MadameClaude: Instructions file for Claude Code

CLAUDE.md

MadameClaude CLAUDE.md is an instructions file for Claude Code from williamkapke/MadameClaude. It costs 609 tokens per session, scanned B, original, MIT.

Repository instructions for Madame Claude, a Node.js monitoring system that displays Claude Code tool-use events in a web interface.

In plain words
What is it for?
Use them when developing or debugging the event bridge, HTTP and WebSocket server, or monitoring interface.
Why use it?
They explain how events travel from hooks through a bridge and server to the live interface, helping agents work within the existing architecture.

Instructions file for Claude Code

Written for Claude Code: PostToolUse hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is williamkapke/MadameClaude's own configuration. It tells Claude Code how to work on MadameClaude 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 MadameClaude configures →

Reuse

Borrowing it

Nothing to install: this file belongs to williamkapke/MadameClaude. 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/williamkapke/MadameClaude/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/williamkapke/MadameClaude

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 MadameClaude CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/williamkapke/madameclaude/claude-md/github.svg)](https://agentmods.dev/instructions/williamkapke/madameclaude/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/williamkapke/madameclaude/claude-md"><img src="https://agentmods.dev/badge/instructions/williamkapke/madameclaude/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 MadameClaude CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/williamkapke/madameclaude/claude-md"><img src="https://agentmods.dev/badge/instructions/williamkapke/madameclaude/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 609 This file is loaded in full into every session.
When invoked 609 The same file — it is already loaded in full.
Security scan B 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 $0.00609 $0.00609
Opus 5.5 $0.00244 $0.00244
Sonnet 5.5 $0.00122 $0.00122
Haiku 4.5 $0.00061 $0.00061

Measured 2mo ago against content hash 3cbf2295ea04, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

MadameClaude CLAUDE.md scanned grade B 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 2mo 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

`~/.claude/settings.json`:
CLAUDE.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 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

Madame Claude is a monitoring system for Claude Code hooks that captures and streams tool usage events to a web interface. It consists of three Node.js-based components that work together to provide real-time visibility into Claude Code's tool usage.

Architecture

The system follows an event-driven architecture with this flow:

Claude Code → Hooks → bridge → HTTP POST → Server → WebSocket → UI

Components

  1. bridge: Reads JSON events from stdin and POSTs them to the server

    • Located in server/bridge.js
    • Stateless converter that always exits with code 0
    • Passes data through without modification
    • Posts to http://localhost:4519/
  2. server: Receives POSTs and streams via WebSocket

    • Located in server/server.js
    • Runs on port 4519 (HTTP and WebSocket)
    • Adds timestamps to received messages
    • Broadcasts all received messages to connected clients
    • Maintains WebSocket connections for real-time updates
  3. ui: Web interface for displaying events (served by server)

Development Commands

cd server
npm install         # Install dependencies
npm start           # Run the server
npm run dev         # Run with file watching
npm test            # Run tests
npm run lint        # Lint code

# Run components directly
node server.js      # Start the server
node bridge.js      # Run the bridge (for testing)

# Or use npx after npm install
npx madame-claude         # Start the server
npx madame-claude-bridge  # Run the bridge

Integration with Claude Code

This project integrates via Claude Code's hooks system. Users configure hooks in ~/.claude/settings.json:

{
  "hooks": {
    "PostToolUse": {
      "command": "/absolute/path/to/MadameClaude/server/bridge.js"
    }
  }
}

Hook types: PreToolUse, PostToolUse, Notification, Stop, SubagentStop

Key Implementation Notes

Read the full file on GitHub · 89 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. 2mo ago First seen · 89 lines · 609 tokens per session scan B 3cbf2295ea04

Subscribe to this mod's changes

MadameClaude CLAUDE.md is an instructions file published in the GitHub repository williamkapke/MadameClaude (25 stars, last pushed 1y ago), licensed MIT. It adds 609 tokens to every session, about $0.0024 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

MadameClaude CLAUDE.md compared with instructions from other repositories

MadameClaude CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
MadameClaude CLAUDE.mdwilliamkapke/MadameClaudeInstructions file251y agoMITB609Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,649GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot