OAAO,QAAS,SAAQ,KAAK;IACZ;IAArB,YAAqB,MAAc,EAAE,OAAe;QAClD,KAAK,CAAC,OAAO,CAAC,CAAC;QADI,WAAM,GAAN,MAAM,CAAQ;IAEnC,CAAC;CACF;AAED,MAAM,CAAC,KAAK,UAAU,OAAO,CAC3B,MAAS,EACT,IAAO,EACP,OAA0B,EAAE;IAE5B,MAAM,UAAU,GAAG,CAAC,IAAI,CAAC,IAAI,IAAI,EAAE,CAA4B,CAAC;IAChE,IAAI,GAAG,GAAW,IAAI,CAAC,OAAO,CAAC,YAAY,EAAE,CAAC,CAAC,EAAE,GAAW,EAAE,EAAE;QAC9D,MAAM,KAAK,GAAG,UAAU,CAAC,GAAG,CAAC,CAAC;QAC9B,IAAI,KAAK,KAAK,SAAS,EAAE,CAAC;YACxB,MAAM,IAAI,KAAK,CAAC,0BAA0B,GAAG,QAAQ,IAAI,EAAE,CAAC,CAAC;QAC/D,CAAC;QACD,OAAO,kBAAkB,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC;IAC3C,CAAC,CAAC,CAAC;IAEH,MAAM,KAAK,GAAG,IAAI,eAAe,EAAE,CAAC;IACpC,KAAK,MAAM,CAAC,GAAG,EAAE,KAAK,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,CAAC,IAAI,CAAC,KAAK,IAAI,EAAE,CAA4B,CAAC,EAAE,CAAC;QACzF,IAAI,KAAK,KAAK,SAAS,EAAE,CAAC;YACxB,KAAK,CAAC,GAAG,CAAC,GAAG,EAAE,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC;QAChC,CAAC;IACH,CAAC;IACD,IAAI,KAAK,CAAC,IAAI,GAAG,CAAC,EAAE,CAAC;QACnB,GAAG,IAAI,IAAI,KAAK,EAAE,CAAC;IACrB,CAAC;IAED,MAAM,IAAI,GAAgB,EAAE,MAAM,EAAE,MAAM,CAAC,WAAW,EAAE,EAAE,CAAC;IAC3D,IAAI,IAAI,CAAC,IAAI,YAAY,IAAI,EAAE,CAAC;QAC9B,IAAI,CAAC,OAAO,GAAG,EAAE,cAAc,EAAE,IAAI,CAAC,IAAI,CAAC,IAAI,IAAI,0BAA0B,EAAE,CAAC;QAChF,IAAI,CAAC,IAAI,GAAG,IAAI,CAAC,IAAI,CAAC;IACxB,CAAC;SAAM,IAAI,IAAI,CAAC,IAAI,KAAK,SAAS,EAAE,CAAC;QACnC,IAAI,CAAC,OAAO,GAAG,EAAE,cAAc,EAAE,kBAAkB,EAAE,CAAC;QACtD,IAAI,CAAC,IAAI,GAAG,IAAI,CAAC,SAAS,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IACxC,CAAC;IAED,MAAM,GAAG,GAAG,MAAM,KAAK,CAAC,GAAG,EAAE,IAAI,CAAC,CAAC;IACnC,MAAM,IAAI,GAAG,MAAM,GAAG,CAAC,IAAI,EAAE,CAAC;IAC9B,IAAI,CAAC,GAAG,CAAC,EAAE,EAAE,CAAC;QACZ,MAAM,IAAI,QAAQ,CAAC,GAAG,CAAC,MAAM,EAAG,IAAyB,CAAC,OAAO,CAAC,CAAC;IACrE,CAAC;IACD,OAAO,IAAwB,CAAC;AAClC,CAAC;AAED,MAAM,CAAC,MAAM,GAAG,GAAG,CAA6B,IAAO,EAAE,IAA4B,EAAE,EAAE,CAAC,OAAO,CAAC,KAAK,EAAE,IAAI,EAAE,IAAI,CAAC,CAAC;AACrH,MAAM,CAAC,MAAM,IAAI,GAAG,CAA8B,IAAO,EAAE,IAA6B,EAAE,EAAE,CAAC,OAAO,CAAC,MAAM,EAAE,IAAI,EAAE,IAAI,CAAC,CAAC;AACzH,MAAM,CAAC,MAAM,GAAG,GAAG,CAA6B,IAAO,EAAE,IAA4B,EAAE,EAAE,CAAC,OAAO,CAAC,KAAK,EAAE,IAAI,EAAE,IAAI,CAAC,CAAC;AAErH,MAAM,UAAU,SAAS,CAAC,KAAa,EAAE,OAAgC,EAAE,OAAqC;IAC9G,MAAM,MAAM,GAAG,IAAI,WAAW,CAAC,qBAAqB,KAAK,EAAE,CAAC,CAAC;IAC7D,MAAM,CAAC,MAAM,GAAG,GAAG,EAAE,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC;IACpC,MAAM,CAAC,OAAO,GAAG,GAAG,EAAE,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC;IACtC,MAAM,CAAC,SAAS,GAAG,CAAC,GAAyB,EAAE,EAAE,CAAC,OAAO,CAAC,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,IAAI,CAAc,CAAC,CAAC;IAC7F,OAAO,MAAM,CAAC;AAChB,CAAC"} \ No newline at end of file +{"version":3,"file":"api.js","sourceRoot":"","sources":["../src/api.ts"],"names":[],"mappings":"AAwCA,MAAM,OAAO,QAAS,SAAQ,KAAK;IACZ;IAArB,YAAqB,MAAc,EAAE,OAAe;QAClD,KAAK,CAAC,OAAO,CAAC,CAAC;QADI,WAAM,GAAN,MAAM,CAAQ;IAEnC,CAAC;CACF;AAED,MAAM,CAAC,KAAK,UAAU,OAAO,CAC3B,MAAS,EACT,IAAO,EACP,OAA0B,EAAE;IAE5B,MAAM,UAAU,GAAG,CAAC,IAAI,CAAC,IAAI,IAAI,EAAE,CAA4B,CAAC;IAChE,IAAI,GAAG,GAAW,IAAI,CAAC,OAAO,CAAC,YAAY,EAAE,CAAC,CAAC,EAAE,GAAW,EAAE,EAAE;QAC9D,MAAM,KAAK,GAAG,UAAU,CAAC,GAAG,CAAC,CAAC;QAC9B,IAAI,KAAK,KAAK,SAAS,EAAE,CAAC;YACxB,MAAM,IAAI,KAAK,CAAC,0BAA0B,GAAG,QAAQ,IAAI,EAAE,CAAC,CAAC;QAC/D,CAAC;QACD,OAAO,kBAAkB,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC;IAC3C,CAAC,CAAC,CAAC;IAEH,MAAM,KAAK,GAAG,IAAI,eAAe,EAAE,CAAC;IACpC,KAAK,MAAM,CAAC,GAAG,EAAE,KAAK,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,CAAC,IAAI,CAAC,KAAK,IAAI,EAAE,CAA4B,CAAC,EAAE,CAAC;QACzF,IAAI,KAAK,KAAK,SAAS,EAAE,CAAC;YACxB,KAAK,CAAC,GAAG,CAAC,GAAG,EAAE,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC;QAChC,CAAC;IACH,CAAC;IACD,IAAI,KAAK,CAAC,IAAI,GAAG,CAAC,EAAE,CAAC;QACnB,GAAG,IAAI,IAAI,KAAK,EAAE,CAAC;IACrB,CAAC;IAED,MAAM,IAAI,GAAgB,EAAE,MAAM,EAAE,MAAM,CAAC,WAAW,EAAE,EAAE,CAAC;IAC3D,IAAI,IAAI,CAAC,IAAI,YAAY,IAAI,EAAE,CAAC;QAC9B,IAAI,CAAC,OAAO,GAAG,EAAE,cAAc,EAAE,IAAI,CAAC,IAAI,CAAC,IAAI,IAAI,0BAA0B,EAAE,CAAC;QAChF,IAAI,CAAC,IAAI,GAAG,IAAI,CAAC,IAAI,CAAC;IACxB,CAAC;SAAM,IAAI,IAAI,CAAC,IAAI,KAAK,SAAS,EAAE,CAAC;QACnC,IAAI,CAAC,OAAO,GAAG,EAAE,cAAc,EAAE,kBAAkB,EAAE,CAAC;QACtD,IAAI,CAAC,IAAI,GAAG,IAAI,CAAC,SAAS,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IACxC,CAAC;IAED,MAAM,GAAG,GAAG,MAAM,KAAK,CAAC,GAAG,EAAE,IAAI,CAAC,CAAC;IACnC,MAAM,IAAI,GAAG,MAAM,GAAG,CAAC,IAAI,EAAE,CAAC;IAC9B,IAAI,CAAC,GAAG,CAAC,EAAE,EAAE,CAAC;QACZ,MAAM,IAAI,QAAQ,CAAC,GAAG,CAAC,MAAM,EAAG,IAAyB,CAAC,OAAO,CAAC,CAAC;IACrE,CAAC;IACD,OAAO,IAAwB,CAAC;AAClC,CAAC;AAED,MAAM,CAAC,MAAM,GAAG,GAAG,CAA6B,IAAO,EAAE,IAA4B,EAAE,EAAE,CAAC,OAAO,CAAC,KAAK,EAAE,IAAI,EAAE,IAAI,CAAC,CAAC;AACrH,MAAM,CAAC,MAAM,IAAI,GAAG,CAA8B,IAAO,EAAE,IAA6B,EAAE,EAAE,CAAC,OAAO,CAAC,MAAM,EAAE,IAAI,EAAE,IAAI,CAAC,CAAC;AACzH,MAAM,CAAC,MAAM,GAAG,GAAG,CAA6B,IAAO,EAAE,IAA4B,EAAE,EAAE,CAAC,OAAO,CAAC,KAAK,EAAE,IAAI,EAAE,IAAI,CAAC,CAAC;AAErH,MAAM,UAAU,SAAS,CAAC,KAAa,EAAE,OAAgC,EAAE,OAAqC;IAC9G,MAAM,MAAM,GAAG,IAAI,WAAW,CAAC,qBAAqB,KAAK,EAAE,CAAC,CAAC;IAC7D,MAAM,CAAC,MAAM,GAAG,GAAG,EAAE,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC;IACpC,MAAM,CAAC,OAAO,GAAG,GAAG,EAAE,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC;IACtC,MAAM,CAAC,SAAS,GAAG,CAAC,GAAyB,EAAE,EAAE,CAAC,OAAO,CAAC,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,IAAI,CAAc,CAAC,CAAC;IAC7F,OAAO,MAAM,CAAC;AAChB,CAAC"} \ No newline at end of file diff --git a/web/dist/app.js b/web/dist/app.js index 9ee05cf..2824b5d 100644 --- a/web/dist/app.js +++ b/web/dist/app.js @@ -43,7 +43,7 @@ async function main() { const left = new Pane("left", "transcript"); const right = new Pane("right", "inbox"); replace(document.body, navbar, banner, h("div", { class: "panes" }, left.el, right.el)); - mountNavbar(navbar, () => right.show("inbox")); + mountNavbar(navbar, (view) => right.show(view)); identityBanner(banner); const status = await get("/api/admin/status"); await Promise.all([loadMe(), loadProjects(), loadInbox()]); diff --git a/web/dist/app.js.map b/web/dist/app.js.map index 725bf15..a33ca7b 100644 --- a/web/dist/app.js.map +++ b/web/dist/app.js.map @@ -1 +1 @@ -{"version":3,"file":"app.js","sourceRoot":"","sources":["../src/app.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,GAAG,EAAE,GAAG,EAAE,SAAS,EAAE,MAAM,UAAU,CAAC;AAC/C,OAAO,EAAE,SAAS,EAAE,CAAC,EAAE,OAAO,EAAE,MAAM,UAAU,CAAC;AACjD,OAAO,EAAE,WAAW,EAAE,MAAM,aAAa,CAAC;AAC1C,OAAO,EAAE,IAAI,EAAE,MAAM,YAAY,CAAC;AAClC,OAAO,EAAE,WAAW,EAAE,SAAS,EAAE,MAAM,EAAE,YAAY,EAAE,MAAM,EAAE,EAAE,EAAE,UAAU,EAAE,KAAK,EAAE,MAAM,YAAY,CAAC;AAEzG,SAAS,cAAc,CAAC,IAAiB;IACvC,MAAM,MAAM,GAAG,GAAG,EAAE;QAClB,MAAM,EAAE,GAAG,KAAK,CAAC,EAAE,CAAC;QACpB,IAAI,CAAC,EAAE,IAAI,CAAC,EAAE,CAAC,QAAQ,IAAI,EAAE,CAAC,SAAS,CAAC,EAAE,CAAC;YACzC,OAAO,CAAC,IAAI,CAAC,CAAC;YACd,IAAI,CAAC,MAAM,GAAG,IAAI,CAAC;YACnB,OAAO;QACT,CAAC;QACD,MAAM,IAAI,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,WAAW,EAAE,UAAU,EAAE,KAAK,EAAE,EAAE,CAAC,YAAY,EAAE,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAC;QAC7F,MAAM,KAAK,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,IAAI,EAAE,OAAO,EAAE,WAAW,EAAE,WAAW,EAAE,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAC;QACtF,MAAM,IAAI,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,aAAa,EAAE,EAAE,qCAAqC,EAAE,IAAI,EAAE,KAAK,EAAE,CAAC,CAAC,QAAQ,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,EAAE,MAAM,CAAC,CAAC,CAAC;QAC9I,IAAI,CAAC,QAAQ,GAAG,KAAK,EAAE,CAAC,EAAE,EAAE;YAC1B,CAAC,CAAC,cAAc,EAAE,CAAC;YACnB,IAAI,CAAC;gBACH,KAAK,CAAC,EAAE,GAAG,MAAM,GAAG,CAAC,SAAS,EAAE,EAAE,IAAI,EAAE,EAAE,QAAQ,EAAE,IAAI,CAAC,KAAK,EAAE,SAAS,EAAE,KAAK,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC;gBAC5F,MAAM,EAAE,CAAC;YACX,CAAC;YAAC,OAAO,GAAG,EAAE,CAAC;gBACb,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,CAAC;YACxB,CAAC;QACH,CAAC,CAAC;QACF,IAAI,CAAC,MAAM,GAAG,KAAK,CAAC;QACpB,OAAO,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC;IACtB,CAAC,CAAC;IACF,EAAE,CAAC,IAAI,EAAE,MAAM,CAAC,CAAC;IACjB,MAAM,EAAE,CAAC;AACX,CAAC;AAED,SAAS,KAAK;IACZ,MAAM,KAAK,GAAG,kBAAkB,CAAC,IAAI,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC;IACrD,MAAM,MAAM,GAAG,KAAK,EAAE,CAAC,CAAC,CAAC,CAAC;IAC1B,IAAI,MAAM,KAAK,KAAK,CAAC,cAAc,EAAE,CAAC;QACpC,KAAK,UAAU,CAAC,MAAM,CAAC,CAAC;IAC1B,CAAC;AACH,CAAC;AAED,KAAK,UAAU,IAAI;IACjB,MAAM,MAAM,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,QAAQ,EAAE,CAAC,CAAC;IAChD,MAAM,MAAM,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,QAAQ,EAAE,MAAM,EAAE,IAAI,EAAE,CAAC,CAAC;IAC3D,MAAM,IAAI,GAAG,IAAI,IAAI,CAAC,MAAM,EAAE,YAAY,CAAC,CAAC;IAC5C,MAAM,KAAK,GAAG,IAAI,IAAI,CAAC,OAAO,EAAE,OAAO,CAAC,CAAC;IACzC,OAAO,CAAC,QAAQ,CAAC,IAAI,EAAE,MAAM,EAAE,MAAM,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE,IAAI,CAAC,EAAE,EAAE,KAAK,CAAC,EAAE,CAAC,CAAC,CAAC;IAExF,WAAW,CAAC,MAAM,EAAE,GAAG,EAAE,CAAC,KAAK,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC,CAAC;IAC/C,cAAc,CAAC,MAAM,CAAC,CAAC;IAEvB,MAAM,MAAM,GAAG,MAAM,GAAG,CAAC,mBAAmB,CAAC,CAAC;IAC9C,MAAM,OAAO,CAAC,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,YAAY,EAAE,EAAE,SAAS,EAAE,CAAC,CAAC,CAAC;IAE3D,SAAS,CAAC,MAAM,CAAC,cAAc,EAAE,WAAW,EAAE,CAAC,SAAS,EAAE,EAAE;QAC1D,KAAK,CAAC,SAAS,GAAG,SAAS,CAAC;QAC5B,MAAM,CAAC,YAAY,CAAC,CAAC;IACvB,CAAC,CAAC,CAAC;IAEH,gBAAgB,CAAC,YAAY,EAAE,KAAK,CAAC,CAAC;IACtC,KAAK,EAAE,CAAC;AACV,CAAC;AAED,IAAI,EAAE,CAAC,KAAK,CAAC,CAAC,GAAY,EAAE,EAAE;IAC5B,OAAO,CAAC,QAAQ,CAAC,IAAI,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE,yBAAyB,SAAS,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC,CAAC;AAClG,CAAC,CAAC,CAAC"} \ No newline at end of file +{"version":3,"file":"app.js","sourceRoot":"","sources":["../src/app.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,GAAG,EAAE,GAAG,EAAE,SAAS,EAAE,MAAM,UAAU,CAAC;AAC/C,OAAO,EAAE,SAAS,EAAE,CAAC,EAAE,OAAO,EAAE,MAAM,UAAU,CAAC;AACjD,OAAO,EAAE,WAAW,EAAE,MAAM,aAAa,CAAC;AAC1C,OAAO,EAAE,IAAI,EAAE,MAAM,YAAY,CAAC;AAClC,OAAO,EAAE,WAAW,EAAE,SAAS,EAAE,MAAM,EAAE,YAAY,EAAE,MAAM,EAAE,EAAE,EAAE,UAAU,EAAE,KAAK,EAAE,MAAM,YAAY,CAAC;AAEzG,SAAS,cAAc,CAAC,IAAiB;IACvC,MAAM,MAAM,GAAG,GAAG,EAAE;QAClB,MAAM,EAAE,GAAG,KAAK,CAAC,EAAE,CAAC;QACpB,IAAI,CAAC,EAAE,IAAI,CAAC,EAAE,CAAC,QAAQ,IAAI,EAAE,CAAC,SAAS,CAAC,EAAE,CAAC;YACzC,OAAO,CAAC,IAAI,CAAC,CAAC;YACd,IAAI,CAAC,MAAM,GAAG,IAAI,CAAC;YACnB,OAAO;QACT,CAAC;QACD,MAAM,IAAI,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,WAAW,EAAE,UAAU,EAAE,KAAK,EAAE,EAAE,CAAC,YAAY,EAAE,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAC;QAC7F,MAAM,KAAK,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,IAAI,EAAE,OAAO,EAAE,WAAW,EAAE,WAAW,EAAE,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAC;QACtF,MAAM,IAAI,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,aAAa,EAAE,EAAE,qCAAqC,EAAE,IAAI,EAAE,KAAK,EAAE,CAAC,CAAC,QAAQ,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,EAAE,MAAM,CAAC,CAAC,CAAC;QAC9I,IAAI,CAAC,QAAQ,GAAG,KAAK,EAAE,CAAC,EAAE,EAAE;YAC1B,CAAC,CAAC,cAAc,EAAE,CAAC;YACnB,IAAI,CAAC;gBACH,KAAK,CAAC,EAAE,GAAG,MAAM,GAAG,CAAC,SAAS,EAAE,EAAE,IAAI,EAAE,EAAE,QAAQ,EAAE,IAAI,CAAC,KAAK,EAAE,SAAS,EAAE,KAAK,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC;gBAC5F,MAAM,EAAE,CAAC;YACX,CAAC;YAAC,OAAO,GAAG,EAAE,CAAC;gBACb,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,CAAC;YACxB,CAAC;QACH,CAAC,CAAC;QACF,IAAI,CAAC,MAAM,GAAG,KAAK,CAAC;QACpB,OAAO,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC;IACtB,CAAC,CAAC;IACF,EAAE,CAAC,IAAI,EAAE,MAAM,CAAC,CAAC;IACjB,MAAM,EAAE,CAAC;AACX,CAAC;AAED,SAAS,KAAK;IACZ,MAAM,KAAK,GAAG,kBAAkB,CAAC,IAAI,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC;IACrD,MAAM,MAAM,GAAG,KAAK,EAAE,CAAC,CAAC,CAAC,CAAC;IAC1B,IAAI,MAAM,KAAK,KAAK,CAAC,cAAc,EAAE,CAAC;QACpC,KAAK,UAAU,CAAC,MAAM,CAAC,CAAC;IAC1B,CAAC;AACH,CAAC;AAED,KAAK,UAAU,IAAI;IACjB,MAAM,MAAM,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,QAAQ,EAAE,CAAC,CAAC;IAChD,MAAM,MAAM,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,QAAQ,EAAE,MAAM,EAAE,IAAI,EAAE,CAAC,CAAC;IAC3D,MAAM,IAAI,GAAG,IAAI,IAAI,CAAC,MAAM,EAAE,YAAY,CAAC,CAAC;IAC5C,MAAM,KAAK,GAAG,IAAI,IAAI,CAAC,OAAO,EAAE,OAAO,CAAC,CAAC;IACzC,OAAO,CAAC,QAAQ,CAAC,IAAI,EAAE,MAAM,EAAE,MAAM,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE,IAAI,CAAC,EAAE,EAAE,KAAK,CAAC,EAAE,CAAC,CAAC,CAAC;IAExF,WAAW,CAAC,MAAM,EAAE,CAAC,IAAI,EAAE,EAAE,CAAC,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC;IAChD,cAAc,CAAC,MAAM,CAAC,CAAC;IAEvB,MAAM,MAAM,GAAG,MAAM,GAAG,CAAC,mBAAmB,CAAC,CAAC;IAC9C,MAAM,OAAO,CAAC,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,YAAY,EAAE,EAAE,SAAS,EAAE,CAAC,CAAC,CAAC;IAE3D,SAAS,CAAC,MAAM,CAAC,cAAc,EAAE,WAAW,EAAE,CAAC,SAAS,EAAE,EAAE;QAC1D,KAAK,CAAC,SAAS,GAAG,SAAS,CAAC;QAC5B,MAAM,CAAC,YAAY,CAAC,CAAC;IACvB,CAAC,CAAC,CAAC;IAEH,gBAAgB,CAAC,YAAY,EAAE,KAAK,CAAC,CAAC;IACtC,KAAK,EAAE,CAAC;AACV,CAAC;AAED,IAAI,EAAE,CAAC,KAAK,CAAC,CAAC,GAAY,EAAE,EAAE;IAC5B,OAAO,CAAC,QAAQ,CAAC,IAAI,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE,yBAAyB,SAAS,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC,CAAC;AAClG,CAAC,CAAC,CAAC"} \ No newline at end of file diff --git a/web/dist/navbar.js b/web/dist/navbar.js index fe6789b..a53c584 100644 --- a/web/dist/navbar.js +++ b/web/dist/navbar.js @@ -1,10 +1,12 @@ import { h, replace } from "./dom.js"; import { activeTasks, findTask, onEach, state } from "./state.js"; -export function mountNavbar(root, showInbox) { +export function mountNavbar(root, show) { const crumb = h("button", { class: "crumb", title: "Switch task (⌘K)" }); crumb.onclick = openSwitcher; const inbox = h("button", { class: "inbox-count" }); - inbox.onclick = showInbox; + inbox.onclick = () => show("inbox"); + const admin = h("button", { class: "nav-link" }, "Admin"); + admin.onclick = () => show("admin"); const conn = h("span", { class: "connection down", title: "connecting" }); const me = h("span", { class: "me" }); const render = () => { @@ -19,7 +21,7 @@ export function mountNavbar(root, showInbox) { replace(me, state.me?.display_name ?? ""); }; onEach(["me", "projects", "tasks", "inbox", "selection", "connection"], render); - replace(root, h("a", { href: "#/", class: "brand" }, "byre"), crumb, h("span", { class: "spacer" }), inbox, conn, me); + replace(root, h("a", { href: "#/", class: "brand" }, "byre"), crumb, h("span", { class: "spacer" }), inbox, admin, conn, me); render(); addEventListener("keydown", (e) => { if (e.key === "k" && (e.metaKey || e.ctrlKey)) { diff --git a/web/dist/navbar.js.map b/web/dist/navbar.js.map index 573038b..f0a15ca 100644 --- a/web/dist/navbar.js.map +++ b/web/dist/navbar.js.map @@ -1 +1 @@ -{"version":3,"file":"navbar.js","sourceRoot":"","sources":["../src/navbar.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,CAAC,EAAE,OAAO,EAAE,MAAM,UAAU,CAAC;AACtC,OAAO,EAAE,WAAW,EAAE,QAAQ,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,YAAY,CAAC;AAElE,MAAM,UAAU,WAAW,CAAC,IAAiB,EAAE,SAAqB;IAClE,MAAM,KAAK,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,KAAK,EAAE,kBAAkB,EAAE,CAAC,CAAC;IACzE,KAAK,CAAC,OAAO,GAAG,YAAY,CAAC;IAE7B,MAAM,KAAK,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,aAAa,EAAE,CAAC,CAAC;IACpD,KAAK,CAAC,OAAO,GAAG,SAAS,CAAC;IAE1B,MAAM,IAAI,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,iBAAiB,EAAE,KAAK,EAAE,YAAY,EAAE,CAAC,CAAC;IAC1E,MAAM,EAAE,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,IAAI,EAAE,CAAC,CAAC;IAEtC,MAAM,MAAM,GAAG,GAAG,EAAE;QAClB,MAAM,IAAI,GAAG,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,QAAQ,CAAC,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;QAC/E,MAAM,OAAO,GAAG,IAAI,CAAC,CAAC,CAAC,KAAK,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,EAAE,KAAK,IAAI,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;QACxF,OAAO,CAAC,KAAK,EAAE,IAAI,CAAC,CAAC,CAAC,GAAG,OAAO,EAAE,IAAI,IAAI,EAAE,MAAM,IAAI,CAAC,KAAK,EAAE,CAAC,CAAC,CAAC,SAAS,EAAE,IAAI,CAAC,CAAC;QAElF,MAAM,OAAO,GAAG,KAAK,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,SAAS,CAAC,CAAC,MAAM,CAAC;QAC3E,KAAK,CAAC,SAAS,GAAG,OAAO,GAAG,CAAC,CAAC,CAAC,CAAC,oBAAoB,CAAC,CAAC,CAAC,aAAa,CAAC;QACrE,OAAO,CAAC,KAAK,EAAE,SAAS,KAAK,CAAC,KAAK,CAAC,MAAM,EAAE,EAAE,OAAO,GAAG,CAAC,IAAI,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,eAAe,EAAE,EAAE,MAAM,OAAO,UAAU,CAAC,CAAC,CAAC;QAE7H,IAAI,CAAC,SAAS,GAAG,KAAK,CAAC,SAAS,CAAC,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC,iBAAiB,CAAC;QACvE,IAAI,CAAC,KAAK,GAAG,KAAK,CAAC,SAAS,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,cAAc,CAAC;QACvD,OAAO,CAAC,EAAE,EAAE,KAAK,CAAC,EAAE,EAAE,YAAY,IAAI,EAAE,CAAC,CAAC;IAC5C,CAAC,CAAC;IAEF,MAAM,CAAC,CAAC,IAAI,EAAE,UAAU,EAAE,OAAO,EAAE,OAAO,EAAE,WAAW,EAAE,YAAY,CAAC,EAAE,MAAM,CAAC,CAAC;IAChF,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC,GAAG,EAAE,EAAE,IAAI,EAAE,IAAI,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE,MAAM,CAAC,EAAE,KAAK,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,QAAQ,EAAE,CAAC,EAAE,KAAK,EAAE,IAAI,EAAE,EAAE,CAAC,CAAC;IACtH,MAAM,EAAE,CAAC;IAET,gBAAgB,CAAC,SAAS,EAAE,CAAC,CAAC,EAAE,EAAE;QAChC,IAAI,CAAC,CAAC,GAAG,KAAK,GAAG,IAAI,CAAC,CAAC,CAAC,OAAO,IAAI,CAAC,CAAC,OAAO,CAAC,EAAE,CAAC;YAC9C,CAAC,CAAC,cAAc,EAAE,CAAC;YACnB,YAAY,EAAE,CAAC;QACjB,CAAC;IACH,CAAC,CAAC,CAAC;AACL,CAAC;AAED,SAAS,YAAY;IACnB,IAAI,QAAQ,CAAC,aAAa,CAAC,WAAW,CAAC,EAAE,CAAC;QACxC,OAAO;IACT,CAAC;IAED,MAAM,KAAK,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,WAAW,EAAE,aAAa,EAAE,YAAY,EAAE,KAAK,EAAE,CAAC,CAAC;IAC9E,MAAM,IAAI,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,KAAK,EAAE,eAAe,EAAE,CAAC,CAAC;IACjD,MAAM,QAAQ,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,mBAAmB,EAAE,CAAC,CAAC;IAC1D,MAAM,GAAG,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,UAAU,EAAE,EAAE,KAAK,EAAE,IAAI,CAAC,CAAC;IACzD,IAAI,QAAQ,GAAG,CAAC,CAAC;IACjB,IAAI,OAAO,GAAmC,EAAE,CAAC;IAEjD,MAAM,KAAK,GAAG,GAAG,EAAE;QACjB,QAAQ,CAAC,MAAM,EAAE,CAAC;QAClB,GAAG,CAAC,MAAM,EAAE,CAAC;IACf,CAAC,CAAC;IAEF,MAAM,EAAE,GAAG,CAAC,MAAc,EAAE,EAAE;QAC5B,KAAK,EAAE,CAAC;QACR,QAAQ,CAAC,IAAI,GAAG,UAAU,MAAM,EAAE,CAAC;IACrC,CAAC,CAAC;IAEF,MAAM,MAAM,GAAG,GAAG,EAAE;QAClB,MAAM,CAAC,GAAG,KAAK,CAAC,KAAK,CAAC,IAAI,EAAE,CAAC,WAAW,EAAE,CAAC;QAC3C,OAAO,GAAG,WAAW,EAAE,CAAC,MAAM,CAAC,CAAC,EAAE,OAAO,EAAE,IAAI,EAAE,EAAE,EAAE,CAAC,GAAG,OAAO,CAAC,IAAI,IAAI,IAAI,CAAC,KAAK,EAAE,CAAC,WAAW,EAAE,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAC;QACjH,QAAQ,GAAG,IAAI,CAAC,GAAG,CAAC,QAAQ,EAAE,IAAI,CAAC,GAAG,CAAC,OAAO,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC;QAC/D,OAAO,CACL,IAAI,EACJ,GAAG,OAAO,CAAC,GAAG,CAAC,CAAC,EAAE,OAAO,EAAE,IAAI,EAAE,EAAE,CAAC,EAAE,EAAE;YACtC,MAAM,EAAE,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,KAAK,EAAE,CAAC,KAAK,QAAQ,CAAC,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,cAAc,EAAE,EAAE,OAAO,CAAC,IAAI,CAAC,EAAE,GAAG,EAAE,IAAI,CAAC,KAAK,CAAC,CAAC;YACrI,EAAE,CAAC,WAAW,GAAG,CAAC,CAAC,EAAE,EAAE;gBACrB,CAAC,CAAC,cAAc,EAAE,CAAC;gBACnB,EAAE,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;YACd,CAAC,CAAC;YACF,OAAO,EAAE,CAAC;QACZ,CAAC,CAAC,EACF,OAAO,CAAC,MAAM,KAAK,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,EAAE,oBAAoB,CAAC,CAC9E,CAAC;IACJ,CAAC,CAAC;IAEF,KAAK,CAAC,OAAO,GAAG,GAAG,EAAE;QACnB,QAAQ,GAAG,CAAC,CAAC;QACb,MAAM,EAAE,CAAC;IACX,CAAC,CAAC;IACF,KAAK,CAAC,SAAS,GAAG,CAAC,CAAC,EAAE,EAAE;QACtB,IAAI,CAAC,CAAC,GAAG,KAAK,QAAQ,EAAE,CAAC;YACvB,KAAK,EAAE,CAAC;QACV,CAAC;aAAM,IAAI,CAAC,CAAC,GAAG,KAAK,WAAW,EAAE,CAAC;YACjC,CAAC,CAAC,cAAc,EAAE,CAAC;YACnB,QAAQ,GAAG,IAAI,CAAC,GAAG,CAAC,QAAQ,GAAG,CAAC,EAAE,OAAO,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;YACtD,MAAM,EAAE,CAAC;QACX,CAAC;aAAM,IAAI,CAAC,CAAC,GAAG,KAAK,SAAS,EAAE,CAAC;YAC/B,CAAC,CAAC,cAAc,EAAE,CAAC;YACnB,QAAQ,GAAG,IAAI,CAAC,GAAG,CAAC,QAAQ,GAAG,CAAC,EAAE,CAAC,CAAC,CAAC;YACrC,MAAM,EAAE,CAAC;QACX,CAAC;aAAM,IAAI,CAAC,CAAC,GAAG,KAAK,OAAO,EAAE,CAAC;YAC7B,MAAM,KAAK,GAAG,OAAO,CAAC,QAAQ,CAAC,CAAC;YAChC,IAAI,KAAK,EAAE,CAAC;gBACV,EAAE,CAAC,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;YACpB,CAAC;QACH,CAAC;IACH,CAAC,CAAC;IACF,QAAQ,CAAC,OAAO,GAAG,KAAK,CAAC;IAEzB,QAAQ,CAAC,IAAI,CAAC,MAAM,CAAC,QAAQ,EAAE,GAAG,CAAC,CAAC;IACpC,MAAM,EAAE,CAAC;IACT,KAAK,CAAC,KAAK,EAAE,CAAC;AAChB,CAAC"} \ No newline at end of file +{"version":3,"file":"navbar.js","sourceRoot":"","sources":["../src/navbar.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,CAAC,EAAE,OAAO,EAAE,MAAM,UAAU,CAAC;AAEtC,OAAO,EAAE,WAAW,EAAE,QAAQ,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,YAAY,CAAC;AAElE,MAAM,UAAU,WAAW,CAAC,IAAiB,EAAE,IAA0B;IACvE,MAAM,KAAK,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,KAAK,EAAE,kBAAkB,EAAE,CAAC,CAAC;IACzE,KAAK,CAAC,OAAO,GAAG,YAAY,CAAC;IAE7B,MAAM,KAAK,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,aAAa,EAAE,CAAC,CAAC;IACpD,KAAK,CAAC,OAAO,GAAG,GAAG,EAAE,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;IAEpC,MAAM,KAAK,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,UAAU,EAAE,EAAE,OAAO,CAAC,CAAC;IAC1D,KAAK,CAAC,OAAO,GAAG,GAAG,EAAE,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;IAEpC,MAAM,IAAI,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,iBAAiB,EAAE,KAAK,EAAE,YAAY,EAAE,CAAC,CAAC;IAC1E,MAAM,EAAE,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,IAAI,EAAE,CAAC,CAAC;IAEtC,MAAM,MAAM,GAAG,GAAG,EAAE;QAClB,MAAM,IAAI,GAAG,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,QAAQ,CAAC,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;QAC/E,MAAM,OAAO,GAAG,IAAI,CAAC,CAAC,CAAC,KAAK,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,EAAE,KAAK,IAAI,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;QACxF,OAAO,CAAC,KAAK,EAAE,IAAI,CAAC,CAAC,CAAC,GAAG,OAAO,EAAE,IAAI,IAAI,EAAE,MAAM,IAAI,CAAC,KAAK,EAAE,CAAC,CAAC,CAAC,SAAS,EAAE,IAAI,CAAC,CAAC;QAElF,MAAM,OAAO,GAAG,KAAK,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,SAAS,CAAC,CAAC,MAAM,CAAC;QAC3E,KAAK,CAAC,SAAS,GAAG,OAAO,GAAG,CAAC,CAAC,CAAC,CAAC,oBAAoB,CAAC,CAAC,CAAC,aAAa,CAAC;QACrE,OAAO,CAAC,KAAK,EAAE,SAAS,KAAK,CAAC,KAAK,CAAC,MAAM,EAAE,EAAE,OAAO,GAAG,CAAC,IAAI,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,eAAe,EAAE,EAAE,MAAM,OAAO,UAAU,CAAC,CAAC,CAAC;QAE7H,IAAI,CAAC,SAAS,GAAG,KAAK,CAAC,SAAS,CAAC,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC,iBAAiB,CAAC;QACvE,IAAI,CAAC,KAAK,GAAG,KAAK,CAAC,SAAS,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,cAAc,CAAC;QACvD,OAAO,CAAC,EAAE,EAAE,KAAK,CAAC,EAAE,EAAE,YAAY,IAAI,EAAE,CAAC,CAAC;IAC5C,CAAC,CAAC;IAEF,MAAM,CAAC,CAAC,IAAI,EAAE,UAAU