playwright-mcp-wsl: Instructions file for Codex

AGENTS.md

playwright-mcp-wsl AGENTS.md is an instructions file for Codex, OpenCode from NorthwoodsSentinel/playwright-mcp-wsl. It costs 2,852 tokens per session, scanned A, original, Apache-2.0.

Project instructions for a small JavaScript wrapper around Playwright MCP, a browser-automation service, when used on Windows Subsystem for Linux (WSL).

In plain words
What is it for?
Guiding changes to the wrapper, including its Chromium settings and configuration merging.
Why use it?
It keeps runtime rules, known gaps, project structure, and WSL-specific browser settings in one place so agents do not make inconsistent changes.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is NorthwoodsSentinel/playwright-mcp-wsl's own configuration. It tells Codex and OpenCode how to work on playwright-mcp-wsl 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-mcp-wsl configures →

Reuse

Borrowing it

Nothing to install: this file belongs to NorthwoodsSentinel/playwright-mcp-wsl. 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/NorthwoodsSentinel/playwright-mcp-wsl/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/NorthwoodsSentinel/playwright-mcp-wsl

Made for: Codex, OpenCode.

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-mcp-wsl AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/northwoodssentinel/playwright-mcp-wsl/agents-md/github.svg)](https://agentmods.dev/instructions/northwoodssentinel/playwright-mcp-wsl/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/northwoodssentinel/playwright-mcp-wsl/agents-md"><img src="https://agentmods.dev/badge/instructions/northwoodssentinel/playwright-mcp-wsl/agents-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-mcp-wsl AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/northwoodssentinel/playwright-mcp-wsl/agents-md"><img src="https://agentmods.dev/badge/instructions/northwoodssentinel/playwright-mcp-wsl/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,852 This file is loaded in full into every session.
When invoked 2,852 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 $0.02852 $0.02852
Opus 5.5 $0.01141 $0.01141
Sonnet 5.5 $0.00570 $0.00570
Haiku 4.5 $0.00285 $0.00285

Measured yesterday against content hash 00a66318f270, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

playwright-mcp-wsl AGENTS.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.

AGENTS.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — playwright-mcp-wsl

Rules for any agent (or person) changing this repo. The shape and most of the wording come from Cliff Hall's modelcontextprotocol/inspector AGENTS.md (branch v2/main, commit d330df9617e44ec893bc1a53618662239342d433), as the maintainer ruled on it. Where his way and ours differ, the source's way stands until there is a reason to depart; every departure below says why.

CLAUDE.md contains only @./AGENTS.md. Keep one copy of these rules: two copies are strictly worse than one, because the stale copy is indistinguishable from the live one.

What this is

A drop-in wrapper for @playwright/mcp that, on WSL, points Playwright at a config adding three Chromium flags (--disable-gpu, --disable-software-rasterizer, --disable-dev-shm-usage), merging them into the user's own config when PLAYWRIGHT_MCP_CONFIG is already set. Off WSL it changes nothing. README.md is the user-facing description; read it before changing anything. It is a published npm package written in plain JavaScript (CommonJS), and stays JavaScript. There is no build step and nothing here deploys or publishes.

Rules for the runtime code

  • No behavior change without an issue that says so. A refactor, a lint fix, a type fix or a review suggestion is never a reason to change what the code does. Comment, formatting and JSDoc-only edits are allowed when the emitted JavaScript stays the same; check by comparing bun build --no-bundle --minify-syntax --minify-whitespace output for each of cli.js, detect.js and index.js before and after.
  • The config must be in place before @playwright/mcp or Playwright loads. On WSL, both cli.js and index.js set PLAYWRIGHT_MCP_CONFIG before their first Playwright require; the tests assert the value seen at load time.
  • A user's config is read, never rewritten. The merge writes a separate file in the OS temp directory and removes it on exit.
  • The published file set is files in package.json. Gate tooling, tests and types/ are not published.

Read the full file on GitHub · 163 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. yesterday First seen · 163 lines · 2,852 tokens per session scan A 00a66318f270

Subscribe to this mod's changes

playwright-mcp-wsl AGENTS.md is an instructions file published in the GitHub repository NorthwoodsSentinel/playwright-mcp-wsl (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,852 tokens to every session, about $0.0114 per session on Opus 5.5. 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 2026-11-17.

Related

playwright-mcp-wsl AGENTS.md compared with instructions from other repositories

playwright-mcp-wsl AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
playwright-mcp-wsl AGENTS.mdNorthwoodsSentinel/playwright-mcp-wslInstructions file0yesterdayApache-2.0A2,852Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283ktodayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot