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-publishgit 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-publish)<a href="https://agentmods.dev/skills/coboljunkie/gitlab-mcp/gl-publish"><img src="https://agentmods.dev/badge/skills/coboljunkie/gitlab-mcp/gl-publish/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-publish"><img src="https://agentmods.dev/badge/skills/coboljunkie/gitlab-mcp/gl-publish.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 | $0.00062 | $0.00450 |
| Opus 5 | $0.00031 | $0.00225 |
| Sonnet 5 | $0.00012 | $0.00090 |
| Haiku 4.5 | $0.00006 | $0.00045 |
Grade A, and why
gl-publish 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 8d 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
Publish Changes to GitLab
Use local git for checkout state, branches, staging, commits, and pushes. Use
the bundled GitLab MCP tools for project resolution and merge-request creation.
Use glab only as a fallback when it is installed and the MCP operation is
unavailable.
Workflow
- Inspect
git status --short, the current branch, the configured remotes, and the full intended diff. - Confirm that the changed files match the user's requested scope. Preserve unrelated work and do not stage it.
- If a new branch is needed, follow the repository's documented branch naming
convention when one exists; otherwise use
gitlab/<short-description>. - Run focused tests or checks appropriate to the change.
- Stage only the intended files and review the staged diff.
- Create one clear commit unless the user requested a different history.
- Push the branch to the resolved GitLab remote.
- Use
create_merge_requestto open a draft merge request with:- a concise title;
- a summary of the change;
- verification performed;
- known limitations or follow-ups.
- Read back the merge request and return its URL.
Guardrails
- Do not include unrelated, generated, credential, or secret files.
- Do not rewrite history, force-push, delete branches, merge, or mark the merge request ready unless explicitly requested.
- Do not claim success until the push and merge-request creation both succeed.
- If tests fail, report the failure and stop before publishing unless the user explicitly directs otherwise.
- If the current branch already has unrelated commits, pause before building a merge request on top of them.
Output
Return the branch, commit, tests, and draft merge-request URL. Clearly identify anything not published.
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.
- 8d ago First seen · 47 lines · 62 tokens per session scan A 98a42e0b3350
gl-publish is a skill published in the GitHub repository CobolJunkie/gitlab-mcp (0 stars, last pushed 21d ago), licensed MIT. It adds 62 tokens to every session and 450 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 2026-08-31.
Other skills, from other repositories
security-pipeline
Use when security verification is needed - pre-commit security checks, vulnerability scanning, STRIDE threat analysis. Integrates with /handoff-verify --security and /commit-push-pr. CWE Top 25 based.
github-commenting
How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules. Load before posting or fixing any PR comment.
git-pushing
Stage, commit, and push git changes with conventional commit messages. Use when user wants to commit and push changes, mentions pushing to remote, or asks to save and push their work. Also activates when user says "push changes", "commit and push", "push this", "push to github", or similar git workflow requests.
commit-msg
You receive a git diff of staged changes via stdin. Generate a commit message.
ag-rebobinar
Undo estruturado. Reverte N acoes do Claude com log detalhado do que foi desfeito. Vai alem de git checkout — rastreia mudancas por sessao, arquivo, e commit, com opcao de revert seletivo.
ag-versionar-codigo
Gerencia git - branches, commits semanticos, PRs, releases e changelog. Use ao final de cada fase ou feature para manter historico limpo.