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/hbd/mcp-chat/claude-mdgit clone --depth 1 https://github.com/hbd/mcp-chatWrote 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/hbd/mcp-chat/claude-md)<a href="https://agentmods.dev/instructions/hbd/mcp-chat/claude-md"><img src="https://agentmods.dev/badge/instructions/hbd/mcp-chat/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 | $0.00595 | $0.00595 |
| Opus 5 | $0.00298 | $0.00298 |
| Sonnet 5 | $0.00119 | $0.00119 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
mcp-chat 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 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.
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 — 85 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
MCP Chat is a Python-based MCP (Model Context Protocol) server that enables direct chat between users through MCP tool calls. It demonstrates using MCP's tool-calling interface for real-time human communication.
Development Setup
This is a Python project using the following tools and conventions:
Package Management
- uv: Use
uvfor all package management tasks- Install dependencies:
uv sync - Add new dependencies:
uv add <package> - Create virtual environment:
uv venv
- Install dependencies:
MCP Framework
- FastMCP: This project uses the FastMCP framework for building the MCP server
- Follow FastMCP conventions for handlers and server setup
- Use FastMCP's built-in decorators and utilities
Code Quality Tools
-
mypy: Type checking
- Run with:
mypy . - Ensure all code has proper type annotations
- Fix all type errors before committing
- Run with:
-
Ruff: Linting and formatting
- Format code:
ruff format . - Lint code:
ruff check . - Fix linting issues:
ruff check --fix . - Always run both before committing changes
- Format code:
Development Commands
# Set up environment
uv venv
source .venv/bin/activate # On Unix/macOS
# or
.venv\Scripts\activate # On Windows
# Install dependencies
uv sync
# Type checking
mypy .
# Linting and formatting
ruff format .
ruff check --fix .
# Run the MCP server
python -m mcp_chat.server
Project Structure
mcp-chat/
├── mcp_chat/
│ ├── __init__.py
│ ├── server.py # Main MCP server entry point
│ ├── handlers/ # MCP request handlers
│ ├── matching/ # Interest matching algorithms
│ └── models/ # Data models and types
├── tests/
├── pyproject.toml # Project configuration and dependencies
└── README.md
Code Conventions
- Use type hints for all functions and class methods
- Follow PEP 8 style guide (enforced by Ruff)
- Write docstrings for all public functions and classes
- Keep functions focused and single-purpose
- Use descriptive variable and function names
- Always use absolute import paths (e.g.,
from mcp_chat.models import Usernotfrom .models import User)
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.
- 4d ago First seen · 85 lines · 595 tokens per session scan A e0df58ab2484
mcp-chat CLAUDE.md is an instructions file published in the GitHub repository hbd/mcp-chat (5 stars, last pushed 1y ago), licensed MIT. It adds 595 tokens to every session, about $0.0030 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
deepagents AGENTS.md
AGENTS.md instructions for langchain-ai/deepagents, covering global development guidelines for the deep agents monorepo, corridor security analysis, development workflow, suppressing ruff rules and pr conventions.
apm python.instructions.md
Python development guidelines.
lobster0 AGENTS.md
AGENTS.md instructions for NEDONION/lobster0, covering lobster0 agent 工程规范, 适用范围与优先级, 项目事实, 常用命令 and 首次安装或依赖变化后.
streamlit e2e_playwright.instructions.md
Instructions for streamlit/streamlit, covering streamlit e2e tests, test structure, key fixtures and utilities, external test mode and url handling (no localhost hardcoding).
codexspec CLAUDE.md
Claude Code instructions for Zts0hg/codexspec, covering claude.md - codexspec development guide, project overview, purpose, technology stack and architecture.
claude-tui CLAUDE.md
Claude Code instructions for slima4/claude-tui, covering claude.md, project overview, top-level scripts, tools and claude-code-statusline.