Fix CI, ship the PR
Check your PR's CI status and fix failures until the build passes.
/loop 5m check my PR and fix CI , /schedule |
claude-code · codex · cursor · windsurf
More ci loops
Wait for CI so you don't have to
Poll gh pr checks every 10 minutes and get told when the PR is ready to merge, or a summary of which checks failed and why.
/loop 10m run `gh pr checks 1234`; if all pass, tell me it's ready to merge; if any fail, summarize which and why
cilow risk
Babysit many PRs at once
Keep every PR labeled codex-watch healthy: fix CI failures, rebase behind-main branches, and nudge pending reviewers on a 15-minute cadence.
/loop 15m check every open PR labeled `codex-watch` and keep each healthy: fix CI failures, rebase when behind main, and nudge if a review is pending
cihigh risk
Morning-triage harness with adversarial reviewer
A cron-fired skill that finds its own work (failed CI, new issues, recent commits), fans each finding out to an isolated worktree, gates every fix behind an adversarial reviewer that assumes the code is broken, and leaves draft PRs — merging stays human.
# .claude/skills/morning-triage/SKILL.md — fired by cron at 06:00
READ (discovery inputs): CI runs that failed since the last run (gh run list --status failure); issues opened in the last 24h; commits merged since yesterday; the previous ./state/triage.md.
JUDGE: for each candidate decide actionable NOW vs noise; blocks a release → P0; already tracked → skip. Keep only what is worth a worktree today — the loop picks, you don't hand it a list.
WRITE: append findings (finding | source | priority | status) to ./state/triage.md and commit it so tomorrow's run can read it.
HANDOFF: one git worktree per finding (git worktree add ../wt-<slug> -b fix/<slug>), MAX_PARALLEL=3 — capped by how many PRs a human can actually review, not by the machine.
VERIFY: a second subagent as adversarial reviewer — ROLE: adversarial code reviewer. ASSUME this code is BROKEN until proven otherwise; do not praise. CHECK in order: does it run (execute, don't read); run the tests and paste real output; edge cases the author skipped; does behavior match the ticket. VERDICT: PASS only if every check holds, otherwise REJECT with each reason listed. Maximum 3 attempts per finding, then log as blocked.
STOP (red lines): never merge, never delete, never push to main; anything uncertain goes to ./inbox/ for a human, NOT into a PR. Caps set before the first run: per-run timeout 45 minutes, daily budget $20. PRs open as drafts; merging stays human.
cimedium risk