Rig Implement

Read Evidence rules and Commit handoff.

Input

• A frozen plan.md with its digest, or a bounded change with explicit scope.
• Optional: kind = feature, fix, refactor, or perf.

Workflow

1. Revalidate the plan. Read current source and compare it with the plan's assumptions. If source contradicts the plan, stop and report; do not rewrite the plan.
2. Start the run. rig_evidence with action: "start", skill: "rig-implement", target paths, and the plan path. Record the plan digest.
3. Establish a baseline. Run the narrowest relevant test or reproduction before editing. For a refactor, capture characterization tests first.
4. Implement in batches. Group non-overlapping edits and their tests into one batch. Run the focused check after each batch. When a batch fails, bisect to the smallest edit so attribution is not lost.
5. Reconcile the scope. After the last edit and any formatter, call rig_evidence with action: "refresh" and a message naming what changed. This is the only way the run adopts edited source.
6. Run configured gates. Call rig_gate with action: "run" and the run ID. Fix failures and rerun the same gate. Never retry a failing gate unchanged, and never substitute a manual claim for a failed check. If a gate rewrites files, refresh the scope and rerun that gate.
7. Record outputs. rig_evidence with action: "record" for changed paths, limits, and any decision that future readers need.
8. Finalize. rig_evidence with action: "finalize". A failed gate or source drift blocks completion; drift means refresh and rerun, never editing the record.
9. Commit handoff. Propose the exact commit message and paths. A plain commit runs when the user asked for it or a local Git grant covers it; otherwise ask once. Never push.

Rules

• Do not touch paths outside the owned set without saying so and getting scope approval.
• Do not delete or weaken tests to reach green.
• Preserve unrelated working-tree changes.
• Keep the change minimal: no opportunistic refactors outside the plan.
• Report incomplete work as incomplete; a partial fix with a clear stop is valid.

Output

Report run ID, changed paths with digests, gate receipts, failed or skipped checks, remaining risks, and the commit handoff. Do not claim completion without a finalized run.