Code Review loops

Review loops that find and rank issues, then hand you the verdict instead of pushing fixes.

8 graded loops in this category.

Address review comments, fix CI

Loop/loop

Check your PR for new comments and CI failures, address them, then loop every 5 minutes until all pass.

prompt
→ Claude
/loop 5m check my PR, address review comments, and fix failing CI
reviewmedium riskclaude-code
⧉ 2source ↗

Map codebase with review prompt

Loop/ralphnew

Run a review prompt against your codebase repeatedly until the completion promise resolves, with no iteration cap.

prompt
→ Claude
/ralph-loop "<review prompt>" --completion-promise "CODEBASE MAP COMPLETE" . One ralph loop per discovered codebase (loops until the promise; no iteration cap per v3.8.0 unbounded solving
reviewmedium riskclaude-code

Review code changes until done

Loop/loop

Review the current change and iterate until you confirm the work is complete.

prompt
→ Claude
/loop Review the current change and continue until complete
reviewlow riskclaude-code

Codex Iterative Repair Loop (JSON-Schema Review → Repair)

Loop/ralph★ OpenAI

OpenAI's first-party loop recipe: a script alternates a Codex review pass that emits machine-readable findings with a repair pass fed those findings verbatim, looping until validation passes, attempts run out, progress stalls, or a decision needs human review.

prompt
→ Claude
Script alternates two `codex exec` calls: (a) review pass with a JSON schema output ("list remaining issues as machine-readable findings"), (b) repair pass fed those findings verbatim. Loop while findings remain, capped by max attempts. Stops for one of four reasons: validation passes, max attempts reached, remaining delta stops changing, or next decision needs human review.
reviewmedium riskclaude-code

Audit code diffs, ship clean

Loop/goal

Run code review on each step's diff, stop when zero findings or after 3 rounds.

prompt
→ Claude
/goal /codex review reports zero real-or-regression findings on every step's diff (the verdict pasted in full each round); or stop after 3 rounds, reporting anything unresolved
reviewlow riskclaude-codecodex
source ↗

Check codex-watch PRs

Loop/loop

Run every 15 minutes to find and display all open pull requests labeled codex-watch.

prompt
→ Claude
/loop 15m check every open PR labeled codex-watch Cap the run at 15 passes.
reviewlow riskcodex
source ↗

The nested perfect loop

Loop/loop

A loop wrapping a goal wrapping a review: every 30 minutes, drive all PR review comments to resolved via /review, 10 turns max per pass.

prompt
→ Claude
/loop 30m /goal all PR review comments resolved via /review, stop after 10 turns
reviewhigh riskclaude-code

Claude ships, Codex reviews

Loop/loopForward Future

Open a PR, run an independent Codex review, fix every blocking finding, and repeat until it's clean.

prompt
→ Claude
Run /clodex [task] think hard --max-iter 5 --threshold medium. Claude plans the task, implements it, opens a pull request, asks Codex for an adversarial review, fixes findings above the accepted severity, and repeats. Keep the branch, PR, findings, verdict, and iteration state resumable. Stop when Codex approves, only accepted findings remain, progress stalls, or the iteration cap is reached. Never describe an errored or exhausted run as approved. Finish with the PR, checks, verdict, and remaining findings.
reviewlow riskclaude-codecodex