Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ulises-jeremias/agent-toolkit --skill gh-fix-cigit clone --depth 1 https://github.com/ulises-jeremias/agent-toolkitWrote 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/ulises-jeremias/agent-toolkit/gh-fix-ci)<a href="https://agentmods.dev/skills/ulises-jeremias/agent-toolkit/gh-fix-ci"><img src="https://agentmods.dev/badge/skills/ulises-jeremias/agent-toolkit/gh-fix-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/ulises-jeremias/agent-toolkit/gh-fix-ci"><img src="https://agentmods.dev/badge/skills/ulises-jeremias/agent-toolkit/gh-fix-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 | $0.00053 | $0.01119 |
| Opus 5 | $0.00026 | $0.00560 |
| Sonnet 5 | $0.00011 | $0.00224 |
| Haiku 4.5 | $0.00005 | $0.00112 |
Grade A, and why
gh-fix-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 6d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix Failing PR Checks
Inspect failing GitHub Actions checks on a PR with gh, fetch run logs, extract
a focused failure snippet, propose a fix plan before making any change, and iterate
until green.
When to use
- A PR has red checks and the user asks to "fix CI", "debug the failing job", or "why is the build red".
- You need a fast triage of which jobs failed and the relevant log slice.
- Branch or PR CI is failing and needs a fast, iterative path to green checks.
Prerequisites
ghinstalled and authenticated (gh auth statusexits 0).doctorreports this under Integrations.python3for the bundled analyzer.- The current directory is inside the target Git repository (or pass
--repo).
Workflow
-
Verify auth.
gh auth status. If unauthenticated, ask the user to rungh auth login(repo + workflow scopes typically required). -
Resolve the PR. Defaults to the current branch's PR, or pass
--pr. -
Inspect checks as source of truth. Use
gh pr checksas the source of truth for overall PR CI state (it includes all PR-attached checks, whilegh run listonly covers GitHub Actions):gh pr checks --json name,bucket,state,workflow,linkFor pending checks,
gh pr checks --watch --fail-fast. -
Run the analyzer:
python3 ~/.local/share/agent-toolkit/skills/gh-fix-ci/scripts/inspect_pr_checks.py \ --repo . --pr <number-or-url>- Add
--jsonfor machine-friendly output suitable for further processing. - Add
--max-lines <n>/--context <n>to widen the snippet window.
The script handles
gh pr checksfield drift, falls back to job-level logs when run-level logs are not yet available, and exits non-zero when failures remain (so it composes in CI / scripts). - Add
-
Scope external providers. Any check whose
detailsUrlis not a GitHub Actions run is reported asexternalwith only the URL — do not attempt to fetch logs from Buildkite/CircleCI/etc. Use the check link to identify the failing command or service when logs are unavailable. -
Summarize. For each failing check report: name, run URL, conclusion, workflow, branch/SHA, and the failure snippet (or "logs pending" if the run is still in progress). Identify the primary failing job and root error.
-
Draft a plan. Propose the fix as a short, numbered plan. Do not edit files yet. If the project has a planning skill (e.g.
planning), delegate the plan structure to it. -
Implement after approval — one failure at a time. Once the user approves the plan, apply the smallest safe fix. Prefer minimal, low-risk changes before broader refactors. Summarize the diff and delegate the push/PR-update step to
github-cli-workflow. -
Recheck and iterate until green. Re-run
gh pr checksafter each push; the check set can change. If checks already failed, diagnose those first; if pending, watch with--watch --fail-fast. Repeat steps 4-8 for the next actionable failure until all required checks are green. Suggest re-running relevant tests locally between iterations.
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.
- 6d ago First seen · 105 lines · 53 tokens per session scan A a8137bb752a7
gh-fix-ci is a skill published in the GitHub repository ulises-jeremias/agent-toolkit (16 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 1,119 once invoked, about $0.0003 per session on Opus 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 2026-09-04.
Other skills, from other repositories
ci-debug-loop
Watch a GitHub Actions CI run, diagnose failures from logs, apply fixes, re-push, and repeat until green or escalate. Use when CI is failing and the user wants to debug and fix it iteratively, or says "fix CI", "debug the build", or similar.
GitHub CI Fix Debugging
Debug and fix failing GitHub PR checks by inspecting GitHub Actions logs, summarizing failure context, drafting fix plans, and implementing fixes after approval.
skillnote-doctor
A diagnostic tool for OpenClaw agents -- checks skill registry connectivity, AGENTS.md setup, config file validity, and installed skill health. Use when your setup seems broken, skills aren't loading, or you want to audit your agent's configuration.
chatcrystal-debug-recall
Recall ChatCrystal memories for debugging tasks involving failing tests, compiler errors, runtime exceptions, dependency issues, environment breakage, or performance regressions. Use when historical root causes, fixes, or pitfalls may accelerate diagnosis before proposing a fix.
github-actions-debugger
Debug and monitor GitHub Actions workflow runs. Check run status, view failed job logs, and troubleshoot CI failures. Use this when the user needs to investigate GitHub Actions failures, inspect job output, or identify the root cause of a broken workflow run.
gitlab-pipeline-debugger
Debug and monitor GitLab CI/CD pipelines for merge requests. Check pipeline status, view job logs, and troubleshoot CI failures. Use this when the user needs to investigate GitLab CI pipeline issues, check job statuses, or view specific job logs.