Builder vs. reviewer, proving each test

A builder and an adversarial reviewer pass a git baton between worktrees, proving every new test can catch its fix.

Use this when

Use autonomy-loop when a repository has deterministic test, build, and lint gates plus a task suited to repeated builder-reviewer handoffs.

How it runs

1. Initialize autonomy-loop, configure deterministic gates and protected paths, and create separate builder and reviewer worktrees.
2. Have the builder read LOOP-STATE.md, implement one bounded change, add a red-before, green-after test, and hand off.
3. Have the reviewer rerun every gate and use revert-or-mutate proof to show the test catches the change.
4. Accept only on both passes; otherwise return findings or park the wave for a human when a circuit breaker fires.

Done when

✓ Every accepted wave passes autonomy-loop's proof-of-test gate. The new test fails without the change, passes with it, every configured gate passes, and protected production changes remain human-gated.

Why it works

Separate worktrees and a git-backed LOOP-STATE.md baton keep the roles independent and resumable. The revert-or-mutate check catches tests that execute code without proving the fix.

Implementation note

The source implementation uses autonomy-loop commands, separate worktrees, and a git-backed baton. Treat local hooks as tripwires, not a security boundary, and keep protected changes behind enforced approval.

Source: Forward Future ↗graded C · 65/100 — how grades work →

More testing loops