Borrowing it
Nothing to install: this file belongs to EdwardAngert/docs-agent-plugin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/EdwardAngert/docs-agent-plugin/main/CLAUDE.mdgit clone --depth 1 https://github.com/EdwardAngert/docs-agent-pluginWrote 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/instructions/edwardangert/docs-agent-plugin/claude-md)<a href="https://agentmods.dev/instructions/edwardangert/docs-agent-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/edwardangert/docs-agent-plugin/claude-md/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/instructions/edwardangert/docs-agent-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/edwardangert/docs-agent-plugin/claude-md.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 | $0.00296 | $0.00296 |
| Opus 5.5 | $0.00118 | $0.00118 |
| Sonnet 5.5 | $0.00059 | $0.00059 |
| Haiku 4.5 | $0.00030 | $0.00030 |
Grade A, and why
docs-agent-plugin 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 1mo 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.
What it actually says
CLAUDE.md
Documentation
This repo is the Docs Assist plugin, and it runs on itself.
Use the plugin for anything under docs/, the README, the changelog, release notes, or a pull request description, rather than writing prose directly.
Start with /docs-assist:health when the state is unclear.
If finishing a documentation task surfaces something else that blocks it, fix that first and say so, rather than stopping to ask.
Two decisions to apply without re-deriving them:
- The documentation set is what
git ls-filesreturns. A file on disk that git ignores is working material, not a document: never audit, lint, count, or rank it. - Before changing a fact, grep for every place it appears and fix them together. Several facts here live in more than one file, and fixing only the first occurrence has produced self-contradicting pages.
.docs-assist/decisions.md has the rest, including which file owns which repeated fact.
Read it before auditing, drafting, or restructuring docs here.
Conventions
The prose rules live in .docs-assist/style.md and the machine-checkable ones in .docs-assist/config.yml.
Both are enforced: node scripts/validate.mjs plus Vale, markdownlint, and cspell.
Run them before calling documentation work done, and treat a clean run as the floor rather than the finish.
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.
- 1mo ago First seen · 25 lines · 296 tokens per session scan A 2144e111541a
docs-agent-plugin CLAUDE.md is an instructions file published in the GitHub repository EdwardAngert/docs-agent-plugin (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 296 tokens to every session, about $0.0012 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 2026-09-19.
docs-agent-plugin CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| docs-agent-plugin CLAUDE.mdEdwardAngert/docs-agent-plugin | Instructions file | 5 | 1mo ago | Apache-2.0 | A | 296 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 3d ago | MIT | A | 4,313 | Codex, OpenCode |