Move workflow file and TODO.md formats into the knowledge base

internal/agents/kb/todo-file.md

@@ -0,0 +1,20 @@
+The format of TODO.md, the project's list of work for byre: items, descriptions, sections and checked items.
+
+# TODO.md
+
+TODO.md at the repo root is the project's list of work for byre.
+
+- Each item is a top-level `- ` line holding only a short title. byre uses the title as the task's title and as the item's identity.
+- The item's description is in lines indented two spaces under it.
+- `#` headings group items into sections.
+- A checked `- [x]` item is skipped.
+
+```markdown
+# Agent UI
+- Fix login redirect
+  The redirect drops the query string after sign-in.
+  Keep the original path and query through the round trip.
+- [x] Drop the web app
+```
+
+Removing an item removes its title line and every indented line under it.

internal/agents/kb/workflow-files.md

@@ -0,0 +1,42 @@
+The YAML format of a workflow's file, which read_workflow returns and save_workflow takes: stages, after, base, model and teams.
+
+# Workflow files
+
+A workflow's file is YAML: an optional `description`, then `stages`. The workflow's name is not in the file. Unknown fields are refused.
+
+| Field | Meaning |
+|---|---|
+| `name` | One line, unique in the workflow. |
+| `after` | The names of the stages whose outputs it gets; it starts once all of them have finished. Absent means the previous stage in the list, and for the first stage none, so a file without `after` is a chain. `[]` means it starts from the brief. |
+| `base` | `parent`, the default: branch from the commit its one `after` stage finished at, or for a stage with none, from where the workflow was started. `main`: branch from the default branch. Refused on a stage with more than one `after` stage, which always branches from the default branch and is told the branches it can merge. |
+| `model` | Also picks the vendor: `gpt-*` models run on Codex, `gemini-*` models on Antigravity, every other model on Claude Code. |
+| `prompt` | The stage agent's instructions. |
+| `agents` | In place of `model`: a list of at least two, each with `name`, `model` and `prompt`, that runs the stage as a team. They work in the stage's one task and worktree and talk through a shared board; each gets the stage's `prompt` and then its own, and the first agent finishes the stage. |
+
+Every stage runs as its own task. Exactly one stage is final (no other stage comes after it), and cycles are refused.
+
+```yaml
+description: Build a change, review and test it in parallel, then fix what they found.
+stages:
+  - name: Build
+    model: claude-opus-5-5
+    prompt: Implement the brief.
+  - name: Review
+    after: [Build]
+    model: gpt-6.1-sol
+    prompt: Review the Build stage's work and list the problems.
+  - name: Test
+    after: [Build]
+    model: gemini-4-argon-high
+    prompt: Exercise the change and report what fails.
+  - name: Fix
+    after: [Review, Test]
+    agents:
+      - name: fixer
+        model: claude-opus-5-5
+        prompt: Fix every problem the reports list.
+      - name: checker
+        model: gpt-6.1-sol
+        prompt: Check each fix as the fixer lands it.
+    prompt: Merge the branches you are given and address both reports.
+```