byre/TODO.md

Bugs

M1 — One agent end to end

M2 — Seeing the work

• Reduce transcript noise Audit transcripts as they actually render for places where the noise can be cut.

M3 — Second vendor and review

• Continuous background review Enforce the codebase's standards and expectations regularly over the whole codebase, not in the light of a particular change.

M4 — Merging and history

M5 — Workflows

• Scheduled tasks A schedules table (project, cron, prompt or workflow) and a timer that creates the task the way the lead's create_task does, managed with lead tools and no UI, like workflows. Example: every Monday, run go vet ./... and gofmt -l and check docs/operations.md against the code. Claude Code Routines, Codex Automations, Copilot cloud automations, Devin, Factory and Conductor all schedule agents.

M6 — Fan-out

M7 — Inbox triage

M8 — macOS client

• Embed teamscale Embed the teamscale library in the server and the client. Ask ian for the detailed plan before starting.

• Phone app A native client for the phone over the same API, sharing the macOS client's SwiftUI code where it can. Every surveyed tool has one (Claude, Codex, Cursor and Conductor apps, GitHub Mobile, Superset for iPhone); it needs its own layout, since two half-width panes don't fit a phone.