A documentation guide for explaining a code repository to human readers through its real behavior, key concepts, source locations, and ways to verify the explanation. A repository is the files and history that make up a software project.

Use it to write onboarding documentation, explain architecture, seed documentation for a new project, update guides after code changes, and document large or multi-project repositories.

It helps people understand how a project actually works instead of giving them a simple file listing. It also provides rules for creating, updating, or removing repository guides.

repo-docs — Skill for Claude Code and Codex by phanghonghao

Install

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.

Any agent

npx skills add phanghonghao/THU-Awesome-Skills --skill repo-docs

Clone the repo

git clone --depth 1 https://github.com/phanghonghao/THU-Awesome-Skills

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/phanghonghao/thu-awesome-skills/repo-docs/github.svg)](https://agentmods.dev/skills/phanghonghao/thu-awesome-skills/repo-docs)

Your own site

<a href="https://agentmods.dev/skills/phanghonghao/thu-awesome-skills/repo-docs"><img src="https://agentmods.dev/badge/skills/phanghonghao/thu-awesome-skills/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/phanghonghao/thu-awesome-skills/repo-docs"><img src="https://agentmods.dev/badge/skills/phanghonghao/thu-awesome-skills/repo-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,819 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00069	$0.02819
Opus 5.5	$0.00028	$0.01128
Sonnet 5.5	$0.00014	$0.00564
Haiku 4.5	$0.00007	$0.00282

Measured 2mo ago against content hash ea2dfde8b771, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/validate_repo_docs.py, validate_repo_docs.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/repo-docs/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repo-Docs

Mission

repo-docs explains a repository to a human reader.

Do not make a tree tour. Build a reader model: what problem the repo solves, one real behavior it performs, the concepts behind that behavior, where source truth lives, and how to verify the understanding.

Load Order

Read this file first.
Open REFERENCE.md for task routing when detailed rules are needed.
Open only the topic file the router points to.
Open EXAMPLES.md only for finished-page tone or output-shape examples.
Prefer bundled scripts over rewriting deterministic checks.

Keep the routing narrow. SKILL.md defines the contract; topic files carry the detailed rules. If a detail appears in two places, keep it in the topic file and leave a pointer here.

Document Contract

File	Role
`SKILL.md`	Entry: mission, principles, output contract, build/sync summary, verification
`REFERENCE.md`	Router to topic files—open only when detail is needed
`WRITING.md`	Explanation design, voice, evidence discovery
`PAGE_RULES.md`	Reader paths, page types, output shape, navigation
`SCOPE_MODES.md`	Seed, large/monorepo scope, specialized repos
`SYNC_RULES.md`	Question loop, change sync, widened content alignment
`QUALITY_RULES.md`	Evidence labels, source truth, quality bar
`EXAMPLES.md`	Finished-page tone and output-shape examples
`scripts/validate_repo_docs.py`	Structure, links, sync anchors, freshness checks
`validate_repo_docs.py`	Compatibility wrapper for older invocations
`repo-docs-zh/SKILL.md`	Chinese language overlay

First Principles

Behavior before inventory: teach one real workflow, request, task, failure, or data path first.
Reader handles before locators: the handle explains; the exact path, function, field, command, or artifact proves.
Direct source links by default: link one claim to one source with readable text. Create references/source-map.md only when repeated grouped locators would clutter pages.
One durable fact, one home: concepts in modules/, exact lookup material in references/, term disambiguation in glossary.md, guide history in change-log.md.
Evidence stays visible but quiet: current source, tests, config, data, command output, and artifacts outrank old docs, memory, and chat.

Read the full file on GitHub · 189 lines

Files

What ships with it

9 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.

Changes

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.

2mo ago First seen · 189 lines · 69 tokens per session scan A ea2dfde8b771

Subscribe to this mod's changes

repo-docs is a skill published in the GitHub repository phanghonghao/THU-Awesome-Skills (8 stars, last pushed 3mo ago), licensed MIT. It adds 69 tokens to every session and 2,819 once invoked, about $0.0003 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 2026-08-31.

Writing and docs

repo-docs next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
repo-docsphanghonghao/THU-Awesome-Skills	Skill	8	3mo ago	MIT	A	69	Claude Code, Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	yesterday	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	100k	yesterday	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	4d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code