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 CobolJunkie/gitlab-mcp --skill gl-fix-cigit clone --depth 1 https://github.com/CobolJunkie/gitlab-mcpWrote 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/coboljunkie/gitlab-mcp/gl-fix-ci)<a href="https://agentmods.dev/skills/coboljunkie/gitlab-mcp/gl-fix-ci"><img src="https://agentmods.dev/badge/skills/coboljunkie/gitlab-mcp/gl-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/coboljunkie/gitlab-mcp/gl-fix-ci"><img src="https://agentmods.dev/badge/skills/coboljunkie/gitlab-mcp/gl-fix-ci.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00070 | $0.00435 |
| Opus 5.5 | $0.00028 | $0.00174 |
| Sonnet 5.5 | $0.00014 | $0.00087 |
| Haiku 4.5 | $0.00007 | $0.00044 |
Grade A, and why
gl-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 2mo 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.
What it actually says
Fix GitLab CI
Use the bundled GitLab MCP tools for pipeline, job, log, artifact, and commit
status inspection. Use local git for code changes and local verification.
Workflow
- Resolve the project and merge request, branch, commit SHA, pipeline ID, or job ID from the request and current checkout.
- For a merge request, call
list_merge_request_pipelines, then inspect the most relevant failed or running pipeline withget_pipeline. - Call
list_pipeline_jobsand inspect failed, canceled, or blocked jobs. - Fetch only the relevant bounded log section with
get_job_log. Retrieve a specific artifact file withget_job_artifact_fileonly when logs are insufficient. - Separate the first causal failure from downstream or canceled noise.
- Explain the root cause with job names, failure evidence, and affected files.
- If the user asked for a fix, make the smallest scoped change in the local checkout and run the closest practical local checks.
- Recheck the resulting diff and report what should change in the next pipeline.
Guardrails
- A diagnosis request does not authorize editing code or CI configuration.
- Do not retry, cancel, or play jobs or pipelines unless the user explicitly requested that state change.
- Do not print or preserve access tokens, masked variables, credentials, or secrets that appear in logs or artifacts.
- Avoid downloading broad artifact archives; request only a named file.
- Do not claim the remote pipeline is fixed until a new pipeline verifies it.
Output
Lead with the root cause. Distinguish observed remote evidence, local changes, local verification, and any remaining remote verification step.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 42 lines · 70 tokens per session scan A 2be963bdbec4
gl-fix-ci is a skill published in the GitHub repository CobolJunkie/gitlab-mcp (0 stars, last pushed 28d ago), licensed MIT. It adds 70 tokens to every session and 435 once invoked, about $0.0003 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 2026-08-31.
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.