codex-watch-pr
Skill118 starsChanged 37 days agoMITView on GitHub
Wait for a pull request's checks to settle in one long-running command, then report passed, skipped, and failed jobs with run links. Use whenever the user asks Codex to watch a pull request or wait for CI, and whenever another workflow needs the result before continuing.
In this repository32 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- analyze-sessionSkill
- codex-analyze-sessionSkill
- codex-commitSkill
- codex-fix-proseSkill
- codex-fix-prSkill
- codex-merge-prSkill
- codex-prSkill
- codex-rebaseSkill
- codex-resolve-rebase-conflictsSkill
- codex-review-commit-messageSkill
- codex-review-pr-descriptionSkill
- codex-review-prose-fixSkill
- codex-review-squash-messageSkill
- codex-write-pr-descriptionSkill
- codex-write-prose-fixSkill
- commitSkill
- fix-proseSkill
- fix-prSkill
- merge-prSkill
- prSkill
- rebaseSkill
- releaseSkill
- resolve-rebase-conflictsSkill
- review-commit-messageSkill
- review-pr-descriptionSkill
- review-prose-fixSkill
- review-squash-messageSkill
- watch-prSkill
- write-pr-descriptionSkill
- write-prose-fixSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 9
Use the pull request number in the task, or omit it for the current branch's open pull request.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Watch a pull request
Use the pull request number in the task, or omit it for the current branch's open pull request. Start one blocking command with a long yield:
bash .agents/skills/codex-watch-pr/scripts/watch-checks.sh <number>Set the execution yield to at most 30 seconds. If it returns a running session, continue it with write_stdin using empty input and a wait of up to 300 seconds. Keep waiting on that same session. Don't start another watcher or poll gh pr checks between waits. Send a concise progress update at least once a minute while checks remain pending.
The script emits PASS, SKIP, and FAIL events and closes with ALL GREEN, FAILED, TIMEOUT, or NO CHECKS. Exit codes are 0 for green, 1 for failures, and 2 for timeout or absent checks. Timeout and absent checks are inconclusive, not failures. Report the pull request, failed jobs, and printed run links. Invoke codex-fix-pr only when the caller requested remediation.
PR_CHECKS_TIMEOUT and PR_CHECKS_INTERVAL override the script bounds in seconds.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

