Check codex-watch PRs

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.
codex

Use this when

You have a PR label that marks work an agent is producing or watching, and you want a recurring read-only status sweep every 15 minutes instead of refreshing GitHub yourself.

Done when

Every pass should print the PR list it found; an empty result is a valid answer, not a failure. Because it only reads, the meaningful check is that the label filter is right — a mistyped label reports "nothing open" forever and looks identical to a quiet queue.

Why it works

It is deliberately the smallest useful loop: fixed interval, read-only, one label. Nothing it does can damage a branch, which makes it the right first loop to run if you have never left an agent on a schedule before. Cap the run at 15 passes so a forgotten loop expires on its own.

Source: serenakeyitangraded C · 70/100 — how grades work →

More review loops

The nested perfect loop

Loop/loopGitHubB

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

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.

Review and self-fix changes to clean

Loop/goalGitHubBnew

Review diffs iteratively, validate findings, self-fix each one, and restart until zero critical/high/medium issues remain.

prompt
→ Claude
/goal changes-review self-recursive loop: review the full diff → run /why-review --validate-findings on every finding → SELF-FIX each validated finding → restart /changes-review from Phase 0 over the WHOLE updated diff (combined with the prior fixes, not just the last fix) → loop until one complete review pass clears that round's bar (rounds 1-2: zero findings; round 3+: zero CRITICAL/HIGH/MEDIUM, a LOW-only round ENDS the loop with the LOWs recorded as deferred) → then run Phase 7.5: one standalone FULL-mode /why-review over the whole target+diff (NOT --validate-findings), fixing and re-running until it is clean → only then run the Phase 8 /docs-update. Do not stop while any validated finding is unfixed, any review pass is non-clean, or the holistic full-mode /why-review has unaddressed findings