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/vosslab/vosslab-skills/setup-install-usage-docsnpx skills add vosslab/vosslab-skills --skill setup-install-usage-docsgit clone --depth 1 https://github.com/vosslab/vosslab-skillsWrote 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/vosslab/vosslab-skills/setup-install-usage-docs)<a href="https://agentmods.dev/skills/vosslab/vosslab-skills/setup-install-usage-docs"><img src="https://agentmods.dev/badge/skills/vosslab/vosslab-skills/setup-install-usage-docs.svg" alt="Measured on agentmods" 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 | $0.00059 | $0.01386 |
| Opus 5 | $0.00030 | $0.00693 |
| Sonnet 5 | $0.00012 | $0.00277 |
| Haiku 4.5 | $0.00006 | $0.00139 |
Grade A, and why
setup-install-usage-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 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.
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup, install, and usage docs
Goal
Write content-supported docs for:
docs/INSTALL.md: setup steps, dependencies, environment requirements.docs/USAGE.md: how to run the tool, CLI flags, practical examples.
Write a doc when repo evidence supports a real Requirements/Install section (INSTALL)
or a real Quick-start/CLI section (USAGE). Treat a basic runnable command, an entry
point, or a dependency manifest (pip_requirements.txt, pyproject.toml, Brewfile)
as install or usage evidence and write the doc from it; INSTALL and USAGE are
near-universal, so do not skip them when this evidence exists. Report the gap instead
of writing a file only when no such evidence exists, so the only content would be a
title plus "Known gaps".
Inputs to request
- Primary run mode: CLI, library, or both, and which one is the main entry point.
- Supported platforms, if known, including any OS or shell constraints already stated.
- One or two common real workflows users should be able to do, described as concrete tasks.
Workflow
- Inspect evidence
- Read
README.mdandAGENTS.mdwhen present to learn purpose, constraints, and any required environment notes. - Look for entry points and run commands (scripts,
pyproject.toml,setup.cfg,Makefile,tools/,bin/) and note what a user actually runs. - Identify dependencies and install method (pip editable, requirements file, system deps), and only record what is confirmed by repo files.
- Read
- Write or update docs
- Write a file when evidence supports a real Requirements/Install or Quick-start/CLI section; trim and correct stale files.
- Report the gap and write no file only when no real install or usage evidence exists.
- Keep doc naming under
docs/consistent with repo conventions.
- Keep docs minimal
- Prefer 2 to 6 bullets per section.
- Prefer one primary path and keep alternates out unless the repo makes them explicit.
- Include exact commands only when verifiable from repo evidence, not inferred.
- Target 40 to 120 lines per doc, and prefer linking to deeper docs when needed.
- Record uncertainty explicitly
- Add a "Known gaps" section with verification tasks only, written as TODO-style checks.
- Do not invent versions, OS support, or flags; leave them as gaps instead.
- Require a verify step on written INSTALL docs
- When evidence supports writing
docs/INSTALL.md, include a "Verify install" section with one command that proves the install worked in a fresh environment. - When no verifiable command and no real install evidence exist, report the gap
and write no
docs/INSTALL.mdfile.
- When evidence supports writing
- Troubleshooting only with evidence
- Add a troubleshooting subsection in
docs/INSTALL.mdonly when you can cite it from repo evidence (existing issues, error messages in scripts, known env vars, CI failures). - Otherwise do not include troubleshooting content or speculative fixes.
- Add a troubleshooting subsection in
- Document dry-run behavior when it exists
- If scripts that modify files expose a
--dry-runoption, document it indocs/USAGE.md. - Do not invent flags. If a dry-run is missing and would help, note it as a "Known gaps" task instead of adding unverified guidance.
- If scripts that modify files expose a
- Keep README scope separate
- Do not move README content here. If README needs pruning or restructuring, use the readme-docs skill and keep INSTALL/USAGE focused on setup and run steps.
- Update changelog
- Update
docs/CHANGELOG.mddirectly when this skill runs as a standalone task; underdelegate-manager-to-subagents, dispatch a docs subagent to add the entry.
- Update
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.
- 4d ago First seen · 137 lines · 59 tokens per session scan A 85afcacf42b3
setup-install-usage-docs is a skill published in the GitHub repository vosslab/vosslab-skills (2 stars, last pushed 8d ago), licensed MIT. It adds 59 tokens to every session and 1,386 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…