docs-mcp: Instructions file for Codex

AGENTS.md

docs-mcp AGENTS.md is an instructions file for Codex, OpenCode from Particle-Academy/docs-mcp. It costs 813 tokens per session, scanned A, original, MIT.

Instructions for using a documentation MCP server, a service that lets an editor or coding agent access documentation for packages installed in a project.

In plain words
What is it for?
Finding setup instructions and consulting documentation for the versions in a project's node_modules folder.
Why use it?
They distinguish local package documentation from a hosted catalog and explain how to install and connect the service.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code.

This is Particle-Academy/docs-mcp's own configuration. It tells Codex and OpenCode how to work on docs-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything docs-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Particle-Academy/docs-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Particle-Academy/docs-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Particle-Academy/docs-mcp

Made for: Codex, OpenCode.

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 docs-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/particle-academy/docs-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/particle-academy/docs-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/particle-academy/docs-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/particle-academy/docs-mcp/agents-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.

agentmods 80×15 button for docs-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/particle-academy/docs-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/particle-academy/docs-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 813 This file is loaded in full into every session.
When invoked 813 The same file — it is already loaded in full.
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 $0.00813 $0.00813
Opus 5.5 $0.00325 $0.00325
Sonnet 5.5 $0.00163 $0.00163
Haiku 4.5 $0.00081 $0.00081

Measured yesterday against content hash 7f445d0bcda8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

docs-mcp AGENTS.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 yesterday.

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.

AGENTS.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Using @particle-academy/docs-mcp — guide for agents

How an agent installs and uses this package in a consumer app. What the package is, is in README.md. Notes for working ON this repo's code are in CONTRIBUTING.md.

Install

Nothing is installed into the project. It is a dev-time stdio MCP server the editor spawns on demand. In .mcp.json at the project root (Claude Code, Cursor):

{
  "mcpServers": {
    "particle-docs": {
      "command": "npx",
      "args": ["-y", "@particle-academy/docs-mcp"]
    }
  }
}

Claude Desktop takes the same entry in claude_desktop_config.json, plus a "cwd" with the project's absolute path when the editor launches from elsewhere. Restart the editor afterwards. Node: >=22.

Find it on the Fancy MCP server

The catalog server is https://ui.particle.academy/mcp (streamable HTTP, no API key; MCP id fancy-ui). Its registry slug is docs-mcp: use install-instructions with that slug.

The two servers answer different questions. fancy-ui (hosted) is the catalog: what exists, and how to install it. docs-mcp (local) serves the docs of the versions actually installed in this project's node_modules.

API essentials

Tool Does
docs_list_packages Every scanned package with name, version, file count, source
docs_list All doc paths; optional package filter
docs_read One doc by (package, path)
docs_search Substring search; hits with line numbers and section headings
docs_refresh Re-scan the filesystem

Every tool returns readable text and a structuredContent JSON payload.

Typical agent flow

agent: docs_list_packages
   → 11 packages found
agent: docs_search { query: "controlled component" }
   → 3 hits across react-fancy/docs/Forms.md, fancy-sheets/docs/Spreadsheet.md, ...
agent: docs_read { package: "@particle-academy/react-fancy", path: "docs/Forms.md" }
   → full markdown

Traps

  • It is a CLI, never a runtime import. Do not import it from app code or ship it in a bundle.
  • It only exposes README.md and docs/**/*.md(x) of each package. Other files are not served.
  • No watchers. After an npm install mid-session, call docs_refresh.
  • Search is substring grep: no ranking, no embeddings. Search for words the doc will contain.
  • In a monorepo, <cwd>/packages/* wins over node_modules for the same package name. Pass --no-workspace to force node_modules.
  • Nothing found? Run npx @particle-academy/docs-mcp --list from the same cwd the editor uses; widen with --scope-any or --cwd <path>.

Read the full file on GitHub · 82 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. yesterday First seen · 82 lines · 813 tokens per session scan A 7f445d0bcda8

Subscribe to this mod's changes

docs-mcp AGENTS.md is an instructions file published in the GitHub repository Particle-Academy/docs-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 813 tokens to every session, about $0.0033 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 2026-11-17.

Related

docs-mcp AGENTS.md compared with instructions from other repositories

docs-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
docs-mcp AGENTS.mdParticle-Academy/docs-mcpInstructions file0yesterdayMITA813Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283ktodayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot