What is playwright-mcp-mod CLAUDE.md?

A project instruction file for a Playwright MCP server, a tool that lets language models control web browsers through structured page information. It documents the project layout and its build, test, browser-specific, Docker, lint, and maintenance commands.

Use it when building, testing, linting, or changing the Playwright MCP server, including tests in Chrome, Firefox, or WebKit.

It gives Claude Code the repository-specific guidance needed to work on the project and run its checks correctly.

How georgeLochner/playwright-mcp-mod configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to georgeLochner/playwright-mcp-mod. 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/georgeLochner/playwright-mcp-mod/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/georgeLochner/playwright-mcp-mod

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/georgelochner/playwright-mcp-mod/claude-md.svg)](https://agentmods.dev/instructions/georgelochner/playwright-mcp-mod/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/georgelochner/playwright-mcp-mod/claude-md"><img src="https://agentmods.dev/badge/instructions/georgelochner/playwright-mcp-mod/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 641 This file is loaded in full into every session.

When invoked 641 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00641	$0.00641
Opus 5	$0.00320	$0.00320
Sonnet 5	$0.00128	$0.00128
Haiku 4.5	$0.00064	$0.00064

Measured 7d ago against content hash 57b5e09f2a60, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

playwright-mcp-mod 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.

CLAUDE.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 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

Playwright MCP is a Model Context Protocol (MCP) server that provides browser automation capabilities using Playwright. It enables LLMs to interact with web pages through structured accessibility snapshots rather than screenshots.

Build and Test Commands

# Run all tests (Chrome by default)
npm test

# Run tests for specific browsers
npm run ctest    # Chrome
npm run ftest    # Firefox
npm run wtest    # WebKit

# Run a single test file
npx playwright test tests/core.spec.ts

# Run a single test by name
npx playwright test -g "browser_navigate"

# Run tests in Docker
npm run dtest

# Lint/update README (generates tool docs from code)
npm run lint

# Copy config.d.ts from upstream Playwright repo
npm run copy-config

# Roll (copy-config + lint)
npm run roll

Architecture

This is a thin wrapper package around the MCP implementation in the main Playwright repository. The core MCP logic lives in playwright/lib/mcp/ - this package just re-exports it.

Entry points:

cli.js - CLI entry point that patches MCP Server before loading Playwright modules. Adds usage tracking (writes to usage.txt) and tool filtering via config file. Uses playwright-core/lib/utilsBundle for command parsing and playwright/lib/mcp/program for MCP commands.
index.js - Library entry point, exports createConnection from playwright/lib/mcp/index
config.d.ts - TypeScript configuration types (copied from main Playwright repo via npm run copy-config)

Test structure:

tests/fixtures.ts - Custom Playwright test fixtures providing MCP client setup via @modelcontextprotocol/sdk
tests/testserver/ - HTTP/HTTPS test server for testing browser automation
Tests use StdioClientTransport to communicate with the MCP server spawned as a subprocess

Browser extension:

extension/ - Chrome extension ("Playwright MCP Bridge") that allows connecting to existing browser tabs
Has its own build system (Vite), tests, and tsconfig

Read the full file on GitHub · 69 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.

7d ago First seen · 69 lines · 641 tokens per session scan A 57b5e09f2a60

Subscribe to this mod's changes

playwright-mcp-mod CLAUDE.md is an instructions file published in the GitHub repository georgeLochner/playwright-mcp-mod (0 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 641 tokens to every session, about $0.0032 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 2026-09-01.

Browser automation E2E testing Testing

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

playwright-mcp-mod: Instructions file for Claude Code