Which AI agents does this loop work with?

Ralph a refactor, module by module is written for claude-code, codex.

Is this loop safe to run unattended?

This loop is graded B (75/100) by looprepo's automatic safety evaluator, which checks for exit conditions, iteration budgets, verification steps, and scoping before publishing.

/ralph refactoringhigh riskadvancedsafety B · 75 · open-ended Geoffrey Huntley

Ralph a refactor, module by module

Break a large refactor into a JSON backlog of modules and let fresh-context iterations convert one module per pass, with guardrails capturing every pattern decision so the result stays consistent.

prompt

→ Claude

/loop fresh context each iteration: read refactor-plan.json and .ralph/guardrails.md, take the next module not marked converted, migrate it to the target pattern described in PROMPT.md, run tests and typecheck, and mark it converted only when green; record every convention decision you make (naming, file layout, error handling) in .ralph/guardrails.md so later modules match earlier ones; stop when all modules are converted or after 30 turns

claude-code · codex

Implementation note

The guardrails file is what keeps module 27 stylistically identical to module 2 despite each iteration knowing nothing about the last. Review it after the first few passes and correct any convention you dislike early.

Source: Geoffrey Huntley (Ralph technique) ↗

More refactoring loops

Migrate an API import by import

/goalnew

Sweep a codebase from a legacy API to its v2 replacement with tests and typecheck as the safety net, capped at 30 turns.

prompt

→ Claude

/goal every file importing from `./legacy-api` now imports from `./v2-api`, all tests pass, and `npm run typecheck` is clean — stop after 30 turns

refactoringmedium risk

Dead code elimination

/goalloopreponew

Hunt down unreferenced exports, unused files, and unreachable branches, deleting them in small verified steps until the analyzer reports clean.

prompt

→ Claude

/goal `npx knip` reports no unused files or exports — remove one cluster of dead code at a time, run the full test suite and typecheck after each removal, and revert any deletion that breaks them; stop after 15 turns

refactoringmedium risk

Tidy code, one safe change at a time

/loopForward Futurenew

Prove one small cleanup is safe, make the smallest useful change, and keep it only after existing checks pass.

prompt

→ Claude

Review [repository or code project] for dead code, meaning unreachable or unused code; stale files or comments; unused dependencies; duplication; broken links; inconsistent names; and confusing structure. Protect unrelated, active, uncommitted, generated, and uncertain work. Prove one low-risk cleanup, make the smallest coherent change, then rerun the build, tests, runtime checks, and diff review. Keep only verified improvements. Stop when none remain, progress stalls, verification is unavailable, or approval is required. Return changes, evidence, and deferred candidates.

refactoringmedium risk