mcp-browser CLAUDE.md

mcp-browser CLAUDE.md is an instructions file for Claude Code from bobmatnyc/mcp-browser. It costs 6,134 tokens per session, scanned A, original, MIT.

A set of coding instructions for an MCP browser project that captures and controls browser console logs through a Chrome extension and server. MCP is a way for an AI agent to connect to external tools.

In plain words
What is it for?
Building or modifying the browser extension, server, WebSocket communication, service layer, MCP tools, tests, and command-line workflows.
Why use it?
It defines the project's architecture, communication rules, security requirements, testing expectations, and coding boundaries so changes fit the existing design.

Instructions file for Claude Code

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

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/masa/Projects/mcp-browser.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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 mcp-browser CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/bobmatnyc/mcp-browser/claude-md.svg)](https://agentmods.dev/instructions/bobmatnyc/mcp-browser/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/bobmatnyc/mcp-browser/claude-md"><img src="https://agentmods.dev/badge/instructions/bobmatnyc/mcp-browser/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 6,134 This file is loaded in full into every session.
When invoked 6,134 The same file — it is already loaded in full.
Security scan A 0 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 5.1 $0.06134 $0.06134
Opus 5 $0.03067 $0.03067
Sonnet 5 $0.01227 $0.01227
Haiku 4.5 $0.00613 $0.00613

Measured 5d ago against content hash 58b0509b7f2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mcp-browser 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 5d 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 · 866 lines

How it starts

The opening of the file, as written. The whole thing — 866 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - AI Agent Instructions for mcp-browser

Project: MCP Browser - Browser console log capture and control via MCP Location: /Users/masa/Projects/mcp-browser Language: Python 3.10+ Architecture: Service-Oriented Architecture (SOA) + Chrome Extension + MCP Server Last Updated: 2025-12-15


🎯 Priority Index

🔴 CRITICAL Instructions

🟡 IMPORTANT Instructions

🟢 STANDARD Instructions

⚪ OPTIONAL Instructions


🔴 CRITICAL: Architecture Constraints

Service-Oriented Architecture (SOA)

NEVER violate these architectural boundaries:

# ✅ CORRECT: Services communicate through dependency injection
class BrowserService:
    def __init__(self, storage_service=None):
        self.storage_service = storage_service  # Injected dependency

# ❌ WRONG: Direct service instantiation breaks DI
class BrowserService:
    def __init__(self):
        self.storage_service = StorageService()  # Don't do this!

Service Layer Rules:

  1. All service methods MUST be async - No blocking operations
  2. 500-line service limit - Enforces single responsibility principle
  3. Constructor injection only - Dependencies resolved at creation time
  4. No circular dependencies - Container enforces dependency graph
  5. Interface segregation - Services expose minimal public APIs

Read the full file on GitHub · 866 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. 5d ago First seen · 866 lines · 6,134 tokens per session scan A 58b0509b7f2d

Subscribe to this mod's changes

mcp-browser CLAUDE.md is an instructions file published in the GitHub repository bobmatnyc/mcp-browser (2 stars, last pushed 8mo ago), licensed MIT. It adds 6,134 tokens to every session, about $0.0307 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.