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/ctrlshiftbryan/chrome-devtools-mcp/claude-mdgit clone --depth 1 https://github.com/ctrlShiftBryan/chrome-devtools-mcpWhat 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 | $0.01580 | $0.01580 |
| Opus 5 | $0.00790 | $0.00790 |
| Sonnet 5 | $0.00316 | $0.00316 |
| Haiku 4.5 | $0.00158 | $0.00158 |
Grade A, and why
chrome-devtools-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 yesterday.
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 — 193 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
chrome-devtools-mcp is an MCP (Model Context Protocol) server that enables AI coding agents to control and inspect a live Chrome browser. It acts as a bridge between MCP clients (like Claude, Cursor, Copilot) and Chrome DevTools, exposing 27 tools across categories: input automation, navigation, emulation, performance, network, and debugging.
Build & Development Commands
# Install dependencies
npm ci
# Build (clean, compile TypeScript, post-build processing, rollup)
npm run build
# Type checking without emitting files
npm run typecheck
# Format code (ESLint + Prettier)
npm run format
# Check formatting without fixing
npm run check-format
# Start the MCP server
npm run start
# Start with debug logging
npm run start-debug
# Run all tests
npm test
# Run only tests marked with test.only
npm run test:only
# Run only tests without rebuilding first
npm run test:only:no-build
# Update test snapshots
npm run test:update-snapshots
# Generate tool reference documentation
npm run docs:generate
# Full docs generation (build + generate + format)
npm run docs
Testing
The project uses Node.js built-in test runner. Test files are in tests/ directory mirroring the src/ structure.
Run a single test file:
npm run build && node --require ./build/tests/setup.js --no-warnings=ExperimentalWarning --test-reporter spec --test-force-exit --test build/tests/path/to/file.test.js
Run specific test with test.only:
npm run test:only
Architecture
Entry Point Flow
src/index.ts- Node version validation, imports mainsrc/main.ts- Server setup, tool registration, stdio transportsrc/cli.ts- CLI argument parsing (yargs)src/browser.ts- Browser launch/connection via Puppeteer
Core Components
McpContext (src/McpContext.ts)
- Central state management for browser sessions
- Manages pages, snapshots, network/console collectors
- Handles emulation states (CPU throttling, network conditions)
- Provides methods for page selection, element lookup by UID, dialog handling
- Implements timeout adjustments based on throttling multipliers
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.
- yesterday First seen · 193 lines · 1,580 tokens per session scan A 0109de5fc077
chrome-devtools-mcp CLAUDE.md is an instructions file published in the GitHub repository ctrlShiftBryan/chrome-devtools-mcp (3 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 1,580 tokens to every session, about $0.0079 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
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
spring-ai-agentcore AGENTS.md
Instructions for spring-ai-community/spring-ai-agentcore, covering agents.md, project overview, architecture, key components and artifact store classes.
flyto-core CLAUDE.md
Instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.
metamask-extension AGENTS.md
AGENTS.md instructions for MetaMask/metamask-extension, covering agents.md, agent instructions summary, critical rules for agents, comprehensive guidelines location and quick setup.
deckforge AGENTS.md
Instructions for tph-kds/deckforge, covering deckforge agent entry point, code intelligence, read order, default routing and non-negotiable implementation rules.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.