Borrowing it
Nothing to install: this file belongs to ReviewStage/stage-cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ReviewStage/stage-cli/main/.agents/skills/fixing-ci/SKILL.mdgit clone --depth 1 https://github.com/ReviewStage/stage-cliWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/reviewstage/stage-cli/fixing-ci)<a href="https://agentmods.dev/skills/reviewstage/stage-cli/fixing-ci"><img src="https://agentmods.dev/badge/skills/reviewstage/stage-cli/fixing-ci/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/reviewstage/stage-cli/fixing-ci"><img src="https://agentmods.dev/badge/skills/reviewstage/stage-cli/fixing-ci.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00036 | $0.00964 |
| Opus 5.5 | $0.00014 | $0.00386 |
| Sonnet 5.5 | $0.00007 | $0.00193 |
| Haiku 4.5 | $0.00004 | $0.00096 |
Grade A, and why
fixing-ci scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fixing CI
Overview
Diagnose failing CI from GitHub logs, fix each issue with an atomic commit, and iterate locally until the full suite is green — then push once.
Principle: One fix, one commit. Never push until all checks pass locally.
Workflow
1. DIAGNOSE → Pull failure logs from GitHub, list all failures
2. For each failure:
a. REPRODUCE → Run the failing check locally to confirm you see it
b. FIX → Fix root cause (not downstream symptoms)
c. VERIFY FIX → Re-run the check to confirm it passes
d. COMMIT → Atomic commit for this fix
3. VERIFY ALL → Run the full suite locally
↳ If anything fails → go back to step 2
↳ All green → proceed
4. PUSH → Push all commits
Step 1: Diagnose
# See recent CI runs on current branch
gh run list --branch $(git branch --show-current) --limit 5
# View failing run (find run-id from above)
gh run view <run-id>
# Stream logs from only the failed steps
gh run view <run-id> --log-failed
Read top-to-bottom and list all distinct failures before fixing any of them. Find the first error in each job — not symptoms that cascade from it.
Step 2: Fix Loop (repeat per failure)
a. Reproduce
Check the project's AGENTS.md for exact commands. Common mappings:
| CI Job | Typical Local Command |
|---|---|
| Lint | pnpm lint |
| Typecheck | pnpm typecheck |
| Tests | pnpm test |
| Build | pnpm build |
Run the failing check and confirm you see the same error locally before touching code.
b. Fix
- Fix the root cause — lint errors often cascade from a single type error upstream
- Don't fix just to silence the error; understand why it's wrong
- If the fix is unclear, read the relevant library docs or AGENTS.md before guessing
c. Verify the Fix
Re-run the specific check to confirm it passes before committing.
d. Commit
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 110 lines · 36 tokens per session scan A 43ef23f43638
fixing-ci is a skill published in the GitHub repository ReviewStage/stage-cli (274 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 964 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
repair-github-ci
Fix failing GitHub CI / Actions checks via fixgithubprci and push to the existing PR head, or fix a branch's failing CI via a linked repair worktree.
mcore-create-issue
Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.
debug-task
Diagnose and fix moon tasks that are broken, misconfigured, or behaving unexpectedly. Use this skill when a moon task is failing, not running, skipped, hanging, producing stale or wrong output, cached when it shouldn't be, re-running every time, or missing outputs after a cache hit. Also covers pipeline hangs, tasks…
operating-github-ci-fixer
Use when the user asks OpenSRE to fix failing GitHub CI, GitHub Actions checks, failing pull request checks, a broken PR branch, or CI on a named branch such as main.
meta-long-running-build-watchdog
Watches a long-running command via tmux, lets sub-agent diagnose failures and propose a fix, and records the diagnosis to memory. Designed for overnight model fine-tunes, CI image builds, or repeated regression suites that may fail intermittently.
gh-fix-ci
Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use gh to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.