agentmods.dev

patchright-mcp: Instructions file for Codex

AGENTS.md

patchright-mcp AGENTS.md is an instructions file for Codex, OpenCode from Ikaleio/patchright-mcp. It costs 307 tokens per session, scanned A, original, Apache-2.0.

Maintenance instructions for Patchright MCP, a server that lets AI tools control web browsers through Playwright. MCP is a standard way for an AI tool to call functions exposed by another program.

In plain words
What is it for?
Use them when updating Playwright MCP or Patchright versions, refreshing npm lockfiles, and checking that the package and command-line names remain correct.
Why use it?
They provide a checklist for keeping the upstream browser-control package, Patchright dependency, package versions, and lockfiles in sync.

Instructions file for CodexOpenCode

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

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

not rated 25repo 8mo ago A scan 307 tokens original Apache-2.0
View source ↗ Ikaleio/patchright-mcp
Reuse

Borrowing it

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

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 patchright-mcp AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ikaleio/patchright-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ikaleio/patchright-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 307 This file is loaded in full into every session.
When invoked 307 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 $0.00307 $0.00307
Opus 5.5 $0.00123 $0.00123
Sonnet 5.5 $0.00061 $0.00061
Haiku 4.5 $0.00031 $0.00031

Measured 2mo ago against content hash 68f587e42b32, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

patchright-mcp 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 2mo 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.

AGENTS.md · 34 lines

What it actually says

Patchright MCP Agent Instructions

These instructions are for coding agents updating upstream versions or the Patchright dependency.

Update the upstream playwright-mcp version

  1. Check the latest upstream version:
    • npm view @playwright/mcp version
  2. Sync versions across this repo:
    • package.json -> version
    • packages/extension/package.json -> version
    • packages/extension/manifest.json -> version
  3. Refresh lockfiles:
    • npm install --package-lock-only
    • npm install --package-lock-only --workspace=packages/extension
  4. Sanity-check:
    • rg -n "\"version\"" package.json packages/extension/package.json packages/extension/manifest.json to confirm versions match.

Update the Patchright version

  1. Check the latest Patchright version:
    • npm view patchright version
  2. Update dependency:
    • packages/playwright-mcp/package.json -> dependencies.patchright
  3. Refresh lockfile:
    • npm install --package-lock-only
  4. Sanity-check:
    • rg -n "patchright" packages/playwright-mcp/package.json package-lock.json to confirm the new version is captured.

Notes

  • Keep the package name as patchright-mcp and the CLI bin as mcp-server-patchright.
  • PLAYWRIGHT_MCP_EXTENSION_TOKEN is retained for compatibility with the upstream server.
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. 2mo ago First seen · 34 lines · 307 tokens per session scan A 68f587e42b32

Subscribe to this mod's changes

patchright-mcp AGENTS.md is an instructions file published in the GitHub repository Ikaleio/patchright-mcp (25 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 307 tokens to every session, about $0.0012 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 2026-08-30.

Browser automation
Related

patchright-mcp AGENTS.md compared with instructions from other repositories

patchright-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
patchright-mcp AGENTS.mdIkaleio/patchright-mcpInstructions file258mo agoApache-2.0A307Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot