repo-docs-discovery

repo-docs-discovery is a skill for Claude Code, Codex from Zyepher/llm-docs-generator. It costs 64 tokens per session (1,986 once invoked), scanned A, original, MIT.

A documentation-discovery workflow for finding the exact source and version of a package's authoritative documentation. It is especially useful for monorepos, which store multiple packages or projects in one repository.

In plain words
What is it for?
Use it before running llm-docs generation to identify the repository, tag, commit, and documentation subtree, and to note unusual layouts or draft content.
Why use it?
It prevents documentation generation from using the wrong repository, release, commit, or documentation folder.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is llm-docs discover --repo <repo-url> --scope <docs-subtree> --output-dir ./reports/<pkg>.

Good fit Use it before running llm-docs generation to identify the repository, tag, commit, and documentation subtree, and to note unusual layouts or draft content.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Zyepher/llm-docs-generator
agentmods
npx agentmods add skills/zyepher/llm-docs-generator/repo-docs-discovery

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.

agentmods badge for repo-docs-discovery

README.md
[![agentmods](https://agentmods.dev/badge/skills/zyepher/llm-docs-generator/repo-docs-discovery/github.svg)](https://agentmods.dev/skills/zyepher/llm-docs-generator/repo-docs-discovery)
Your own site
<a href="https://agentmods.dev/skills/zyepher/llm-docs-generator/repo-docs-discovery"><img src="https://agentmods.dev/badge/skills/zyepher/llm-docs-generator/repo-docs-discovery/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.

agentmods 80×15 button for repo-docs-discovery

Your own site · 80×15
<a href="https://agentmods.dev/skills/zyepher/llm-docs-generator/repo-docs-discovery"><img src="https://agentmods.dev/badge/skills/zyepher/llm-docs-generator/repo-docs-discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,986 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00064 $0.01986
Opus 5 $0.00032 $0.00993
Sonnet 5 $0.00013 $0.00397
Haiku 4.5 $0.00006 $0.00199

Measured 10d ago against content hash 518da3feb62c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

repo-docs-discovery 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 10d 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.

skills/repo-docs-discovery/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

repo-docs-discovery

This skill resolves the question Step 1 of the llm-docs-generator playbook asks: for the exact version this project runs, where is the authoritative docs tree, at which commit? You investigate and decide; llm-docs only converts the explicit local path you hand it. Hand generation a concrete answer: repo URL + tag + commit + docs subtree path, plus notes on anything non-obvious (drafts, framework subtrees, docs that live in another package's repo).

Every step states WHY so you can adapt it to a repo whose layout differs from the examples.

Division Of Labor (never violate)

  • You own version choice, source authority, docs-tree selection, and task fit.
  • The CLI owns bounded inspection, parsing, formatting, and honest failure. It never decides which repo, tag, or docs path is authoritative.
  • Never pass a package name, repo URL, docs URL, or discovery report to generate --source. Resolve it to an explicit local path first.
  • Run llm-docs capabilities --json before assuming a discovery mode exists; modes not reported there are unavailable unless the installed CLI says otherwise. llm-docs agent doctor --json is read-only diagnostics; do not claim agent install codex or other lifecycle commands unless capabilities reports them.
  • Never store credentials or tokens in reports, manifests, or notes.
  • Do not execute repository scripts, docs-build scripts, or install hooks from an inspected source.

Step 1 — Package → Repo (primary evidence: the installed package's own metadata)

WHY: the package the project actually installed names its own upstream repo in its installed metadata. That is stronger evidence than a web search or memory. The metadata store is ecosystem-specific; the rule — resolve version and repo from what the package manager installed — is not.

npm worked example — read the installed package.json:

cat <project>/node_modules/<pkg>/package.json

Read three fields:

  • version — the exact version you must match.
  • repository.url — the upstream repo (often a monorepo hosting many packages).
  • repository.directory — the package's subpath inside that repo when present (e.g. packages/react-query). This tells you where the package lives, which is the anchor for finding its docs.

Read the full file on GitHub · 123 lines

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.

  1. 10d ago First seen · 123 lines · 64 tokens per session scan A 518da3feb62c

Subscribe to this mod's changes

repo-docs-discovery is a skill published in the GitHub repository Zyepher/llm-docs-generator (5 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 1,986 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.