,EAAE,OAAO,EAAE,OAAO,EAAE,WAAW,EAAE,YAAY,CAAC,EAAE,MAAM,CAAC,CAAC;IAChF,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC,GAAG,EAAE,EAAE,IAAI,EAAE,IAAI,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE,MAAM,CAAC,EAAE,KAAK,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,QAAQ,EAAE,CAAC,EAAE,KAAK,EAAE,KAAK,EAAE,IAAI,EAAE,EAAE,CAAC,CAAC;IAC7H,MAAM,EAAE,CAAC;IAET,gBAAgB,CAAC,SAAS,EAAE,CAAC,CAAC,EAAE,EAAE;QAChC,IAAI,CAAC,CAAC,GAAG,KAAK,GAAG,IAAI,CAAC,CAAC,CAAC,OAAO,IAAI,CAAC,CAAC,OAAO,CAAC,EAAE,CAAC;YAC9C,CAAC,CAAC,cAAc,EAAE,CAAC;YACnB,YAAY,EAAE,CAAC;QACjB,CAAC;IACH,CAAC,CAAC,CAAC;AACL,CAAC;AAED,SAAS,YAAY;IACnB,IAAI,QAAQ,CAAC,aAAa,CAAC,WAAW,CAAC,EAAE,CAAC;QACxC,OAAO;IACT,CAAC;IAED,MAAM,KAAK,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,WAAW,EAAE,aAAa,EAAE,YAAY,EAAE,KAAK,EAAE,CAAC,CAAC;IAC9E,MAAM,IAAI,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,KAAK,EAAE,eAAe,EAAE,CAAC,CAAC;IACjD,MAAM,QAAQ,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,mBAAmB,EAAE,CAAC,CAAC;IAC1D,MAAM,GAAG,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,UAAU,EAAE,EAAE,KAAK,EAAE,IAAI,CAAC,CAAC;IACzD,IAAI,QAAQ,GAAG,CAAC,CAAC;IACjB,IAAI,OAAO,GAAmC,EAAE,CAAC;IAEjD,MAAM,KAAK,GAAG,GAAG,EAAE;QACjB,QAAQ,CAAC,MAAM,EAAE,CAAC;QAClB,GAAG,CAAC,MAAM,EAAE,CAAC;IACf,CAAC,CAAC;IAEF,MAAM,EAAE,GAAG,CAAC,MAAc,EAAE,EAAE;QAC5B,KAAK,EAAE,CAAC;QACR,QAAQ,CAAC,IAAI,GAAG,UAAU,MAAM,EAAE,CAAC;IACrC,CAAC,CAAC;IAEF,MAAM,MAAM,GAAG,GAAG,EAAE;QAClB,MAAM,CAAC,GAAG,KAAK,CAAC,KAAK,CAAC,IAAI,EAAE,CAAC,WAAW,EAAE,CAAC;QAC3C,OAAO,GAAG,WAAW,EAAE,CAAC,MAAM,CAAC,CAAC,EAAE,OAAO,EAAE,IAAI,EAAE,EAAE,EAAE,CAAC,GAAG,OAAO,CAAC,IAAI,IAAI,IAAI,CAAC,KAAK,EAAE,CAAC,WAAW,EAAE,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAC;QACjH,QAAQ,GAAG,IAAI,CAAC,GAAG,CAAC,QAAQ,EAAE,IAAI,CAAC,GAAG,CAAC,OAAO,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC;QAC/D,OAAO,CACL,IAAI,EACJ,GAAG,OAAO,CAAC,GAAG,CAAC,CAAC,EAAE,OAAO,EAAE,IAAI,EAAE,EAAE,CAAC,EAAE,EAAE;YACtC,MAAM,EAAE,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,KAAK,EAAE,CAAC,KAAK,QAAQ,CAAC,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,cAAc,EAAE,EAAE,OAAO,CAAC,IAAI,CAAC,EAAE,GAAG,EAAE,IAAI,CAAC,KAAK,CAAC,CAAC;YACrI,EAAE,CAAC,WAAW,GAAG,CAAC,CAAC,EAAE,EAAE;gBACrB,CAAC,CAAC,cAAc,EAAE,CAAC;gBACnB,EAAE,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;YACd,CAAC,CAAC;YACF,OAAO,EAAE,CAAC;QACZ,CAAC,CAAC,EACF,OAAO,CAAC,MAAM,KAAK,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,EAAE,oBAAoB,CAAC,CAC9E,CAAC;IACJ,CAAC,CAAC;IAEF,KAAK,CAAC,OAAO,GAAG,GAAG,EAAE;QACnB,QAAQ,GAAG,CAAC,CAAC;QACb,MAAM,EAAE,CAAC;IACX,CAAC,CAAC;IACF,KAAK,CAAC,SAAS,GAAG,CAAC,CAAC,EAAE,EAAE;QACtB,IAAI,CAAC,CAAC,GAAG,KAAK,QAAQ,EAAE,CAAC;YACvB,KAAK,EAAE,CAAC;QACV,CAAC;aAAM,IAAI,CAAC,CAAC,GAAG,KAAK,WAAW,EAAE,CAAC;YACjC,CAAC,CAAC,cAAc,EAAE,CAAC;YACnB,QAAQ,GAAG,IAAI,CAAC,GAAG,CAAC,QAAQ,GAAG,CAAC,EAAE,OAAO,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;YACtD,MAAM,EAAE,CAAC;QACX,CAAC;aAAM,IAAI,CAAC,CAAC,GAAG,KAAK,SAAS,EAAE,CAAC;YAC/B,CAAC,CAAC,cAAc,EAAE,CAAC;YACnB,QAAQ,GAAG,IAAI,CAAC,GAAG,CAAC,QAAQ,GAAG,CAAC,EAAE,CAAC,CAAC,CAAC;YACrC,MAAM,EAAE,CAAC;QACX,CAAC;aAAM,IAAI,CAAC,CAAC,GAAG,KAAK,OAAO,EAAE,CAAC;YAC7B,MAAM,KAAK,GAAG,OAAO,CAAC,QAAQ,CAAC,CAAC;YAChC,IAAI,KAAK,EAAE,CAAC;gBACV,EAAE,CAAC,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;YACpB,CAAC;QACH,CAAC;IACH,CAAC,CAAC;IACF,QAAQ,CAAC,OAAO,GAAG,KAAK,CAAC;IAEzB,QAAQ,CAAC,IAAI,CAAC,MAAM,CAAC,QAAQ,EAAE,GAAG,CAAC,CAAC;IACpC,MAAM,EAAE,CAAC;IACT,KAAK,CAAC,KAAK,EAAE,CAAC;AAChB,CAAC"} \ No newline at end of file diff --git a/web/dist/panes.js b/web/dist/panes.js index ca21040..00c6d92 100644 --- a/web/dist/panes.js +++ b/web/dist/panes.js @@ -1,3 +1,4 @@ +import { mountAdmin } from "./admin.js"; import { mountChanges } from "./changes.js"; import { h, replace } from "./dom.js"; import { mountInbox } from "./inbox.js"; @@ -8,8 +9,9 @@ const views = { changes: { label: "Changes", mount: (root) => mountChanges(root) }, tasks: { label: "Tasks", mount: mountTasks }, inbox: { label: "Inbox", mount: mountInbox }, + admin: { label: "Admin", mount: mountAdmin }, }; -const order = ["transcript", "changes", "tasks", "inbox"]; +const order = ["transcript", "changes", "tasks", "inbox", "admin"]; export class Pane { key; el; diff --git a/web/dist/panes.js.map b/web/dist/panes.js.map index 1c4b7cf..5aae241 100644 --- a/web/dist/panes.js.map +++ b/web/dist/panes.js.map @@ -1 +1 @@ -{"version":3,"file":"panes.js","sourceRoot":"","sources":["../src/panes.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,YAAY,EAAE,MAAM,cAAc,CAAC;AAC5C,OAAO,EAAE,CAAC,EAAE,OAAO,EAAE,MAAM,UAAU,CAAC;AACtC,OAAO,EAAE,UAAU,EAAE,MAAM,YAAY,CAAC;AACxC,OAAO,EAAE,eAAe,EAAE,MAAM,WAAW,CAAC;AAC5C,OAAO,EAAE,UAAU,EAAE,MAAM,YAAY,CAAC;AAIxC,MAAM,KAAK,GAA8E;IACvF,UAAU,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,KAAK,EAAE,eAAe,EAAE;IAC3D,OAAO,EAAE,EAAE,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,CAAC,IAAI,EAAE,EAAE,CAAC,YAAY,CAAC,IAAI,CAAC,EAAE;IAClE,KAAK,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,KAAK,EAAE,UAAU,EAAE;IAC5C,KAAK,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,KAAK,EAAE,UAAU,EAAE;CAC7C,CAAC;AAEF,MAAM,KAAK,GAAW,CAAC,YAAY,EAAE,SAAS,EAAE,OAAO,EAAE,OAAO,CAAC,CAAC;AAElE,MAAM,OAAO,IAAI;IAOc;IANpB,EAAE,CAAc;IACR,IAAI,CAAc;IAClB,IAAI,CAAc;IAC3B,IAAI,CAAO;IACX,OAAO,GAAe,GAAG,EAAE,GAAE,CAAC,CAAC;IAEvC,YAA6B,GAAW,EAAE,QAAc;QAA3B,QAAG,GAAH,GAAG,CAAQ;QACtC,IAAI,CAAC,IAAI,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,CAAC,CAAC;QAC7C,IAAI,CAAC,IAAI,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,CAAC,CAAC;QAC7C,IAAI,CAAC,EAAE,GAAG,CAAC,CAAC,SAAS,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,IAAI,CAAC,IAAI,EAAE,IAAI,CAAC,IAAI,CAAC,CAAC;QAEhE,MAAM,KAAK,GAAG,YAAY,CAAC,OAAO,CAAC,IAAI,CAAC,UAAU,EAAE,CAAgB,CAAC;QACrE,IAAI,CAAC,IAAI,GAAG,KAAK,IAAI,KAAK,IAAI,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,QAAQ,CAAC;QACvD,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IACvB,CAAC;IAED,IAAI,CAAC,IAAU;QACb,IAAI,CAAC,OAAO,EAAE,CAAC;QACf,IAAI,CAAC,IAAI,GAAG,IAAI,CAAC;QACjB,YAAY,CAAC,OAAO,CAAC,IAAI,CAAC,UAAU,EAAE,EAAE,IAAI,CAAC,CAAC;QAE9C,OAAO,CACL,IAAI,CAAC,IAAI,EACT,GAAG,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE;YACjB,MAAM,CAAC,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,CAAC,KAAK,IAAI,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,EAAE,EAAE,EAAE,KAAK,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC;YAC7E,CAAC,CAAC,OAAO,GAAG,GAAG,EAAE,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;YAC/B,OAAO,CAAC,CAAC;QACX,CAAC,CAAC,CACH,CAAC;QAEF,MAAM,IAAI,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,aAAa,IAAI,EAAE,EAAE,CAAC,CAAC;QACtD,OAAO,CAAC,IAAI,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC;QACzB,IAAI,CAAC,OAAO,GAAG,KAAK,CAAC,IAAI,CAAC,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;IACzC,CAAC;IAEO,UAAU;QAChB,OAAO,aAAa,IAAI,CAAC,GAAG,EAAE,CAAC;IACjC,CAAC;CACF"} \ No newline at end of file +{"version":3,"file":"panes.js","sourceRoot":"","sources":["../src/panes.