Borrowing it
Nothing to install: this file belongs to eyalzh/browser-control-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.
curl -O https://raw.githubusercontent.com/eyalzh/browser-control-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/eyalzh/browser-control-mcpWrote 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/eyalzh/browser-control-mcp/claude-md)<a href="https://agentmods.dev/instructions/eyalzh/browser-control-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/eyalzh/browser-control-mcp/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 5.1 | $0.00467 | $0.00467 |
| Opus 5 | $0.00234 | $0.00234 |
| Sonnet 5 | $0.00093 | $0.00093 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
browser-control-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 7d 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.
What it actually says
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Commands
Installation
npm install # Install all dependencies (includes subproject dependencies)
Build
npm run build # Build all projects using nx
Individual project builds
# MCP Server
cd mcp-server && npm run build
# Firefox Extension
cd firefox-extension && npm run build
Test
cd firefox-extension && npm test
Start MCP Server
cd mcp-server && npm start
Package DXT
cd mcp-server && npm run pack-dxt
Architecture
This is a monorepo with three main components:
- mcp-server: Node.js MCP server that communicates with Claude Desktop and the browser extension via WebSocket
- firefox-extension: Firefox browser extension that executes browser actions
- common: Shared TypeScript interfaces for message passing between server and extension
Communication Flow
- MCP Server ↔ Claude Desktop: MCP protocol over stdio
- MCP Server ↔ Firefox Extension: WebSocket with authentication via shared secret
- Extension uses Firefox WebExtensions API for browser control
Key Files
mcp-server/server.ts: Main MCP server with tool definitionsmcp-server/browser-api.ts: WebSocket client for extension communicationfirefox-extension/background.ts: Extension background scriptfirefox-extension/message-handler.ts: Handles server messages and executes browser actionscommon/server-messages.ts: Messages sent from server to extensioncommon/extension-messages.ts: Messages sent from extension to server
Authentication
The extension generates a random secret key that must be configured in the MCP server's environment as EXTENSION_SECRET. The server connects to the extension on port 8089 (configurable via EXTENSION_PORT).
Development Notes
- Uses esbuild for extension bundling
- TypeScript throughout with shared interfaces
- Jest for testing (extension only)
- Nx for monorepo management
- Extension requires user consent for accessing webpage content by default
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.
- 7d ago First seen · 70 lines · 467 tokens per session scan A f92d3ff4365c
browser-control-mcp CLAUDE.md is an instructions file published in the GitHub repository eyalzh/browser-control-mcp (320 stars, last pushed 14d ago), licensed MIT. It adds 467 tokens to every session, about $0.0023 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 2026-08-30.
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.
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.
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).
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).
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.
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.