agentleFS
Sign inStart free
zaxbysaucezaxbysauce/opencode-swarm/.agents/skills/ci-fix-monitor/SKILL.md

ci-fix-monitor

Skill517 starsChanged 3 days agoMITView on GitHub

Codex adapter for monitoring and fixing CI failures on opencode-swarm PRs. Use when diagnosing failed checks, fixing `package-check` (npm tarball) failures, resolving quality/lint/format errors, fixing macOS cross-platform file I/O failures, or watching a PR until all checks are green.

  • Deletes or force-pushes
  • Commits and pushes

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Read .opencode/skills/ci-fix-monitor/SKILL.md for the full protocol.

    line 10
  2. Very specific:

    After any source fix, run the focused test file (bun test <file>) before committing.

    line 25
  3. Very specific:

    Do not declare victory until ALL required checks show green.

    line 26

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

CI Fix Monitor

Read .opencode/skills/ci-fix-monitor/SKILL.md for the full protocol.

Also load:

  1. .agents/skills/commit-pr/SKILL.md before committing or pushing any fix
  2. .agents/skills/engineering-conventions/SKILL.md if the fix touches source files
  3. .agents/skills/running-tests/SKILL.md before running any test suite as part of a fix

Codex-specific execution notes:

  • MCP tool names (mcp__github__*) are injected by the runtime harness and may differ across environments. Verify availability via ToolSearch before first use in a session.
  • No gh CLI available. Use mcp__github__pull_request_read (method get_check_runs) to list check status and mcp__github__get_job_logs (with return_content: true) to fetch failure logs.
  • For package-check failures: package-check validates the npm tarball (npm pack + tarball contents). A failure is a source/build/package-manifest problem, not generated-file drift. dist/ is generated and NOT committed — do not stage it; run bun run build locally only when you need the bundle to verify (e.g. node --input-type=module -e "await import('./dist/index.js'); console.log('dist import OK')"). There is no longer a committed-dist drift check.
  • For a branch behind main (version-drift): git fetch origin main && git rebase origin/main (abort with git rebase --abort if conflicts occur and escalate to user), then git push --force-with-lease origin <branch>. Force-push is required and expected after rebase.
  • For format violations: bunx biome format --write <specific-file> — do NOT run biome format --write . on the whole repo.
  • After any source fix, run the focused test file (bun test <file>) before committing.
  • Do not declare victory until ALL required checks show green; skipped is acceptable only if the same check was skipped on the base branch.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free