Which AI agents does this loop work with?

Claude ships, Codex reviews 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 reviewlow riskadvancedsafety C · 65 Forward Futurepre-dates current gate · under review

Claude ships, Codex reviews

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.

claude-code · codex

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.

Source: Forward Future ↗