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.
git clone --depth 1 https://github.com/Zyepher/llm-docs-generatornpx agentmods add skills/zyepher/llm-docs-generator/repo-docs-discoveryWrote 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/zyepher/llm-docs-generator/repo-docs-discovery)<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.
<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>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 | $0.00064 | $0.01986 |
| Opus 5 | $0.00032 | $0.00993 |
| Sonnet 5 | $0.00013 | $0.00397 |
| Haiku 4.5 | $0.00006 | $0.00199 |
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.
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 --jsonbefore assuming a discovery mode exists; modes not reported there are unavailable unless the installed CLI says otherwise.llm-docs agent doctor --jsonis read-only diagnostics; do not claimagent install codexor 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.
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.
- 10d ago First seen · 123 lines · 64 tokens per session scan A 518da3feb62c
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.
Other skills, from other repositories
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
crit-story
Author a crit story and continue the interactive review loop only when the user explicitly invokes crit-story or directly asks you to generate a crit story. Do not infer this skill from generic review, PR, or diff-review requests.
snip
You are an expert at writing declarative YAML filters for snip, a CLI proxy that reduces LLM token consumption by filtering shell output.
goai
GoAI is a Go SDK for AI applications. One unified API across 25+ LLM providers. Inspired by the Vercel AI SDK, adapted to Go idioms (generics, interfaces, channels).