Which AI agents does this loop work with?

Builder vs. reviewer, proving each test is written for claude-code, codex.

Is this loop safe to run unattended?

This loop is graded C (65/100) by looprepo's automatic safety evaluator, which checks for exit conditions, iteration budgets, verification steps, and scoping before publishing.

Loop/loop Testingmedium riskadvancedsafety C · 65 Forward Futurepre-dates current gate · under review

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.

prompt

→ Claude

Use autonomy-loop for [repository task] after the test, build, and lint gates pass. Run /autonomy-loop:autonomy-init, then start builder and reviewer in separate worktrees. The builder reads LOOP-STATE.md, makes one bounded change, and adds a red-before, green-after test. The reviewer reruns the gates and proves the test by reverting or mutating the fix. Accept only on both passes; park protected or repeated-failure work for a human. Finish with the commit, gate evidence, test proof, trust tier, and risks.

claude-code · codex

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

Initialize autonomy-loop, configure deterministic gates and protected paths, and create separate builder and reviewer worktrees.
Have the builder read LOOP-STATE.md, implement one bounded change, add a red-before, green-after test, and hand off.
Have the reviewer rerun every gate and use revert-or-mutate proof to show the test catches the change.
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 ↗

More testing loops

Stabilize flaky tests for good

Loop/goalForward Future

Measure the flakiness, fix one root cause at a time, and stop after a defined streak of stable full-suite runs.

prompt

→ Claude

Run [test suite] [N] times under the same conditions and list tests whose result changes. Fix the most frequent flake at its root cause—shared state, timing, ordering, or an external dependency—never with a blind sleep or retry. Run that test [N] times, then rerun the full suite. Repeat until [N] consecutive full-suite runs pass, progress stalls, or approval is required. Return each flake, root cause, fix, evidence, and justified quarantine.

testingmedium riskclaude-code codex

Build a todo CLI app with tests

Loop/ralphnew

Ralph autonomously builds a todo CLI application with comprehensive test coverage over multiple iterations until complete.

prompt

→ Claude

/ralph-loop "Build a todo CLI app with tests" --max-iterations 30

testinglow riskclaude-code

Kill flaky tests

Loop/loop

Run your test suite repeatedly, collect every intermittent failure, and fix or quarantine flaky tests until you get five consecutive green runs.

prompt

→ Claude

/loop run my test suite 20 times, collect every intermittent failure, fix or quarantine the flaky ones, and don't stop until you get 5 consecutive fully-green runs

testinghigh riskclaude-code cursor