all-agents-mcp: Instructions file for Claude Code

CLAUDE.md

all-agents-mcp CLAUDE.md is an instructions file for Claude Code from Dokkabei97/all-agents-mcp. It costs 1,721 tokens per session, scanned A, original, MIT.

A project guide for all-agents-mcp, an MCP server that coordinates several AI command-line agents through one interface. It covers the project layout, development commands, architecture, tools, and resources.

In plain words
What is it for?
Working on the TypeScript server, running its build and tests, checking code quality, and understanding how its agent tools are registered.
Why use it?
It gives coding agents the repository context needed to build, test, lint, and debug the project consistently.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is Dokkabei97/all-agents-mcp's own configuration. It tells Claude Code how to work on all-agents-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 all-agents-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Dokkabei97/all-agents-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/Dokkabei97/all-agents-mcp/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Dokkabei97/all-agents-mcp

Made for: Claude Code.

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 all-agents-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dokkabei97/all-agents-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/dokkabei97/all-agents-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dokkabei97/all-agents-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dokkabei97/all-agents-mcp/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.

agentmods 80×15 button for all-agents-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dokkabei97/all-agents-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dokkabei97/all-agents-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,721 This file is loaded in full into every session.
When invoked 1,721 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.01721 $0.01721
Opus 5 $0.00860 $0.00860
Sonnet 5 $0.00344 $0.00344
Haiku 4.5 $0.00172 $0.00172

Measured 9d ago against content hash f39c64a38918, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

all-agents-mcp CLAUDE.md scanned grade A with 1 finding 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 9d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- **`executor.ts`**: `spawnAgent()` — low-level `child_process.spawn` with `AbortController` timeout. All CLI invocations go through here.
CLAUDE.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 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.

Project Overview

all-agents-mcp is a stdio-based MCP server that orchestrates multiple AI CLI agents (Claude Code, Codex, Gemini CLI, Copilot CLI) through a unified interface. Exposes 14 tools and 3 resources.

Development methodology: This project follows AIDE (Agent-Informed Development Engineering) v1.0 — a software development methodology for the agentic era. See AIDE-REFERENCE.md for the full reference. Key adopted principles noted below with [AIDE P#] tags.

Build & Development Commands

npm run build        # TypeScript compilation (tsc → dist/)
npm run dev          # Watch mode (tsc --watch)
npm run lint         # Biome check with auto-fix (biome check --write .)
npm test             # Run all tests (vitest run)
npm run test:watch   # Watch mode tests (vitest)
npx vitest run src/path/to/file.test.ts  # Run a single test file

Debug logging: AA_MCP_LOG_LEVEL=debug node dist/index.js (levels: debug, info, warn, error)

Architecture

Entry Flow

src/index.tscreateServer() in src/server.ts → registers all tools/resources → connects StdioServerTransport.

Layer Structure [AIDE P2: Locality]

src/
├── agents/         # Agent abstraction — IAgent interface + per-agent implementations
├── orchestrator/   # Process spawning, parallel execution, complexity analysis, verification
├── tools/          # 14 MCP tool definitions (one file = one tool)
├── resources/      # 3 MCP resource definitions
├── session/        # File-based JSON session storage (~/.all-agents-mcp/sessions/)
├── config/         # Env var config loader (AA_MCP_* overrides) + Zod schema
├── utils/          # Logger (stderr-only), CLI detection
├── server.ts       # McpServer factory — registers all tools and resources
└── index.ts        # Entry point — stdio transport connection

Agent Layer (src/agents/)

Read the full file on GitHub · 116 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. 9d ago First seen · 116 lines · 1,721 tokens per session scan A f39c64a38918

Subscribe to this mod's changes

all-agents-mcp CLAUDE.md is an instructions file published in the GitHub repository Dokkabei97/all-agents-mcp (14 stars, last pushed 5mo ago), licensed MIT. It adds 1,721 tokens to every session, about $0.0086 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens