playwright-pool: Instructions file for Claude Code

CLAUDE.md

playwright-pool CLAUDE.md is an instructions file for Claude Code from zbrooklyn-claude-labs/playwright-pool. It costs 499 tokens per session, scanned A, original, MIT.

A project instruction file for a Playwright browser-pool MCP server. Playwright is a tool for controlling web browsers, and MCP is a standard way for agents to call tools provided by another program.

In plain words
What is it for?
Use it when developing or manually testing the Playwright pool, including launching, navigating, checking authentication, and closing browser windows.
Why use it?
It explains the repository structure, branch process, manual checks, and the rule that visible browser output must be verified against the code and measurements.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is zbrooklyn-claude-labs/playwright-pool's own configuration. It tells Claude Code how to work on playwright-pool itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything playwright-pool configures →

Reuse

Borrowing it

Nothing to install: this file belongs to zbrooklyn-claude-labs/playwright-pool. 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/zbrooklyn-claude-labs/playwright-pool/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/zbrooklyn-claude-labs/playwright-pool

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 playwright-pool CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zbrooklyn-claude-labs/playwright-pool/claude-md/github.svg)](https://agentmods.dev/instructions/zbrooklyn-claude-labs/playwright-pool/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/zbrooklyn-claude-labs/playwright-pool/claude-md"><img src="https://agentmods.dev/badge/instructions/zbrooklyn-claude-labs/playwright-pool/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.

agentmods 80×15 button for playwright-pool CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/zbrooklyn-claude-labs/playwright-pool/claude-md"><img src="https://agentmods.dev/badge/instructions/zbrooklyn-claude-labs/playwright-pool/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 499 This file is loaded in full into every session.
When invoked 499 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00499 $0.00499
Opus 5 $0.00249 $0.00249
Sonnet 5 $0.00100 $0.00100
Haiku 4.5 $0.00050 $0.00050

Measured 8d ago against content hash 31e303fe518a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

playwright-pool 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 8d 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 · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Playwright Pool — Project Rules

Overview

MCP server that dynamically manages authenticated Playwright browser pools from a single golden profile.

Branch Rules

  • main is the default branch
  • Feature work on feature branches, merge via PR

Key Files

  • server.js — the entire MCP server (single file)
  • package.json — dependencies and metadata
  • README.md — public documentation

Testing

No automated tests yet. Manual testing:

  1. Configure in .mcp.json
  2. Launch windows via pool_launch
  3. Verify auth with pool_navigate to authenticated pages
  4. Verify cleanup with pool_close all

Core Design Principle: Visual Truth

The rendered UI is the source of truth, not the source code. All audit tools must prioritize what the user actually sees over what the code says should happen.

Three-Layer Audit Rule — all three must agree before any UI claim:

  1. Code check (what the CSS/HTML says)
  2. Programmatic measurement (what the browser computed — getComputedStyle, getBoundingClientRect)
  3. Visual verification (screenshot — what the user actually sees)

Code saying padding: 16px means nothing if a conflicting style makes the visual result wrong. When building audit tools, always verify against the rendered output, not just the DOM/CSS.

Performance Guidelines

  • Prefer CLI for audits and screenshots — saves context tokens (~20 tokens for a file path vs ~28,000 for a full snapshot)
  • Use MCP for interactive browser sessions (clicking, navigating, reacting to page state)
  • Always use snapshot_compact over browser_snapshot — 20x fewer tokens (~1,375 vs ~28,000)
  • First pool_launch has ~17s overhead (template creation); subsequent operations are fast (<2s)

Architecture Decisions

  • Auth overlay, not full profile copy — copying entire Chromium profiles causes crashes due to cache/GPU data tied to specific Chromium builds. We create a fresh profile and overlay only the 13 auth-critical files.
  • Template caching — the first pool_launch creates a template profile (one headless Chromium launch). Subsequent launches just copy the template (filesystem only, no Chromium launch).
  • UUID session isolation — each MCP server process gets a random UUID prefix. Concurrent sessions never collide on disk.

Read the full file on GitHub · 43 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. 8d ago First seen · 43 lines · 499 tokens per session scan A 31e303fe518a

Subscribe to this mod's changes

playwright-pool CLAUDE.md is an instructions file published in the GitHub repository zbrooklyn-claude-labs/playwright-pool (0 stars, last pushed 2mo ago), licensed MIT. It adds 499 tokens to every session, about $0.0025 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.

Related

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.

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

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens