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 agentmods add skills/neeeophytee/agent-stylebooks/gitlab-docsnpx skills add Neeeophytee/agent-stylebooks --skill gitlab-docsgit clone --depth 1 https://github.com/Neeeophytee/agent-stylebooksWhat 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 | $0.00058 | $0.00747 |
| Opus 5 | $0.00029 | $0.00374 |
| Sonnet 5 | $0.00012 | $0.00149 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
gitlab-docs 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitLab docs
Create brief, direct product documentation that functions as a trustworthy source of truth.
Preserve technical truth
- Keep commands, code, product names, UI labels, versions, defaults, and results exact.
- Do not convert an implementation detail into a product promise.
- Separate confirmed behavior from a workaround, hypothesis, or planned behavior.
- Ask for missing availability, permission, or version facts instead of inventing them.
Choose a topic type
Select one primary purpose per topic:
- Concept: explain what something is, why it matters, and how parts relate.
- Task: help the reader achieve one outcome through ordered actions.
- Reference: present fields, options, syntax, or limits in a predictable structure.
- Troubleshooting: connect a symptom to checks, causes, and recoveries.
Split a page when these purposes compete. A short context paragraph may introduce a task, but do not bury the first action under a conceptual essay.
Write from the customer's perspective
- Lead with what the reader can accomplish or needs to know.
- Address the reader as
youfor user actions. Name GitLab or another component when the product performs the action. - Prefer active voice, but use passive voice when the actor is irrelevant and the result is clearer.
- Use concise, conversational sentences without chatty asides.
- Keep one term for each feature. Match the product's visible labels and casing.
- State facts and achievable outcomes. Qualify performance or security claims.
- Write for translation: use explicit subjects, literal language, and straightforward sentence order.
Build tasks and troubleshooting
- Put prerequisites, permissions, and availability before the steps.
- Start steps with imperative verbs and keep each action observable.
- Explain the expected result after the action.
- Include verification when configuration changes are not immediately visible.
- For failures, begin with the symptom the reader sees. Then give checks in the least expensive useful order and make recovery consequences clear.
- Use fake data and reserved example domains. Never expose real credentials.
What ships with it
2 files 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.
- 3d ago First seen · 79 lines · 58 tokens per session scan A e7f3ca605146
gitlab-docs is a skill published in the GitHub repository Neeeophytee/agent-stylebooks (57 stars, last pushed 10d ago), licensed MIT. It adds 58 tokens to every session and 747 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 2026-08-30.
Other skills, from other repositories
readme
Create, redesign, audit, or update a repository README.md by inspecting the actual project; write accurate setup and usage guidance with a selectable brand voice, polished information architecture, evidence-based badges and claims, discoverability suggestions, and an optional editable SVG/PNG banner. Use when the user…
yapper
Yapper forces AI responses to be maximally verbose, thoroughly elaborated, and exhaustively explained. All output is expanded by 200–400%. Technical accuracy is maintained at 100%. This plugin is the structural and philosophical inverse of compression-based plugins.
golden-rss
Use when testing the rss golden build.
agy-delegate
Delegate a coding task to the Google Antigravity CLI (agy) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Antigravity or agy - phrasings like "have Antigravity do X", "delegate this to agy", "run it through agy", or "use…
gcloud-usage
This skill should be used when user asks about "GCloud logs", "Cloud Logging queries", "Google Cloud metrics", "GCP observability", "trace analysis", or "debugging production issues on GCP".
spk-team-auth
Handle Spec Kitty team authentication, hosted credentials, account selection, and auth-related recovery.