execution-checklistlisted

# Execution checklist Three-section self-check at task wrap-up. Per-reply mandatory, conditional when triggers fire, task-end book-keeping. > Source: the project's execution policy (typically > `.claude/rules/execution-policy.md`). This skill carries the long-form > checklist so the policy rule itself stays index-sized. ## Usage - **Not every reply needs this** — small change / pure research → skip. - **Load it at wrap-up** — after the final Edit/Write, before emitting the Conclusion, before `smart-commit`. - **Honour the chain rule** — sentinels already trigger their reviewer via hooks; this skill backstops the AI-judgment calls the hook system cannot see. --- ## Per-reply (always check when the turn included Edit/Write) Four boxes must clear: 1. **TDD pre-run** — Bug fix / feature that touches business logic: did `tdd-guide` (or the configured first agent in `review_agents`) run in the RED phase, writing the failing test first? Skip for pure docs / harness / hook edits. 2. **Final gate ran** — After the Edit/Write, the matching reviewer slot (code / db / sec / frontend / doc per `review_agents`) either ran, or has an explicit "self-accountable skip" reason recorded (e.g. all sentinels clean already, session-local agent dispatch unavailable, pure review-feedback fixup). 3. **Output structure complete** — `Conclusion → Changed files → Verification → Risks/Open questions`. When blocked: `Blocker → Tried → Next viable option`. 4. **Edit-