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/hoornet/agentdocs-mcp/claude-mdgit clone --depth 1 https://github.com/hoornet/agentdocs-mcpWrote 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/hoornet/agentdocs-mcp/claude-md)<a href="https://agentmods.dev/instructions/hoornet/agentdocs-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hoornet/agentdocs-mcp/claude-md.svg" alt="Measured on agentmods" 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 | $0.00968 | $0.00968 |
| Opus 5 | $0.00484 | $0.00484 |
| Sonnet 5 | $0.00194 | $0.00194 |
| Haiku 4.5 | $0.00097 | $0.00097 |
Grade A, and why
agentdocs-mcp 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 5d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code (claude.ai/code) working in this repository.
What this is
agentdocs-mcp — the stdio MCP server for AgentDocs, published to npm
and listed in the official MCP registry as io.github.hoornet/agentdocs-mcp. It gives MCP clients
read/search/write access to AgentDocs Markdown docs.
ESM ("type": "module"), TypeScript, Node >=20, no runtime framework. Dependencies are just
@modelcontextprotocol/sdk and zod.
Layout
| Path | Purpose |
|---|---|
src/index.ts |
entry point — builds the McpServer, wires stdio transport, registers tools |
src/config.ts |
env/config loading (AGENTDOCS_TOKEN, AGENTDOCS_URL) |
src/client.ts |
HTTP client for the AgentDocs API (ApiError) |
src/resolve.ts |
slug-or-UUID addressing |
src/context.ts |
shared ToolContext / CredentialInfo types |
src/tools/{read,write,share,comments}.ts |
the MCP tool registrations |
test/*.test.mjs |
unit tests — no credentials, no network. npm run test:unit |
test/smoke*.mjs |
smoke scripts, run by hand against a real instance (credentials required) |
docs/PUBLISHING.md |
release procedure + directory/registry listings |
server.json |
official MCP registry manifest — version must match the published npm version |
Build with npm run build (tsc → dist/). npm run watch for incremental.
Two invariants that have each caused a shipped bug
1. The version lives in package.json and nowhere else.
src/index.ts derives it at runtime via createRequire(import.meta.url)("../package.json").version.
Do not "simplify" this into a hardcoded VERSION string. A hand-maintained literal is precisely
what silently drifted two releases behind and made 0.6.0/0.6.1 report 0.5.2 to every client in the
MCP initialize handshake. Fixed in 0.6.2 — keep it derived.
2. Never trust a lifecycle hook to produce the build.
Publish with npm run release (= npm run build && npm publish), not bare npm publish.
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.
- 5d ago First seen · 67 lines · 968 tokens per session scan A 46b6286fba2e
agentdocs-mcp CLAUDE.md is an instructions file published in the GitHub repository hoornet/agentdocs-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 968 tokens to every session, about $0.0048 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 instructions, from other repositories
inkdex AGENTS.md
AGENTS.md instructions for antonlunden/inkdex, covering agents.md, general coding guidelines and development.
core copilot-instructions.md
Copilot 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.
abap_wiki AGENTS.md
AGENTS.md instructions for Gixsy95/abap_wiki, covering agents.md - abapwiki operating contract, 1. identity and mission, 2. language, 3. architecture: the two planes and 4. inviolable rules.
seekstone CLAUDE.md
Claude Code instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
wikifier CLAUDE.md
Claude Code instructions for IronAdamant/wikifier, covering claude.md, what this is, hard constraints, mandatory workflow (the project's own protocol) and ... edit source (prioritize 🔴 red, then 🟡 yellow) ...
data-olympus AGENTS.md
Instructions for knaisoma/data-olympus, covering data olympus, project overview, architecture, development workflow and code standards.