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,UAAU,EAAE,MAAM,YAAY,CAAC;AACxC,OAAO,EAAE,YAAY,EAAE,MAAM,cAAc,CAAC;AAC5C,OAAO,EAAE,CAAC,EAAE,OAAO,EAAE,MAAM,UAAU,CAAC;AACtC,OAAO,EAAE,UAAU,EAAE,MAAM,YAAY,CAAC;AACxC,OAAO,EAAE,eAAe,EAAE,MAAM,WAAW,CAAC;AAC5C,OAAO,EAAE,UAAU,EAAE,MAAM,YAAY,CAAC;AAIxC,MAAM,KAAK,GAA8E;IACvF,UAAU,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,KAAK,EAAE,eAAe,EAAE;IAC3D,OAAO,EAAE,EAAE,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,CAAC,IAAI,EAAE,EAAE,CAAC,YAAY,CAAC,IAAI,CAAC,EAAE;IAClE,KAAK,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,KAAK,EAAE,UAAU,EAAE;IAC5C,KAAK,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,KAAK,EAAE,UAAU,EAAE;IAC5C,KAAK,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,KAAK,EAAE,UAAU,EAAE;CAC7C,CAAC;AAEF,MAAM,KAAK,GAAW,CAAC,YAAY,EAAE,SAAS,EAAE,OAAO,EAAE,OAAO,EAAE,OAAO,CAAC,CAAC;AAE3E,MAAM,OAAO,IAAI;IAOc;IANpB,EAAE,CAAc;IACR,IAAI,CAAc;IAClB,IAAI,CAAc;IAC3B,IAAI,CAAO;IACX,OAAO,GAAe,GAAG,EAAE,GAAE,CAAC,CAAC;IAEvC,YAA6B,GAAW,EAAE,QAAc;QAA3B,QAAG,GAAH,GAAG,CAAQ;QACtC,IAAI,CAAC,IAAI,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,CAAC,CAAC;QAC7C,IAAI,CAAC,IAAI,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,CAAC,CAAC;QAC7C,IAAI,CAAC,EAAE,GAAG,CAAC,CAAC,SAAS,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,IAAI,CAAC,IAAI,EAAE,IAAI,CAAC,IAAI,CAAC,CAAC;QAEhE,MAAM,KAAK,GAAG,YAAY,CAAC,OAAO,CAAC,IAAI,CAAC,UAAU,EAAE,CAAgB,CAAC;QACrE,IAAI,CAAC,IAAI,GAAG,KAAK,IAAI,KAAK,IAAI,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,QAAQ,CAAC;QACvD,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IACvB,CAAC;IAED,IAAI,CAAC,IAAU;QACb,IAAI,CAAC,OAAO,EAAE,CAAC;QACf,IAAI,CAAC,IAAI,GAAG,IAAI,CAAC;QACjB,YAAY,CAAC,OAAO,CAAC,IAAI,CAAC,UAAU,EAAE,EAAE,IAAI,CAAC,CAAC;QAE9C,OAAO,CACL,IAAI,CAAC,IAAI,EACT,GAAG,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE;YACjB,MAAM,CAAC,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,CAAC,KAAK,IAAI,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,EAAE,EAAE,EAAE,KAAK,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC;YAC7E,CAAC,CAAC,OAAO,GAAG,GAAG,EAAE,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;YAC/B,OAAO,CAAC,CAAC;QACX,CAAC,CAAC,CACH,CAAC;QAEF,MAAM,IAAI,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,aAAa,IAAI,EAAE,EAAE,CAAC,CAAC;QACtD,OAAO,CAAC,IAAI,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC;QACzB,IAAI,CAAC,OAAO,GAAG,KAAK,CAAC,IAAI,CAAC,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;IACzC,CAAC;IAEO,UAAU;QAChB,OAAO,aAAa,IAAI,CAAC,GAAG,EAAE,CAAC;IACjC,CAAC;CACF"} \ No newline at end of file diff --git a/web/dist/state.js b/web/dist/state.js index 2b237c4..d67ed6d 100644 --- a/web/dist/state.js +++ b/web/dist/state.js @@ -148,5 +148,6 @@ export function handleEvent(ev) { void loadInbox(); break; } + notify("event", ev); } //# sourceMappingURL=state.js.map \ No newline at end of file diff --git a/web/dist/state.js.map b/web/dist/state.js.map index 44f2e35..bfc52d7 100644 --- a/web/dist/state.js.map +++ b/web/dist/state.js.map @@ -1 +1 @@ -{"version":3,"file":"state.js","sourceRoot":"","sources":["../src/state.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,GAAG,EAAyF,MAAM,UAAU,CAAC;AAItH,MAAM,CAAC,MAAM,KAAK,GAAG;IACnB,EAAE,EAAE,SAA6B;IACjC,QAAQ,EAAE,EAAe;IACzB,KAAK,EAAE,IAAI,GAAG,EAAkB;IAChC,QAAQ,EAAE,IAAI,GAAG,EAA0B;IAC3C,KAAK,EAAE,EAAiB;IACxB,cAAc,EAAE,SAA+B;IAC/C,UAAU,EAAE,EAAiB;IAC7B,iBAAiB,EAAE,CAAC;IACpB,SAAS,EAAE,KAAK;CACjB,CAAC;AAEF,MAAM,SAAS,GAAG,IAAI,GAAG,EAA0C,CAAC;AAEpE,MAAM,UAAU,EAAE,CAAC,KAAY,EAAE,EAA8B;IAC7D,IAAI,GAAG,GAAG,SAAS,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;IAC/B,IAAI,CAAC,GAAG,EAAE,CAAC;QACT,GAAG,GAAG,IAAI,GAAG,EAAE,CAAC;QAChB,SAAS,CAAC,GAAG,CAAC,KAAK,EAAE,GAAG,CAAC,CAAC;IAC5B,CAAC;IACD,GAAG,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC;IACZ,OAAO,GAAG,EAAE,CAAC,GAAG,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC;AAC9B,CAAC;AAED,MAAM,UAAU,MAAM,CAAC,MAAe,EAAE,EAA8B;IACpE,MAAM,IAAI,GAAG,MAAM,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC;IAC1C,OAAO,GAAG,EAAE;QACV,KAAK,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;YACvB,GAAG,EAAE,CAAC;QACR,CAAC;IACH,CAAC,CAAC;AACJ,CAAC;AAED,MAAM,UAAU,WAAW;IACzB,OAAO,KAAK,CAAC,QAAQ,CAAC,OAAO,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,CAAC,KAAK,CAAC,KAAK,CAAC,GAAG,CAAC,OAAO,CAAC,EAAE,CAAC,IAAI,EAAE,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,KAAK,QAAQ,CAAC,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC,EAAE,OAAO,EAAE,IAAI,EAAE,CAAC,CAAC,CAAC,CAAC;AAC1J,CAAC;AAED,MAAM,UAAU,MAAM,CAAC,KAAY,EAAE,MAAgB;IACnD,KAAK,MAAM,EAAE,IAAI,SAAS,CAAC,GAAG,CAAC,KAAK,CAAC,IAAI,EAAE,EAAE,CAAC;QAC5C,EAAE,CAAC,MAAM,CAAC,CAAC;IACb,CAAC;AACH,CAAC;AAED,MAAM,UAAU,QAAQ,CAAC,EAAU;IACjC,KAAK,MAAM,KAAK,IAAI,KAAK,CAAC,KAAK,CAAC,MAAM,EAAE,EAAE,CAAC;QACzC,MAAM,IAAI,GAAG,KAAK,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,EAAE,KAAK,EAAE,CAAC,CAAC;QAC5C,IAAI,IAAI,EAAE,CAAC;YACT,OAAO,IAAI,CAAC;QACd,CAAC;IACH,CAAC;IACD,OAAO,SAAS,CAAC;AACnB,CAAC;AAED,MAAM,UAAU,cAAc,CAAC,MAAc;IAC3C,OAAO,KAAK,CAAC,QAAQ,CAAC,GAAG,CAAC,MAAM,CAAC,EAAE,QAAQ,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,KAAK,KAAK,WAAW,CAAC,IAAI,KAAK,CAAC,QAAQ,CAAC,GAAG,CAAC,MAAM,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC;AACpH,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,MAAM;IAC1B,KAAK,CAAC,EAAE,GAAG,MAAM,GAAG,CAAC,SAAS,CAAC,CAAC;IAChC,MAAM,CAAC,IAAI,CAAC,CAAC;AACf,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,YAAY;IAChC,KAAK,CAAC,QAAQ,GAAG,MAAM,GAAG,CAAC,eAAe,CAAC,CAAC;IAC5C,MAAM,OAAO,CAAC,GAAG,CAAC,KAAK,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,SAAS,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC;IAC9D,MAAM,CAAC,UAAU,CAAC,CAAC;AACrB,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,SAAS,CAAC,SAAiB;IAC/C,MAAM,KAAK,GAAG,MAAM,GAAG,CAAC,iCAAiC,EAAE,EAAE,IAAI,EAAE,EAAE,SAAS,EAAE,EAAE,CAAC,CAAC;IACpF,KAAK,CAAC,KAAK,CAAC,GAAG,CAAC,SAAS,EAAE,KAAK,CAAC,CAAC;IAClC,MAAM,OAAO,CAAC,GAAG,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,KAAK,QAAQ,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,YAAY,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC;IAC7F,MAAM,CAAC,OAAO,CAAC,CAAC;AAClB,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,YAAY,CAAC,MAAc;IAC/C,KAAK,CAAC,QAAQ,CAAC,GAAG,CAAC,MAAM,EAAE,MAAM,GAAG,CAAC,8BAA8B,EAAE,EAAE,IAAI,EAAE,EAAE,MAAM,EAAE,EAAE,CAAC,CAAC,CAAC;IAC5F,MAAM,CAAC,UAAU,EAAE,MAAM,CAAC,CAAC;AAC7B,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,SAAS;IAC7B,KAAK,CAAC,KAAK,GAAG,MAAM,GAAG,CAAC,YAAY,CAAC,CAAC;IACtC,MAAM,CAAC,OAAO,CAAC,CAAC;AAClB,CAAC;AAED,IAAI,cAAuC,CAAC;AAE5C,MAAM,CAAC,KAAK,UAAU,UAAU,CAAC,MAA0B;IACzD,KAAK,CAAC,cAAc,GAAG,MAAM,CAAC;IAC9B,KAAK,CAAC,UAAU,GAAG,EAAE,CAAC;IACtB,KAAK,CAAC,iBAAiB,GAAG,CAAC,CAAC;IAC5B,cAAc,GAAG,SAAS,CAAC;IAC3B,MAAM,CAAC,WAAW,CAAC,CAAC;IAEpB,IAAI,CAAC,MAAM,EAAE,CAAC;QACZ,OAAO;IACT,CAAC;IAED,MAAM,IAAI,GAAgB,EAAE,CAAC;IAC7B,cAAc,GAAG,IAAI,CAAC;IACtB,SAAS,CAAC;QACR,MAAM,IAAI,GAAG,MAAM,GAAG,CAAC,4BAA4B,EAAE,EAAE,IAAI,EAAE,EAAE,MAAM,EAAE,EAAE,KAAK,EAAE,EAAE,KAAK,EAAE,KAAK,CAAC,iBAAiB,EAAE,KAAK,EAAE,IAAI,EAAE,EAAE,CAAC,CAAC;QACnI,IAAI,KAAK,CAAC,cAAc,KAAK,MAAM,IAAI,cAAc,KAAK,IAAI,EAAE,CAAC;YAC/D,OAAO;QACT,CAAC;QACD,gBAAgB,CAAC,IAAI,CAAC,CAAC;QACvB,IAAI,IAAI,CAAC,MAAM,GAAG,IAAI,EAAE,CAAC;YACvB,MAAM;QACR,CAAC;IACH,CAAC;IACD,cAAc,GAAG,SAAS,CAAC;IAC3B,gBAAgB,CAAC,IAAI,CAAC,CAAC;AACzB,CAAC;AAED,SAAS,gBAAgB,CAAC,MAAmB;IAC3C,MAAM,KAAK,GAAG,MAAM,CAAC,MAAM,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,EAAE,CAAC,GAAG,GAAG,KAAK,CAAC,iBAAiB,CAAC,CAAC;IACtE,IAAI,KAAK,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QACvB,OAAO;IACT,CAAC;IACD,KAAK,CAAC,UAAU,CAAC