Claude ships, Codex reviews
Open a PR, run an independent Codex review, fix every blocking finding, and repeat until it's clean.
Use this when
Use Clodex when Claude is building a meaningful code change and Codex should independently review each repair round.
How it runs
- Choose the task, thinking level, maximum iterations, and highest acceptable finding severity.
- Have Claude plan, implement, verify, and open the pull request through Clodex.
- Run the Codex adversarial review, fix blocking findings, push, and review again.
- Persist state across rounds and finish with the verdict, remaining findings, checks, and pull-request link.
Done when
✓ The pull request reaches the configured review bar. Codex approves it or only explicitly accepted findings remain; errors, stalls, and exhausted limits are reported as such.
Why it works
Clodex separates the Claude builder from the Codex reviewer and turns review feedback into a bounded repair loop. Persisted state keeps the work resumable without treating an interruption as approval.
Implementation note
The source implementation uses Clodex with Codex as the adversarial reviewer. Treat the severity threshold as a ceiling for acceptable findings, not a minimum severity to inspect.
More review loops
Map codebase with review prompt
Run a review prompt against your codebase repeatedly until the completion promise resolves, with no iteration cap.
Address review comments, fix CI
Check your PR for new comments and CI failures, address them, then loop every 5 minutes until all pass.
The nested perfect 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.