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 structured-world/gitlab-mcp --skill gitlab-discoverygit clone --depth 1 https://github.com/structured-world/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/structured-world/gitlab-mcp/gitlab-discovery)<a href="https://agentmods.dev/skills/structured-world/gitlab-mcp/gitlab-discovery"><img src="https://agentmods.dev/badge/skills/structured-world/gitlab-mcp/gitlab-discovery/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/structured-world/gitlab-mcp/gitlab-discovery"><img src="https://agentmods.dev/badge/skills/structured-world/gitlab-mcp/gitlab-discovery.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 | $0.00047 | $0.00361 |
| Opus 5.5 | $0.00019 | $0.00144 |
| Sonnet 5.5 | $0.00009 | $0.00072 |
| Haiku 4.5 | $0.00005 | $0.00036 |
Grade A, and why
gitlab-discovery 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 4d 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
Find the GitLab target
Use tools from the selected GitLab connection. Read manage_context with {"action":"show"} when the account/namespace is unclear. Existing namespace restrictions remain authoritative; do not switch accounts or broaden scope to get around a missing result.
- Find a named project with
browse_projects, for example{"action":"search","q":"backend","per_page":20,"page":1}. For projects in a known group use{"action":"list","group_id":"example-group","per_page":20,"page":1}.browse_namespacesprovides namespace discovery when the target is a group. - Select the exact returned
path_with_namespaceor project ID. If several results fit and conversation context cannot resolve them, ask for the target; do not guess from the first result. - Inspect the selected project with
{"action":"get","project_id":"example-group/backend"}. Explain the returned identity and accessible repository details, then use that same project for follow-ups. - Retrieve additional pages only as needed to satisfy the request. For an empty result, report that nothing matched within this account/scope. On a tool error, diagnose access instead of claiming the project does not exist.
For subsequent MR review, work items or CI investigation, reuse the verified project identity and load the corresponding installed skill using its host-provided path. Do not assume a repository checkout or an absolute skill installation directory. This discovery workflow performs no GitLab mutations.
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.
- 4d ago First seen · 16 lines · 47 tokens per session scan A 220d595b0d81
gitlab-discovery is a skill published in the GitHub repository structured-world/gitlab-mcp (8 stars, last pushed today), licensed Apache-2.0. It adds 47 tokens to every session and 361 once invoked, about $0.0002 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 2026-10-10.
Other skills, from other repositories
report-issue
File a bug or feature request against this repository (cyanheads/git-mcp-server) using the gh CLI. Use for tool logic bugs, git provider misbehavior, transport issues, auth/config problems, or new feature proposals.
feedback-nudge
Use when the user wants to report a bug, request a feature, or send feedback to the Zooza engineering team. Also offer proactively after a successful commit operation (max once per week).
release-and-publish
Ship a release end-to-end across every registry the project targets (npm, MCP Registry, GitHub Releases for .mcpb bundles, GHCR). Runs the final verification gate, fast-forwards main when the release rode a release PR, creates the annotated tag on the commit main now points at, pushes commits and tags, then publishes…
release-and-publish
Ship a release end-to-end across every registry the project targets (npm, MCP Registry, GitHub Releases for .mcpb bundles, GHCR). Runs the final verification gate, fast-forwards main when the release rode a release PR, creates the annotated tag on the commit main now points at, pushes commits and tags, then publishes…
git-wrapup
Land working-tree changes as logical commits — the work grouped by concern, topped by a release commit (version bump, changelog, regenerated artifacts). The work commits land first, then the version bump, verification, and the release commit on top. Stops at "committed locally on main" — or, when the project releases…
orchestrations
Pick and run a multi-phase workflow that chains foundational task skills (git-wrapup, release-and-publish, maintenance, field-test, setup, etc.) end-to-end. Routes user intent to a workflow file under workflows/ — greenfield builds, maintenance + release, field-test + fix, or known-work + release. Single source for…