Borrowing it
Nothing to install: this file belongs to jmrplens/gitlab-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jmrplens/gitlab-mcp-server/main/.github/skills/update-starlight-docs/SKILL.mdgit clone --depth 1 https://github.com/jmrplens/gitlab-mcp-serverWrote 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/jmrplens/gitlab-mcp-server/update-starlight-docs)<a href="https://agentmods.dev/skills/jmrplens/gitlab-mcp-server/update-starlight-docs"><img src="https://agentmods.dev/badge/skills/jmrplens/gitlab-mcp-server/update-starlight-docs/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/jmrplens/gitlab-mcp-server/update-starlight-docs"><img src="https://agentmods.dev/badge/skills/jmrplens/gitlab-mcp-server/update-starlight-docs.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 | $0.00062 | $0.03999 |
| Opus 5.5 | $0.00025 | $0.01600 |
| Sonnet 5.5 | $0.00012 | $0.00800 |
| Haiku 4.5 | $0.00006 | $0.00400 |
Grade A, and why
update-starlight-docs scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSLO https://github.com/jmrplens/gitlab-mcp-server/releases/download/v%%VERSION%%/gitlab-mcp-server-linux-amd64 How it starts
The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Starlight Documentation
Update the Astro Starlight user documentation site to reflect code changes that affect user-facing features, configuration, or behavior.
Before Starting
- Identify what changed in the code that affects users
- Read the current Starlight docs structure:
site/src/content/docs/ - Determine affected pages (EN and ES)
- Check whether a generator writes the page or the figure (table below); if one does, change its source and run it instead of editing
Where Documentation Lives
The site is the only home of the user documentation, in English and Spanish. docs/ keeps contributor material only, under docs/development/, and the README is a short landing page that links the site (ADR-0025).
| Audience | Path | Format |
|---|---|---|
| Users | site/src/content/docs/ (English) and site/src/content/docs/es/ (Spanish) |
MDX (Starlight) |
| Contributors and AI agents | docs/development/, CLAUDE.md, AGENTS.md, .github/ |
Markdown |
Rule: a change to user-facing behavior updates the site page that describes it, in English and in Spanish, in the same change. A contributor-only change (a gate, a generator, a convention) goes to docs/development/ or CLAUDE.md, and never to the site. There is no second copy of a user page anywhere in the repository to keep in step.
Pages and data a generator writes
Never edit these by hand: change the source the generator reads, then run it. make update-all runs every Go command in this table, the benchmark through its redraw target; the last row is the site build's own.
| What | Source | Command |
|---|---|---|
reference/tools/<group>.mdx and its es/ twin, one page per catalog group, named after the group's tool name without gitlab_ and with hyphens (gitlab_merge_request is merge-request.mdx), and the index.mdx beside them |
the action catalog and cmd/gen_tool_reference/domains.json |
make gen-tool-reference |
reference/fine-grained-permissions.mdx and its es/ twin |
the handlers and docs/development/gitlab-api-live.json |
make gen-action-grants |
The block between {/*START BENCHMARK*/} and {/*END BENCHMARK*/} of performance/resource-benchmark.mdx in both languages, the charts under site/public/benchmarks/, and site/src/data/resource-benchmark.json |
a measurement of the binary | make bench-resources measures; make bench-resources-render redraws from the committed record |
site/src/data/stats.json, the counts (tools, meta-tools, actions, groups, resources, prompts) the pages print as {stats...} |
the catalog and the registered surfaces | make gen-site-stats |
site/src/data/token-footprint.json |
a token measurement of every tier, surface and meta schema mode | make gen-footprint |
The site's own /llms.txt and /es/llms.txt |
the content collection and the SECTIONS table of site/scripts/gen-llms.mjs |
written by pnpm run build, never committed |
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 Changed 0821ce865cd0
- 7d ago Changed 1a83ab51b5fd
- 12d ago Changed · +16 lines d9f1f107edb3
- 16d ago Changed · +43 lines · +18 tokens per session 364b3816a581
- 1mo ago Changed · +13 lines 41f28d35f45f
- 1mo ago Changed · -1 lines d7157ed6a919
- 1mo ago First seen · 120 lines · 44 tokens per session scan A 375921eae18e
update-starlight-docs is a skill published in the GitHub repository jmrplens/gitlab-mcp-server (46 stars, last pushed today), licensed MIT. It adds 62 tokens to every session and 3,999 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…
crit-story
Author a crit story and continue the interactive review loop only when the user explicitly invokes crit-story or directly asks you to generate a crit story. Do not infer this skill from generic review, PR, or diff-review requests.
snip
You are an expert at writing declarative YAML filters for snip, a CLI proxy that reduces LLM token consumption by filtering shell output.
goai
GoAI is a Go SDK for AI applications. One unified API across 25+ LLM providers. Inspired by the Vercel AI SDK, adapted to Go idioms (generics, interfaces, channels).
golang-benchmark
Run reproducible Go benchmarks, profiling, benchstat and CI regression analysis.
implement-rfc
Implement one RFC: check its predecessors, present a plan for approval, write the code, then demonstrate every acceptance criterion.