agent CLAUDE.md

agent CLAUDE.md is an instructions file for coding agents from 1mcp-app/agent. It costs 1,557 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for developing 1MCP Agent, a project that provides an MCP-based agent service, including its setup, build, testing, and debugging commands.

In plain words
What is it for?
Installing dependencies, running development builds, linting, type-checking, running unit and end-to-end tests, and debugging the 1MCP Agent project.
Why use it?
They give an agent the exact commands and quality checks needed to make safe changes in the repository.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/1mcp-app/agent/claude-md
Clone the repo
git clone --depth 1 https://github.com/1mcp-app/agent

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 agent CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/1mcp-app/agent/claude-md.svg)](https://agentmods.dev/instructions/1mcp-app/agent/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/1mcp-app/agent/claude-md"><img src="https://agentmods.dev/badge/instructions/1mcp-app/agent/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,557 This file is loaded in full into every session.
When invoked 1,557 The same file — it is already loaded in full.
Security scan A 2 findings. Scan, not verified.
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 $0.01557 $0.01557
Opus 5 $0.00779 $0.00779
Sonnet 5 $0.00311 $0.00311
Haiku 4.5 $0.00156 $0.00156

Measured 4d ago against content hash 5d12d9ac6cfc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent CLAUDE.md scanned grade A with 2 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 4d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl "http://localhost:3050/mcp?app=cursor&tags=filesystem,search"

Runs shell commandslowCapability

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

- **Runtime**: Node.js with child_process APIs for server management
CLAUDE.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 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 Information

Development Commands

# Setup
pnpm install
cp .env.example .env  # Required for development

# Build & Run
pnpm build            # Build the project
pnpm dev              # Development with auto-rebuild
pnpm watch            # Watch mode for development

# Quality Checks (run before committing)
pnpm lint && pnpm typecheck && pnpm build && pnpm test:unit

# Testing
pnpm test:unit                              # Run all unit tests
pnpm test:unit src/config/mcpConfigManager.test.ts  # Run single test file
pnpm test:unit -t "ServerManager"           # Run tests matching name pattern (-t = --testNamePattern)
pnpm test:unit:watch                        # Watch mode
pnpm test:unit:coverage                     # With coverage
pnpm test:e2e                               # E2E tests (sequential, with fixtures)
pnpm test:e2e:watch                         # E2E watch mode

# Debug
pnpm inspector                              # MCP Inspector

# Documentation
pnpm docs:dev         # Start VitePress dev server
pnpm docs:build       # Build documentation (run after doc changes)

# Binary
pnpm sea:build        # Create SEA bundle
pnpm sea:binary       # Build binary for current platform

Architecture Overview

1MCP is a unified MCP server that aggregates multiple MCP servers into one endpoint. It acts as a proxy, managing servers as subprocesses and forwarding requests from AI assistants.

Layered Architecture

src/
├── commands/           # CLI commands (yargs-based)
├── transport/          # HTTP/SSE and STDIO protocol implementations
│   └── http/
│       ├── routes/     # Endpoint handlers (oauth, sse, streamable)
│       └── middlewares/# Security, auth, tag extraction
├── core/               # Business logic
│   ├── server/         # ServerManager - lifecycle management
│   ├── capabilities/   # Tool/resource aggregation
│   ├── loading/        # mcpLoadingManager, parallelExecutor, state tracking
│   └── filtering/      # Request filtering
├── config/             # McpConfigManager with hot-reload
├── auth/               # OAuth 2.1 with scope-based authorization
├── domains/            # Self-contained business domains
│   ├── preset/             # Preset management
│   ├── backup/             # Backup management
│   ├── discovery/          # App discovery
│   ├── installation/       # App installation
│   ├── registry/           # Server registry
│   ├── server-management/  # Server management
│   └── config-change/      # Config mutation/reload observation
├── application/        # Cross-cutting services (health, config reload)
└── logger/             # Winston-based conditional logging

Read the full file on GitHub · 177 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. 4d ago First seen · 177 lines · 1,557 tokens per session scan A 5d12d9ac6cfc

Subscribe to this mod's changes

agent CLAUDE.md is an instructions file published in the GitHub repository 1mcp-app/agent (494 stars, last pushed 5d ago), licensed Apache-2.0. It adds 1,557 tokens to every session, about $0.0078 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.