benefriches: Skill for Claude Code

.claude/skills/fix-ci/SKILL.md

fix-ci is a skill for Claude Code from incubateur-ademe/benefriches. It costs 94 tokens per session (1,807 once invoked), scanned A, original, MIT.

A workflow for diagnosing and fixing a failed GitHub Actions job, using the exact failing commit and a separate worktree for reproduction.

In plain words
What is it for?
Use it when a GitHub Actions run fails and you need to retrieve the error, reproduce it locally, apply a fix, and verify it.
Why use it?
It narrows the investigation to the real failure and keeps debugging changes isolated from the current working directory.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is incubateur-ademe/benefriches's own configuration. It tells Claude Code how to work on benefriches itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything benefriches configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is git worktree add -b fix/ci-<runId> ../benefriches-fix-ci-<runId> <headSha>.

Reuse

Borrowing it

Nothing to install: this file belongs to incubateur-ademe/benefriches. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/incubateur-ademe/benefriches/main/.claude/skills/fix-ci/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/incubateur-ademe/benefriches

Made for: Claude Code.

Wrote 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.

agentmods badge for fix-ci

README.md
[![agentmods](https://agentmods.dev/badge/skills/incubateur-ademe/benefriches/fix-ci/github.svg)](https://agentmods.dev/skills/incubateur-ademe/benefriches/fix-ci)
Your own site
<a href="https://agentmods.dev/skills/incubateur-ademe/benefriches/fix-ci"><img src="https://agentmods.dev/badge/skills/incubateur-ademe/benefriches/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.

agentmods 80×15 button for fix-ci

Your own site · 80×15
<a href="https://agentmods.dev/skills/incubateur-ademe/benefriches/fix-ci"><img src="https://agentmods.dev/badge/skills/incubateur-ademe/benefriches/fix-ci.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,807 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00094 $0.01807
Opus 5 $0.00047 $0.00903
Sonnet 5 $0.00019 $0.00361
Haiku 4.5 $0.00009 $0.00181

Measured 13d ago against content hash 2156cfea70b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

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 13d 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.

.claude/skills/fix-ci/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fix CI — diagnose and fix a failed GitHub Actions job run

Take a failed GitHub Actions run, deterministically identify what failed, reproduce it in an isolated worktree based on the exact failing commit, fix it, and verify green locally. Integration (commit/push/merge) is left to the user.

Determinism rule (non-negotiable)

All GitHub access goes through the fixed gh CLI commands documented below, with the flags shown. Do not use the browser MCP, do not hand-craft REST calls, and do not improvise alternative gh invocations. This keeps data-gathering reproducible.

Prerequisite: gh auth status must succeed. If not, stop and tell the user to run gh auth login.

Procedure

1. Resolve the run

  • If the user passed an argument, extract the run ID (and job ID if present):
    • From a URL like https://github.com/<owner>/<repo>/actions/runs/<id> → take <id>.
    • From .../runs/<id>/job/<jobId> → take <id> and <jobId>. A job URL names the exact job the user cares about, so carry <jobId> into step 2 to skip job selection.
    • From a bare number → use it directly.
  • If no argument, pick the latest failed run on the current branch:
    gh run list --branch "$(git branch --show-current)" --status failure --limit 1 \
      --json databaseId,headSha,headBranch,workflowName
    
    Take the first result. If none, report "no failed run found for this branch" and stop.
  • Fetch run metadata (single deterministic call):
    gh run view <id> --json databaseId,workflowName,headBranch,headSha,conclusion,jobs
    

2. Select the failed job

  • If a <jobId> came from a job URL (step 1), use that job.
  • Otherwise, from .jobs keep those with conclusion == "failure" and take the first one — picking deterministically (rather than asking) keeps the skill non-interactive. If more than one job failed, note in your final report that the others exist so the user can re-run /fix-ci for them.
  • Record the selected job's numeric id (.jobs[].databaseId) as <jobId> — step 3 uses it to scope the logs.
  • Classify — bail early on deploy/infra: if the job name matches deploy / scalingo / production / staging, this is not a code fix. Print a diagnosis from the logs (step 3) and stop — do not create a worktree or edit anything.

Read the full file on GitHub · 154 lines

Changes

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.

  1. 13d ago First seen · 154 lines · 94 tokens per session scan A 2156cfea70b5

Subscribe to this mod's changes

fix-ci is a skill published in the GitHub repository incubateur-ademe/benefriches (45 stars, last pushed 4d ago), licensed MIT. It adds 94 tokens to every session and 1,807 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

Verification & Quality Assurance

Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.

ruvnet/RuView · 36 tokens

smoke-test

Health smoke tests + auto-fix for gbrain installs (and OpenClaw services when present). Run after machine/container restarts or whenever something seems broken. Tests critical services, auto-fixes bounded local issues, and reports worker topology without starting daemons. Extensible via user-defined test scripts in…

garrytan/gbrain · 79 tokens

mcore-create-issue

Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.

NVIDIA/skills · 26 tokens

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 when it should be cached, or when outputs are empty or missing after a…

moonrepo/moon · 231 tokens

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.

Tracer-Cloud/opensre · 48 tokens

ci-triage

Classify CI failures — distinguish clear regressions from infra flakes and security-test failures. Produces structured failure reports.

cobusgreyling/loop-engineering · 28 tokens