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 instructions/thevibeworks/claude-code-docs/claude-mdgit clone --depth 1 https://github.com/thevibeworks/claude-code-docsWhat 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 | $0.02775 | $0.02775 |
| Opus 5 | $0.01388 | $0.01388 |
| Sonnet 5 | $0.00555 | $0.00555 |
| Haiku 4.5 | $0.00278 | $0.00278 |
Grade A, and why
claude-code-docs CLAUDE.md 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 2d 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Repository Purpose
Comprehensive archive of everything Anthropic publishes for building with Claude. 3,900+ docs from 12 sources; active sources auto-updated four times daily (blog archive frozen, see Fetcher).
Fetcher
scripts/fetcher.py -- single-file multi-source fetcher.
Sources: code.claude.com, platform.claude.com, claude.com/docs, modelcontextprotocol.io, support.claude.com (sitemap + .md), github.com/anthropics/* (10 repos). anthropic.com blog (engineering/research/news) is a FROZEN archive as of 2026-07: the site is HTML-only and the jina.ai proxy path was removed.
Five rules keep the archive honest, all learned the hard way:
- Discovery surfaces are incomplete. Sitemaps and llms.txt undercount what a site serves, so every full run also refetches what is already on disk. Without this, 1,560 de-indexed-but-live API pages sat stale for seven weeks.
- The archive must be able to shrink. Full runs reap files whose URL is gone (404/410 or HTML shell). Only markup is deleted automatically; real markdown that died upstream is reported for a human. A >200-file reap is refused outright as an upstream outage.
- A redirect means the content belongs elsewhere. If a fetch lands on a
different path, the body in hand is the target's; writing it back to the
requested path misattributes it. That is how the 471KB
release-notes/system-prompts.mdbriefly became the 3.7KB overview it now redirects to, after upstream split it into per-model pages. - A known failure must not look like a new one.
tombstones.jsonrecords every URL confirmed gone, so a page that died once is counted quietly on later runs instead of re-reported. Only new deaths and resurrections are printed loudly, and the success rate is computed over live docs — 123 standing failures pinning it at 96.9% would hide the next real breakage. - A discovery only counts once it is a file.
discovery.jsonrecords what exists upstream thatsources.jsondoes not: unknown redirect targets, new anthropics repos, and whether each domain serves.mdat all. Printing it was not enough — the pipeline had loggedsupport.claude.com -> academy.claude.comfor weeks into an Actions log with no reader, and a human found those 725 pages by chasing a dead article. The decision agent readsgit status, so a new source now arrives as a diff.
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.
- 2d ago First seen · 201 lines · 2,775 tokens per session scan A 0ec340e719b4
claude-code-docs CLAUDE.md is an instructions file published in the GitHub repository thevibeworks/claude-code-docs (38 stars, last pushed 2d ago), licensed MIT. It adds 2,775 tokens to every session, about $0.0139 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 2026-08-30.
Other instructions, from other repositories
liam AGENTS.md
Instructions for liam-hq/liam, covering repository guidelines, project structure & modules, build, test, and development, coding style & naming and testing guidelines.
core copilot-instructions.md
Instructions for asdecided/core: These decisions are already accepted. Do not re-open or contradict them; ask the AsDecided MCP tools (getartifact, searchartifacts) for the full text before proposing a change that touches one.
slideops CLAUDE.md
Instructions for glukicov/slideops, covering claude.md, what this repository is, commands, the demo deck's citations must still match this repo and the citation mechanism (the core idea).
valuein AGENTS.md
AGENTS.md instructions for valuein/valuein, covering agents.md — valuein public oss hub, project, what valuein is, default install + first query (use this verbatim) and either workflow — both work in any virtual environment.
valuein CLAUDE.md
Claude Code instructions for valuein/valuein, covering claude.md, what this repo is (and isn't), sibling repos — where the actual code lives, commands and with a paid/sp500 token.
docs AGENTS.md
Instructions for argos-ci/docs, covering agents.md, always use the documentation skills and keep the table of contents in sync.