agentic-mcp: Instructions file for Claude Code

CLAUDE.md

agentic-mcp CLAUDE.md is an instructions file for Claude Code from F0rty-Tw0/agentic-mcp. It costs 994 tokens per session, scanned A, original, MIT.

A configurable gateway that lets an AI assistant send requests to several coding assistants and AI command-line tools through MCP. MCP is a standard way for software to expose tools to an AI assistant.

In plain words
What is it for?
Use it to ask Claude, Codex, Copilot, Gemini, OpenCode, or other configured providers, compare their answers, and track asynchronous requests.
Why use it?
It avoids writing a separate integration for every supported provider and lets provider settings be maintained in configuration files. It also supports parallel requests and longer-running jobs.

Instructions file for Claude Code

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

This is F0rty-Tw0/agentic-mcp's own configuration. It tells Claude Code how to work on agentic-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 agentic-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to F0rty-Tw0/agentic-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/F0rty-Tw0/agentic-mcp/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/F0rty-Tw0/agentic-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 agentic-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/f0rty-tw0/agentic-mcp/claude-md.svg)](https://agentmods.dev/instructions/f0rty-tw0/agentic-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/f0rty-tw0/agentic-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/f0rty-tw0/agentic-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 994 This file is loaded in full into every session.
When invoked 994 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 $0.00994 $0.00994
Opus 5 $0.00497 $0.00497
Sonnet 5 $0.00199 $0.00199
Haiku 4.5 $0.00099 $0.00099

Measured 6d ago against content hash c9d9b7f9798e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

agentic-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 6d 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.

CLAUDE.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Gotchas

  • pnpm run — always pnpm run <script>, never bare pnpm <script>.
  • No extensions on relative imports — use './foo', never './foo.ts' or './foo.js'. Package imports keep their original extension ('@modelcontextprotocol/sdk/server/mcp.js').
  • Config over code — new providers go in providers.json, not in source files. No code changes, no rebuilds.
  • Never shell: true — all spawns use cross-spawn with array args. Never pass user input through a shell.

Architecture

  • Multi-model AI gateway wrapping CLI tools (Claude, Codex, Copilot, Gemini, OpenCode) as MCP servers
  • Config-driven: providers defined in src/config/providers.json with Zod-validated schema (providers.schema.json)
  • Entry point: src/index.ts -> src/entry/domain-logic/entry.ts (handles --version, --help, setup subcommand, or starts MCP server)

Module Map

  • ask/ — per-provider ask handler (command building, execution, response parsing, sessions)
  • ask-all/ — fan-out to all providers in parallel
  • background-jobs/ — async job queue for long-running asks (mode: async, action: status)
  • cli-args/ — declarative config -> CLI string[] arg builder
  • config/ — providers.json loader with multi-source resolution (--config, env, user-local, bundled)
  • entry/ — CLI entry point (--version, --help, setup, MCP server)
  • provider-metrics/ — per-provider call counts, response times, success rates
  • server/ — MCP server factory
  • session/ — session store with locking for multi-turn conversations
  • setup/agentic-mcp setup CLI for configuring MCP clients
  • shared/ — cross-cutting: command-execution (spawning, semaphore), mcp-protocol (types, heartbeat), provider (config types, env resolver, model error detection), validation (request registry, Zod utils)
  • simple-tools/ — ping, help, list_providers handlers
  • streaming/ — live output streaming via MCP progress notifications
  • tool-registry/ — MCP tool registration (builds tool definitions from provider config)
  • types/ — ambient declarations (build-env.d.ts)

Read the full file on GitHub · 77 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. 6d ago First seen · 77 lines · 994 tokens per session scan A c9d9b7f9798e

Subscribe to this mod's changes

agentic-mcp CLAUDE.md is an instructions file published in the GitHub repository F0rty-Tw0/agentic-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 994 tokens to every session, about $0.0050 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.

Related

Other instructions, from other repositories

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 · 5,182 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

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

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

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens