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 nweii/agent-stuff --skill repo-docsgit clone --depth 1 https://github.com/nweii/agent-stuffWrote 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/nweii/agent-stuff/repo-docs)<a href="https://agentmods.dev/skills/nweii/agent-stuff/repo-docs"><img src="https://agentmods.dev/badge/skills/nweii/agent-stuff/repo-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/nweii/agent-stuff/repo-docs"><img src="https://agentmods.dev/badge/skills/nweii/agent-stuff/repo-docs.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 | $0.00052 | $0.02589 |
| Opus 5.5 | $0.00021 | $0.01036 |
| Sonnet 5.5 | $0.00010 | $0.00518 |
| Haiku 4.5 | $0.00005 | $0.00259 |
Grade A, and why
repo-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 12d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo docs
User-facing repo docs serve a stranger: someone who arrived cold, is deciding whether the project fits, and then sets it up or uses it. Their coding agent often reads the same page and follows its steps. Write every page for that pair, never for the owner.
The guidance has two layers. The content rules apply to every user-facing doc in every repo. The format defaults apply only where the repo, its ecosystem, or its docs site has no convention of its own; when one exists, follow it.
Most rules below are judgments, each with the test that decides it. Apply the test to the case in front of you: the same detail can belong in a reference table and not in a heading, or in a closing section and not in a setup step. Scale the steps to the change as well: a one-line fix needs the facts it touches and their echoes, while a new doc or a public-release pass needs every step in full.
RFCs use the document-mode guidance for their sections. PR descriptions and commit messages use the sentence and verification rules, with their repository's format rather than a documentation mode. Product UI strings use the product's copy guidelines.
Steps
1. Gather the facts
Read the doc you are changing, its siblings, the code and config behind each claim, and every echo of its facts elsewhere (website copy, storefront text, in-app help, installed docs, other docs in the repo). Check the repo's visibility with gh repo view --json visibility and look for existing conventions: a docs site, a style the other docs share, README requirements from the plugin or package directory the project ships through.
Done when you can name the audience, the conventions that bind the doc, every echo location, and the code path behind each claim you will touch.
2. Place the material
Put each piece of material in the document that owns it, using the map below. Give each fact one canonical home and link to it from everywhere else; copy a fact only where a link cannot reach (a storefront, an app's help text).
What ships with it
4 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.
- 12d ago Changed · +8 lines · -11 tokens per session ee604f585a9a
- 24d ago First seen · 114 lines · 63 tokens per session scan A 285a9e88ea3c
repo-docs is a skill published in the GitHub repository nweii/agent-stuff (10 stars, last pushed 3d ago), licensed MIT. It adds 52 tokens to every session and 2,589 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 2026-09-23.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Fetches URLs and PDFs, then summarizes or returns clean Markdown. Use when asked to read, fetch, quote, cite, convert, or save a URL or PDF. Not for local text files already in the repo.