,IAAI,CAAC,GAAG,KAAK,CAAC,CAAC;IAChC,KAAK,CAAC,iBAAiB,GAAG,KAAK,CAAC,EAAE,CAAC,CAAC,CAAC,CAAE,CAAC,GAAG,CAAC;IAC5C,MAAM,CAAC,YAAY,EAAE,KAAK,CAAC,CAAC;AAC9B,CAAC;AAED,MAAM,UAAU,WAAW,CAAC,EAAa;IACvC,IAAI,EAAE,CAAC,GAAG,KAAK,CAAC,EAAE,CAAC;QACjB,IAAI,EAAE,CAAC,OAAO,IAAI,EAAE,CAAC,OAAO,KAAK,KAAK,CAAC,cAAc,IAAI,CAAC,cAAc,EAAE,CAAC;YACzE,MAAM,CAAC,QAAQ,EAAE,EAAE,CAAC,CAAC;QACvB,CAAC;QACD,OAAO;IACT,CAAC;IAED,IAAI,EAAE,CAAC,OAAO,IAAI,EAAE,CAAC,OAAO,KAAK,KAAK,CAAC,cAAc,EAAE,CAAC;QACtD,IAAI,cAAc,EAAE,CAAC;YACnB,cAAc,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QAC1B,CAAC;aAAM,CAAC;YACN,gBAAgB,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC;QACzB,CAAC;IACH,CAAC;IAED,QAAQ,EAAE,CAAC,IAAI,EAAE,CAAC;QAChB,KAAK,cAAc;YACjB,IAAI,EAAE,CAAC,OAAO,CAAC,OAAO,CAAC,KAAK,KAAK,CAAC,EAAE,EAAE,KAAK,EAAE,CAAC;gBAC5C,KAAK,MAAM,EAAE,CAAC;YAChB,CAAC;YACD,MAAM;QACR,KAAK,iBAAiB;YACpB,KAAK,YAAY,EAAE,CAAC;YACpB,MAAM;QACR,KAAK,cAAc,CAAC;QACpB,KAAK,aAAa,CAAC;QACnB,KAAK,gBAAgB;YACnB,IAAI,EAAE,CAAC,UAAU,EAAE,CAAC;gBAClB,KAAK,SAAS,CAAC,EAAE,CAAC,UAAU,CAAC,CAAC;YAChC,CAAC;YACD,MAAM;QACR,KAAK,iBAAiB,CAAC;QACvB,KAAK,eAAe,CAAC;QACrB,KAAK,eAAe;YAClB,IAAI,EAAE,CAAC,OAAO,EAAE,CAAC;gBACf,KAAK,YAAY,CAAC,EAAE,CAAC,OAAO,CAAC,CAAC;YAChC,CAAC;YACD,MAAM;QACR,KAAK,eAAe,CAAC;QACrB,KAAK,eAAe;YAClB,KAAK,SAAS,EAAE,CAAC;YACjB,MAAM;IACV,CAAC;AACH,CAAC"} \ No newline at end of file +{"version":3,"file":"state.js","sourceRoot":"","sources":["../src/state.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,GAAG,EAAyF,MAAM,UAAU,CAAC;AAItH,MAAM,CAAC,MAAM,KAAK,GAAG;IACnB,EAAE,EAAE,SAA6B;IACjC,QAAQ,EAAE,EAAe;IACzB,KAAK,EAAE,IAAI,GAAG,EAAkB;IAChC,QAAQ,EAAE,IAAI,GAAG,EAA0B;IAC3C,KAAK,EAAE,EAAiB;IACxB,cAAc,EAAE,SAA+B;IAC/C,UAAU,EAAE,EAAiB;IAC7B,iBAAiB,EAAE,CAAC;IACpB,SAAS,EAAE,KAAK;CACjB,CAAC;AAEF,MAAM,SAAS,GAAG,IAAI,GAAG,EAA0C,CAAC;AAEpE,MAAM,UAAU,EAAE,CAAC,KAAY,EAAE,EAA8B;IAC7D,IAAI,GAAG,GAAG,SAAS,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;IAC/B,IAAI,CAAC,GAAG,EAAE,CAAC;QACT,GAAG,GAAG,IAAI,GAAG,EAAE,CAAC;QAChB,SAAS,CAAC,GAAG,CAAC,KAAK,EAAE,GAAG,CAAC,CAAC;IAC5B,CAAC;IACD,GAAG,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC;IACZ,OAAO,GAAG,EAAE,CAAC,GAAG,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC;AAC9B,CAAC;AAED,MAAM,UAAU,MAAM,CAAC,MAAe,EAAE,EAA8B;IACpE,MAAM,IAAI,GAAG,MAAM,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC;IAC1C,OAAO,GAAG,EAAE;QACV,KAAK,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;YACvB,GAAG,EAAE,CAAC;QACR,CAAC;IACH,CAAC,CAAC;AACJ,CAAC;AAED,MAAM,UAAU,WAAW;IACzB,OAAO,KAAK,CAAC,QAAQ,CAAC,OAAO,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,CAAC,KAAK,CAAC,KAAK,CAAC,GAAG,CAAC,OAAO,CAAC,EAAE,CAAC,IAAI,EAAE,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,KAAK,QAAQ,CAAC,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC,EAAE,OAAO,EAAE,IAAI,EAAE,CAAC,CAAC,CAAC,CAAC;AAC1J,CAAC;AAED,MAAM,UAAU,MAAM,CAAC,KAAY,EAAE,MAAgB;IACnD,KAAK,MAAM,EAAE,IAAI,SAAS,CAAC,GAAG,CAAC,KAAK,CAAC,IAAI,EAAE,EAAE,CAAC;QAC5C,EAAE,CAAC,MAAM,CAAC,CAAC;IACb,CAAC;AACH,CAAC;AAED,MAAM,UAAU,QAAQ,CAAC,EAAU;IACjC,KAAK,MAAM,KAAK,IAAI,KAAK,CAAC,KAAK,CAAC,MAAM,EAAE,EAAE,CAAC;QACzC,MAAM,IAAI,GAAG,KAAK,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,EAAE,KAAK,EAAE,CAAC,CAAC;QAC5C,IAAI,IAAI,EAAE,CAAC;YACT,OAAO,IAAI,CAAC;QACd,CAAC;IACH,CAAC;IACD,OAAO,SAAS,CAAC;AACnB,CAAC;AAED,MAAM,UAAU,cAAc,CAAC,MAAc;IAC3C,OAAO,KAAK,CAAC,QAAQ,CAAC,GAAG,CAAC,MAAM,CAAC,EAAE,QAAQ,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,KAAK,KAAK,WAAW,CAAC,IAAI,KAAK,CAAC,QAAQ,CAAC,GAAG,CAAC,MAAM,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC;AACpH,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,MAAM;IAC1B,KAAK,CAAC,EAAE,GAAG,MAAM,GAAG,CAAC,SAAS,CAAC,CAAC;IAChC,MAAM,CAAC,IAAI,CAAC,CAAC;AACf,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,YAAY;IAChC,KAAK,CAAC,QAAQ,GAAG,MAAM,GAAG,CAAC,eAAe,CAAC,CAAC;IAC5C,MAAM,OAAO,CAAC,GAAG,CAAC,KAAK,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,SAAS,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC;IAC9D,MAAM,CAAC,UAAU,CAAC,CAAC;AACrB,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,SAAS,CAAC,SAAiB;IAC/C,MAAM,KAAK,GAAG,MAAM,GAAG,CAAC,iCAAiC,EAAE,EAAE,IAAI,EAAE,EAAE,SAAS,EAAE,EAAE,CAAC,CAAC;IACpF,KAAK,CAAC,KAAK,CAAC,GAAG,CAAC,SAAS,EAAE,KAAK,CAAC,CAAC;IAClC,MAAM,OAAO,CAAC,GAAG,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,KAAK,QAAQ,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,YAAY,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC;IAC7F,MAAM,CAAC,OAAO,CAAC,CAAC;AAClB,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,YAAY,CAAC,MAAc;IAC/C,KAAK,CAAC,QAAQ,CAAC,GAAG,CAAC,MAAM,EAAE,MAAM,GAAG,CAAC,8BAA8B,EAAE,EAAE,IAAI,EAAE,EAAE,MAAM,EAAE,EAAE,CAAC,CAAC,CAAC;IAC5F,MAAM,CAAC,UAAU,EAAE,MAAM,CAAC,CAAC;AAC7B,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,SAAS;IAC7B,KAAK,CAAC,KAAK,GAAG,MAAM,GAAG,CAAC,YAAY,CAAC,CAAC;IACtC,MAAM,CAAC,OAAO,CAAC,CAAC;AAClB,CAAC;AAED,IAAI,cAAuC,CAAC;AAE5C,MAAM,CAAC,KAAK,UAAU,UAAU,CAAC,MAA0B;IACzD,KAAK,CAAC,cAAc,GAAG,MAAM,CAAC;IAC9B,KAAK,CAAC,UAAU,GAAG,EAAE,CAAC;IACtB,KAAK,CAAC,iBAAiB,GAAG,CAAC,CAAC;IAC5B,cAAc,GAAG,SAAS,CAAC;IAC3B,MAAM,CAAC,WAAW,CAAC,CAAC;IAEpB,IAAI,CAAC,MAAM,EAAE,CAAC;QACZ,OAAO;IACT,CAAC;IAED,MAAM,IAAI,GAAgB,EAAE,CAAC;IAC7B,cAAc,GAAG,IAAI,CAAC;IACtB,SAAS,CAAC;QACR,MAAM,IAAI,GAAG,MAAM,GAAG,CAAC,4BAA4B,EAAE,EAAE,IAAI,EAAE,EAAE,MAAM,EAAE,EAAE,KAAK,EAAE,EAAE,KAAK,EAAE,KAAK,CAAC,iBAAiB,EAAE,KAAK,EAAE,IAAI,EAAE,EAAE,CAAC,CAAC;QACnI,IAAI,KAAK,CAAC,cAAc,KAAK,MAAM,IAAI,cAAc,KAAK,IAAI,EAAE,CAAC;YAC/D,OAAO;QACT,CAAC;QACD,gBAAgB,CAAC,IAAI,CAAC,CAAC;QACvB,IAAI,IAAI,CAAC,MAAM,GAAG,IAAI,EAAE,CAAC;YACvB,MAAM;QACR,CAAC;IACH,CAAC;IACD,cAAc,GAAG,SAAS,CAAC;IAC3B,gBAAgB,CAAC,IAAI,CAAC,CAAC;AACzB,CAAC;AAED,SAAS,gBAAgB,CAAC,MAAmB;IAC3C,MAAM,KAAK,GAAG,MAAM,CAAC,MAAM,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,EAAE,CAAC,GAAG,GAAG,KAAK,CAAC,iBAAiB,CAAC,CAAC;IACtE,IAAI,KAAK,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QACvB,OAAO;IACT,CAAC;IACD,KAAK,CAAC,UAAU,CAAC,IAAI,CAAC,GAAG,KAAK,CAAC,CAAC;IAChC,KAAK,CAAC,iBAAiB,GAAG,KAAK,CAAC,EAAE,CAAC,CAAC,CAAC,CAAE,CAAC,GAAG,CAAC;IAC5C,MAAM,CAAC,YAAY,EAAE,KAAK,CAAC,CAAC;AAC9B,CAAC;AAED,MAAM,UAAU,WAAW,CAAC,EAAa;IACvC,IAAI,EAAE,CAAC,GAAG,KAAK,CAAC,EAAE,CAAC;QACjB,IAAI,EAAE,CAAC,OAAO,IAAI,EAAE,CAAC,OAAO,KAAK,KAAK,CAAC,cAAc,IAAI,CAAC,cAAc,EAAE,CAAC;YACzE,MAAM,CAAC,QAAQ,EAAE,EAAE,CAAC,CAAC;QACvB,CAAC;QACD,OAAO;IACT,CAAC;IAED,IAAI,EAAE,CAAC,OAAO,IAAI,EAAE,CAAC,OAAO,KAAK,KAAK,CAAC,cAAc,EAAE,CAAC;QACtD,IAAI,cAAc,EAAE,CAAC;YACnB,cAAc,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QAC1B,CAAC;aAAM,CAAC;YACN,gBAAgB,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC;QACzB,CAAC;IACH,CAAC;IAED,QAAQ,EAAE,CAAC,IAAI,EAAE,CAAC;QAChB,KAAK,cAAc;YACjB,IAAI,EAAE,CAAC,OAAO,CAAC,OAAO,CAAC,KAAK,KAAK,CAAC,EAAE,EAAE,KAAK,EAAE,CAAC;gBAC5C,KAAK,MAAM,EAAE,CAAC;YAChB,CAAC;YACD,MAAM;QACR,KAAK,iBAAiB;YACpB,KAAK,YAAY,EAAE,CAAC;YACpB,MAAM;QACR,KAAK,cAAc,CAAC;QACpB,KAAK,aAAa,CAAC;QACnB,KAAK,gBAAgB;YACnB,IAAI,EAAE,CAAC,UAAU,EAAE,CAAC;gBAClB,KAAK,SAAS,CAAC,EAAE,CAAC,UAAU,CAAC,CAAC;YAChC,CAAC;YACD,MAAM;QACR,KAAK,iBAAiB,CAAC;QACvB,KAAK,eAAe,CAAC;QACrB,KAAK,eAAe;YAClB,IAAI,EAAE,CAAC,OAAO,EAAE,CAAC;gBACf,KAAK,YAAY,CAAC,EAAE,CAAC,OAAO,CAAC,CAAC;YAChC,CAAC;YACD,MAAM;QACR,KAAK,eAAe,CAAC;QACrB,KAAK,eAAe;YAClB,KAAK,SAAS,EAAE,CAAC;YACjB,MAAM;IACV,CAAC;IAED,MAAM,CAAC,OAAO,EAAE,EAAE,CAAC,CAAC;AACtB,CAAC"} \ No newline at end of file diff --git a/web/src/admin.ts b/web/src/admin.ts new file mode 100644 index 0000000..778e844 --- /dev/null +++ b/web/src/admin.ts @@ -0,0 +1,242 @@ +import { get, type ByreEvent, type Status, type TurnRef } from "./api.js"; +import { ago, errorText, h, replace } from "./dom.js"; +import { findTask, on, onEach, state } from "./state.js"; + +const refreshKinds = new Set(["session.created", "session.state", "task.created", "task.merged", "task.discarded", "project.created"]); + +export function mountAdmin(root: HTMLElement): () => void { + let status: Status | undefined; + let error = ""; + let inFlight = false; + let again = false; + let disposed = false; + + const render = () => { + if (!status) { + replace(root, h("div", { class: error ? "empty error-text" : "empty" }, error || "Loading…")); + return; + } + replace( + root, + h( + "div", + { class: "admin-view" }, + error && h("p", { class: "error-text" }, error), + turnsSection(status), + rateLimitsSection(status.rate_limits), + serverSection(status), + ), + ); + }; + + const refresh = async () => { + if (inFlight) { + again = true; + return; + } + inFlight = true; + try { + const next = await get("/api/admin/status"); + if (disposed) { + return; + } + status = next; + error = ""; + } catch (err) { + error = `Couldn't load status: ${errorText(err)}`; + } + inFlight = false; + render(); + if (again && !disposed) { + again = false; + void refresh(); + } + }; + + const onEvent = (detail?: unknown) => { + const ev = detail as ByreEvent; + if (refreshKinds.has(ev.kind) || (ev.kind === "agent.vendor" && ev.payload["type"] === "rate_limit_event")) { + void refresh(); + return; + } + if (status && ev.seq > status.last_event_seq) { + status.last_event_seq = ev.seq; + render(); + } + }; + + const offs = [ + on("event", onEvent), + on("connection", () => { + if (state.connected) { + void refresh(); + } + }), + onEach(["projects", "tasks"], render), + ]; + + render(); + void refresh(); + + return () => { + disposed = true; + for (const off of offs) { + off(); + } + }; +} + +function turnsSection(s: Status): HTMLElement { + const vendors = [...new Set([...Object.keys(s.caps.per_vendor), ...s.running_turns.map((t) => t.vendor), ...s.queued_turns.map((t) => t.vendor)])].sort(); + const runningFor = (vendor: string) => s.running_turns.filter((t) => t.vendor === vendor).length; + + return h( + "section", + { class: "admin-section" }, + h("h2", {}, "Turns"), + h( + "div", + { class: "caps" }, + capTile("All vendors", s.running_turns.length, s.caps.global), + ...vendors.map((v) => capTile(v, runningFor(v), s.caps.per_vendor[v])), + h("div", { class: "cap-tile" }, h("div", { class: "cap-label" }, "Queued"), h("div", { class: s.queued_turns.length > 0 ? "cap-value warn" : "cap-value" }, s.queued_turns.length)), + ), + h("h3", {}, "Running"), + turnList(s.running_turns, "running", "No turns running."), + h("h3", {}, "Queued"), + turnList(s.queued_turns, "queued", "Nothing queued."), + ); +} + +function capTile(label: string, running: number, cap: number | undefined): HTMLElement { + const full = cap !== undefined && running >= cap; + return h( + "div", + { class: "cap-tile" }, + h("div", { class: "cap-label" }, label), + h("div", { class: full ? "cap-value warn" : "cap-value" }, running, h("span", { class: "cap-max" }, cap === undefined ? " / no cap" : ` / ${cap}`)), + ); +} + +function turnList(turns: TurnRef[], kind: "running" | "queued", empty: string): HTMLElement { + return h( + "ul", + { class: "task-list" }, + ...turns.map((t, i) => { + const task = findTask(t.task_id); + const project = task ? state.projects.find((p) => p.id === task.project_id) : undefined; + return h( + "li", + {}, + h( + "a", + { href: `#/task/${t.task_id}` }, + kind === "queued" ? h("span", { class: "queue-pos" }, `${i + 1}.`) : h("span", { class: "dot running", title: "running" }), + h("span", { class: "task-title" }, project && h("span", { class: "project-name" }, `${project.name} ▸ `), task?.title ?? t.task_id), + h("span", { class: "task-state" }, t.vendor), + ), + ); + }), + turns.length === 0 && h("li", { class: "empty-row" }, empty), + ); +} + +function rateLimitsSection(limits: Status["rate_limits"]): HTMLElement { + const vendors = Object.keys(limits).sort(); + return h( + "section", + { class: "admin-section" }, + h("h2", {}, "Rate limits"), + ...vendors.map((v) => rateLimitCard(v, limits[v] ?? {})), + vendors.length === 0 && h("p", { class: "hint" }, "No vendor has reported a rate-limit status since byre started."), + ); +} + +function rateLimitCard(vendor: string, info: Record): HTMLElement { + const { status, rateLimitType, resetsAt, unifiedWindows, ...rest } = info; + const statusText = String(status ?? "unknown"); + const tone = statusText === "allowed" ? "ok" : statusText === "rejected" ? "danger" : "warn"; + const windows = (unifiedWindows ?? {}) as Record; + + return h( + "div", + { class: "card rate-limit" }, + h( + "header", + {}, + h("span", { class: "vendor" }, vendor), + h("span", { class: `rl-status ${tone}` }, statusText), + rateLimitType !== undefined && h("span", {}, String(rateLimitType)), + typeof resetsAt === "number" && h("span", { class: "resets" }, "resets ", resetText(resetsAt)), + ), + Object.keys(windows).length > 0 && + h( + "table", + { class: "rl-windows" }, + h("tr", {}, h("th", {}, "Window"), h("th", {}, "Used"), h("th", {}, "Resets")), + ...Object.entries(windows).map(([name, w]) => + h( + "tr", + {}, + h("td", {}, name), + h("td", { class: utilizationClass(w.utilization) }, w.utilization === undefined ? "—" : `${Math.round(w.utilization * 100)}%`), + h("td", {}, w.resetsAt === undefined ? "—" : resetText(w.resetsAt)), + ), + ), + ), + Object.keys(rest).length > 0 && + h( + "dl", + { class: "kv" }, + ...Object.entries(rest).flatMap(([k, v]) => [h("dt", {}, k), h("dd", {}, typeof v === "object" ? JSON.stringify(v) : String(v))]), + ), + ); +} + +function utilizationClass(u: number | undefined): string { + if (u === undefined) { + return ""; + } + if (u >= 0.9) { + return "danger"; + } + if (u >= 0.7) { + return "warn"; + } + return ""; +} + +function resetText(unixSeconds: number): string { + const at = new Date(unixSeconds * 1000); + const time = at.toLocaleString(undefined, { weekday: "short", hour: "numeric", minute: "2-digit" }); + const minutes = Math.round((at.getTime() - Date.now()) / 60000); + if (minutes <= 0) { + return `${time} (passed)`; + } + const rel = minutes < 60 ? `${minutes}m` : minutes < 1440 ? `${Math.floor(minutes / 60)}h ${minutes % 60}m` : `${Math.floor(minutes / 1440)}d ${Math.floor((minutes % 1440) / 60)}h`; + return `${time} (in ${rel})`; +} + +function serverSection(s: Status): HTMLElement { + const rows: [string, string][] = [ + ["Started", `${new Date(s.started_at).toLocaleString()} (${ago(s.started_at)})`], + ["Agent processes", String(s.live_agents)], + ["Projects", String(s.projects)], + ["Active tasks", String(s.active_tasks)], + ["Live clients", String(s.sse_clients)], + ["Database", bytes(s.db_bytes)], + ["Last event", `#${s.last_event_seq}`], + ]; + return h("section", { class: "admin-section" }, h("h2", {}, "Server"), h("dl", { class: "kv" }, ...rows.flatMap(([k, v]) => [h("dt", {}, k), h("dd", {}, v)]))); +} + +function bytes(n: number): string { + const units = ["B", "KB", "MB", "GB", "TB"]; + let i = 0; + let v = n; + while (v >= 1024 && i < units.length - 1) { + v /= 1024; + i++; + } + return `${v.toFixed(i === 0 ? 