PlayMCP: Instructions file for Codex

AGENTS.md

PlayMCP AGENTS.md is an instructions file for Codex, OpenCode from jomon003/PlayMCP. It costs 701 tokens per session, scanned A, original, MIT.

Repository instructions for PlayMCP, a TypeScript server that exposes Playwright browser automation through MCP, a tool protocol for connecting AI agents to programs. They describe commands, files, tests, and project rules.

In plain words
What is it for?
Use them when developing or reviewing PlayMCP changes, running its build and tests, or locating its server, tools, and browser-automation code.
Why use it?
They give coding agents the local project context and verification steps needed to make changes without guessing how the repository works.

Instructions file for CodexOpenCode

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

This is jomon003/PlayMCP's own configuration. It tells Codex and OpenCode how to work on PlayMCP 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 PlayMCP configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jomon003/PlayMCP. 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/jomon003/PlayMCP/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/jomon003/PlayMCP

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 PlayMCP AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jomon003/playmcp/agents-md/github.svg)](https://agentmods.dev/instructions/jomon003/playmcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/jomon003/playmcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jomon003/playmcp/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 PlayMCP AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jomon003/playmcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jomon003/playmcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 701 This file is loaded in full into every session.
When invoked 701 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 $0.00701 $0.00701
Opus 5.5 $0.00280 $0.00280
Sonnet 5.5 $0.00140 $0.00140
Haiku 4.5 $0.00070 $0.00070

Measured yesterday against content hash acf8a7c16012, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

PlayMCP 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 · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for coding agents working on this repository. Usage docs for people live in README.md, and the tool reference is in docs/tools.md.

What this is

An MCP server (stdio) that exposes Playwright browser automation as tools. It's TypeScript and ESM, runs on Node 20+, and is built on @modelcontextprotocol/sdk with zod schemas.

Commands

npm install
npx playwright install chromium   # once; the tests need it
npm run build                     # tsc -> dist/
npm run typecheck
npm test                          # builds, then runs node:test on test/tools.test.js and test/stdio.test.js (~5s, headless)
npm run inspect                   # MCP Inspector against dist/index.js

Run npm test before finishing any change. CI runs the same command on Node 20, 22 and 24 inside the mcr.microsoft.com/playwright image. When you upgrade playwright, update that image tag in .github/workflows/ci.yml to match.

Layout

Path Role
src/index.ts Entry point and bin. Connects the stdio transport and closes the browser on exit.
src/server.ts createServer(). Registers every tool (schema, annotations, handler) and the server instructions.
src/browser.ts BrowserController. Owns the browser, context and page, plus the console, network and dialog state. Contains no MCP code.
test/tools.test.js Tests each tool through an in-memory MCP client against test/fixtures/index.html.
test/stdio.test.js End-to-end test that spawns dist/index.js over stdio.

Rules

  • Never write to stdout from server code. stdout carries the MCP protocol. Use console.error, or the log() helper in browser.ts, which is gated by PLAYMCP_DEBUG.
  • Keep Playwright logic in BrowserController and MCP concerns (schemas, result formatting) in server.ts.
  • Handlers throw on failure. The tool() wrapper turns exceptions into isError results, so don't catch-and-hide errors in handlers.
  • Use locators (page.locator(...)), not the deprecated page.click/page.type style APIs.
  • Code passed to page.evaluate runs in the browser and can't reference Node variables. Pass them as arguments.

Read the full file on GitHub · 50 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 · 50 lines · 701 tokens per session scan A acf8a7c16012

Subscribe to this mod's changes

PlayMCP AGENTS.md is an instructions file published in the GitHub repository jomon003/PlayMCP (15 stars, last pushed yesterday), licensed MIT. It adds 701 tokens to every session, about $0.0028 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 2026-11-12.

Related

PlayMCP AGENTS.md compared with instructions from other repositories

PlayMCP AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
PlayMCP AGENTS.mdjomon003/PlayMCPInstructions file15yesterdayMITA701Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,086GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file280k2d agoMITA4,325Codex, OpenCode