Document td concurrency rule in CLAUDE.md and AGENTS.md

Sub-agents must never call td commands directly. Concurrent writes
from parallel agents corrupt the SQLite database. Only the
orchestrator manages td task lifecycle.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-03-19 19:33:21 -04:00
parent 3d41c623bc
commit 16ba4166f2
2 changed files with 5 additions and 0 deletions

View File

@@ -7,6 +7,7 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
- **Commit after every task**: When a task is complete, stage all changed files and create a git commit before marking the task done.
- **Keep documentation current**: Update `CLAUDE.md` with any new commands, architecture details, or setup steps introduced by your task. Update `PRD.md` only if scope/design decisions changed.
- **Mark tasks in td**: `td start <id>` when beginning, `td close <id>` when done.
- **Only the orchestrator touches td**: Sub-agents must never call `td` commands directly. Concurrent `td` writes from parallel agents corrupt the SQLite database. The orchestrator handles all `td start`/`td close` calls before and after delegating to sub-agents.
## Task Management