0 : 1)} ${units[i]}`; +} diff --git a/web/src/api.gen.ts b/web/src/api.gen.ts index d2258d1..ad499a1 100644 --- a/web/src/api.gen.ts +++ b/web/src/api.gen.ts @@ -655,8 +655,11 @@ export interface components { Status: { /** @description Agent processes currently running. */ live_agents: number; - running_turns: number; - queued_turns: number; + /** @description Turns running now, oldest session first. */ + running_turns: components["schemas"]["TurnRef"][]; + /** @description Turns waiting for room under the caps, in the order they will start. */ + queued_turns: components["schemas"]["TurnRef"][]; + caps: components["schemas"]["Caps"]; /** @description The latest rate-limit status each vendor reported, keyed by vendor. */ rate_limits: { [key: string]: Record; @@ -671,6 +674,19 @@ export interface components { active_tasks: number; sse_clients: number; }; + Caps: { + /** @description Most turns running at once across all vendors. */ + global: number; + /** @description Most turns running at once per vendor, keyed by vendor. */ + per_vendor: { + [key: string]: number; + }; + }; + TurnRef: { + session_id: string; + task_id: string; + vendor: string; + }; }; responses: { /** @description Error. */ diff --git a/web/src/api.ts b/web/src/api.ts index 9c3b9d3..c9cde45 100644 --- a/web/src/api.ts +++ b/web/src/api.ts @@ -12,6 +12,7 @@ export type InboxResponseCreate = Schemas["InboxResponseCreate"]; export type Attachment = Schemas["Attachment"]; export type ByreEvent = Schemas["Event"]; export type Status = Schemas["Status"]; +export type TurnRef = Schemas["TurnRef"]; type Method = "get" | "post" | "put"; diff --git a/web/src/app.ts b/web/src/app.ts index 41f3e87..b5319da 100644 --- a/web/src/app.ts +++ b/web/src/app.ts @@ -46,7 +46,7 @@ async function main(): Promise { const right = new Pane("right", "inbox"); replace(document.body, navbar, banner, h("div", { class: "panes" }, left.el, right.el)); - mountNavbar(navbar, () => right.show("inbox")); + mountNavbar(navbar, (view) => right.show(view)); identityBanner(banner); const status = await get("/api/admin/status"); diff --git a/web/src/navbar.ts b/web/src/navbar.ts index 99e56ae..bf43ec3 100644 --- a/web/src/navbar.ts +++ b/web/src/navbar.ts @@ -1,12 +1,16 @@ import { h, replace } from "./dom.js"; +import type { View } from "./panes.js"; import { activeTasks, findTask, onEach, state } from "./state.js"; -export function mountNavbar(root: HTMLElement, showInbox: () => void): void { +export function mountNavbar(root: HTMLElement, show: (view: View) => void): void { const crumb = h("button", { class: "crumb", title: "Switch task (⌘K)" }); crumb.onclick = openSwitcher; const inbox = h("button", { class: "inbox-count" }); - inbox.onclick = showInbox; + inbox.onclick = () => show("inbox"); + + const admin = h("button", { class: "nav-link" }, "Admin"); + admin.onclick = () => show("admin"); const conn = h("span", { class: "connection down", title: "connecting" }); const me = h("span", { class: "me" }); @@ -26,7 +30,7 @@ export function mountNavbar(root: HTMLElement, showInbox: () => void): void { }; onEach(["me", "projects", "tasks", "inbox", "selection", "connection"], render); - replace(root, h("a", { href: "#/", class: "brand" }, "byre"), crumb, h("span", { class: "spacer" }), inbox, conn, me); + replace(root, h("a", { href: "#/", class: "brand" }, "byre"), crumb, h("span", { class: "spacer" }), inbox, admin, conn, me); render(); addEventListener("keydown", (e) => { diff --git a/web/src/panes.ts b/web/src/panes.ts index 8bad107..cb3021e 100644 --- a/web/src/panes.ts +++ b/web/src/panes.ts @@ -1,19 +1,21 @@ +import { mountAdmin } from "./admin.js"; import { mountChanges } from "./changes.js"; import { h, replace } from "./dom.js"; import { mountInbox } from "./inbox.js"; import { mountTranscript } from "./task.js"; import { mountTasks } from "./tasks.js"; -export type View = "transcript" | "changes" | "tasks" | "inbox"; +export type View = "transcript" | "changes" | "tasks" | "inbox" | "admin"; const views: Record () => void }> = { transcript: { label: "Transcript", mount: mountTranscript }, changes: { label: "Changes", mount: (root) => mountChanges(root) }, tasks: { label: "Tasks", mount: mountTasks }, inbox: { label: "Inbox", mount: mountInbox }, + admin: { label: "Admin", mount: mountAdmin }, }; -const order: View[] = ["transcript", "changes", "tasks", "inbox"]; +const order: View[] = ["transcript", "changes", "tasks", "inbox", "admin"]; export class Pane { readonly el: HTMLElement; diff --git a/web/src/state.ts b/web/src/state.ts index 858bea6..5043fb2 100644 --- a/web/src/state.ts +++ b/web/src/state.ts @@ -1,6 +1,6 @@ import { get, type AgentSession, type ByreEvent, type InboxItem, type Project, type Task, type User } from "./api.js"; -export type Topic = "me" | "projects" | "tasks" | "sessions" | "inbox" | "selection" | "transcript" | "stream" | "connection"; +export type Topic = "me" | "projects" | "tasks" | "sessions" | "inbox" | "selection" | "transcript" | "stream" | "connection" | "event"; export const state = { me: undefined as User | undefined, @@ -170,4 +170,6 @@ export function handleEvent(ev: ByreEvent): void { void loadInbox(); break; } + + notify("event", ev); } diff --git a/web/style.css b/web/style.css index 9964caf..0992a40 100644 --- a/web/style.css +++ b/web/style.css @@ -1247,3 +1247,133 @@ pre.diff .meta { padding: 24px; color: var(--danger); } + +.nav-link { + background: transparent; +} + +.admin-view { + flex: 1; + min-height: 0; + overflow-y: auto; + padding: 8px 16px 16px; +} + +.admin-section h2 { + font-size: 13px; + margin: 16px 0 8px; +} + +.admin-section h3 { + font-size: 12px; + color: var(--muted); + margin: 12px 0 4px; +} + +.caps { + display: flex; + flex-wrap: wrap; + gap: 8px; +} + +.cap-tile { + border: 1px solid var(--border); + border-radius: 8px; + background: var(--surface); + padding: 6px 12px; + min-width: 110px; +} + +.cap-label { + font-size: 11px; + color: var(--muted); +} + +.cap-value { + font-size: 18px; + font-weight: 700; +} + +.cap-value.warn { + color: var(--warn); +} + +.cap-max { + font-size: 12px; + font-weight: 400; + color: var(--muted); +} + +.queue-pos { + width: 3ch; + color: var(--muted); + flex-shrink: 0; +} + +.rate-limit + .rate-limit { + margin-top: 8px; +} + +.rate-limit .vendor { + color: var(--text); + font-weight: 700; + font-size: 13px; +} + +.rate-limit .resets { + margin-left: auto; +} + +.rl-status { + font-weight: 700; +} + +.rl-status.ok, +.rl-windows .ok { + color: var(--ok); +} + +.rl-status.warn, +.rl-windows .warn { + color: var(--warn); +} + +.rl-status.danger, +.rl-windows .danger { + color: var(--danger); +} + +.rl-windows { + border-collapse: collapse; + margin-top: 8px; + width: 100%; +} + +.rl-windows th, +.rl-windows td { + text-align: left; + padding: 2px 12px 2px 0; + border-bottom: 1px solid var(--border); +} + +.rl-windows th { + font-weight: 400; + font-size: 11px; + color: var(--muted); +} + +.kv { + display: grid; + grid-template-columns: max-content 1fr; + gap: 2px 16px; + margin: 8px 0 0; +} + +.kv dt { + color: var(--muted); +} + +.kv dd { + margin: 0; + word-break: break-word; +}