What is puppeteer-real-browser-mcp-server CLAUDE.md?

Project instructions for developing a Puppeteer-based real-browser MCP server. Puppeteer is a tool for controlling a web browser with code, and an MCP server connects such tools to an AI assistant.

Use them when modifying that browser-automation server to guide research, planning, coding standards, and test-driven development, or TDD—writing tests around expected behavior while implementing the code.

They provide a required order for development: research current documentation and practices before planning or coding. This helps account for changing APIs and common implementation problems.

How withLinda/puppeteer-real-browser-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to withLinda/puppeteer-real-browser-mcp-server. 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/withLinda/puppeteer-real-browser-mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/withLinda/puppeteer-real-browser-mcp-server

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/withlinda/puppeteer-real-browser-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/withlinda/puppeteer-real-browser-mcp-server/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/withlinda/puppeteer-real-browser-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/withlinda/puppeteer-real-browser-mcp-server/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/withlinda/puppeteer-real-browser-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/withlinda/puppeteer-real-browser-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 5,427 This file is loaded in full into every session.

When invoked 5,427 The same file — it is already loaded in full.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin 92% copy Near-identical to another mod 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	$0.05427	$0.05427
Opus 5	$0.02714	$0.02714
Sonnet 5	$0.01085	$0.01085
Haiku 4.5	$0.00543	$0.00543

Measured 11d ago against content hash 0b2897443b19, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

puppeteer-real-browser-mcp-server CLAUDE.md scanned grade A 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 11d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

const { spawn } = require('child_process'); // CommonJS

Origin

This is a copy

92% identical to puppeteer-real-browser-mcp-server AGENTS.md — 40 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 719 lines

How it starts

The opening of the file, as written. The whole thing — 719 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Instructions for Claude Code

MANDATORY: Research-First Development

Before planning or implementing ANY solution, you MUST:

Web Research Phase (REQUIRED)
- Web search for the latest documentation on relevant technologies about the problem at hand
- Look up current best practices for the problem domain
- Check for recent updates or changes in APIs/frameworks
- Research common pitfalls and solutions
Planning Phase (After Research)
- Think hard and create a detailed plan based on research findings
- Reference specific documentation or sources found
- Identify potential challenges discovered during research
Implementation Phase
- Implement based on researched best practices
- Include comments referencing research sources
- Apply patterns found during research phase

Example Research Queries

"latest [technology] best practices 2025"
"[framework] recent changes documentation"
"[problem domain] implementation patterns"
"[error message] solutions"

IMPORTANT: Never skip the web research phase. Always state what you're web researching and share findings before proceeding.

📝 Coding Standards

Remember we're using zsh shell in MacOS
You MUST prefer using Typescript instead of JavaScript, but if the task is not possible in Typescript or already written in Javascript, you can use JavaScript
If something is not clear, you MUST ask for clarification
if something is not installed, please install it instead of looking alternative methods
If something is not working, please debug it instead of looking for alternatives
if something is not possible, please explain why it is not possible instead of looking for alternatives

🧪 Test-Driven Development (TDD) Workflow

Core TDD Principles (Red-Green-Refactor)

TDD follows a strict three-phase cycle for every feature:

🔴 RED    →  🟢 GREEN  →  🔵 REFACTOR
Write      Make it      Make it
failing    work         better
test       (minimal)    (clean)
  ↑                        ↓
  ←←←←←←←←←←←←←←←←←←←←←←←←←←←←

Read the full file on GitHub · 719 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.

11d ago First seen · 719 lines · 5,427 tokens per session scan A 0b2897443b19

Subscribe to this mod's changes

puppeteer-real-browser-mcp-server CLAUDE.md is an instructions file published in the GitHub repository withLinda/puppeteer-real-browser-mcp-server (26 stars, last pushed 2mo ago), licensed MIT. It adds 5,427 tokens to every session, about $0.0271 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). It is 92% identical to puppeteer-real-browser-mcp-server AGENTS.md, differing in 40 lines, and is treated as a copy.

Browser automation

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

puppeteer-real-browser-mcp-server: Instructions file for Claude Code