Completion Audit

When to use

• Wrapping up a long / multi-stage task, or any task that produces user-visible artifacts (runs, dashboards, reports, exports).

Procedure

1. Enumerate the touched files / user-visible surfaces this task changed.
2. Reconcile: compare the plan/objective against expectations expressed in the thread (not just what's written in the plan). Differences are surfaced, never silently dropped.
3. Map each touched surface to a check in the protected acceptance_manifest.yaml (read-only). Any user-visible surface with no check → record in review_queue.yaml and mark blocked.
4. Gather real evidence paths (actual artifacts/configs), not run_state assertions.
5. Write completion_candidate.yaml (your proposal; status = candidate_complete).
6. Invoke the external gate: check_acceptance.py --manifest ... --inventory ... --candidate ... --repo .

Outputs

• completion_candidate.yaml (proposal only)
• review_queue.yaml (blocking open items)
• gate result (PASS → an external verifier may grant complete; FAIL/any review item → blocked)