What is macwright CLAUDE.md?

A project instruction set for MacWright, an MCP server that lets AI agents control a macOS desktop. It covers screenshots, mouse and keyboard input, windows, clipboard, Safari, AppleScript, shell commands, notifications, and visual screen parsing.

Use it when developing, building, testing, or setting up MacWright for native macOS desktop and Safari automation.

It explains the project’s macOS-only requirements, commands, architecture, and permission setup. This helps agents avoid applying Linux assumptions or missing required Accessibility access.

How ruchit-p/macwright configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ruchit-p/macwright. 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/ruchit-p/macwright/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ruchit-p/macwright

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/ruchit-p/macwright/claude-md/github.svg)](https://agentmods.dev/instructions/ruchit-p/macwright/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/ruchit-p/macwright/claude-md"><img src="https://agentmods.dev/badge/instructions/ruchit-p/macwright/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/ruchit-p/macwright/claude-md"><img src="https://agentmods.dev/badge/instructions/ruchit-p/macwright/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 807 This file is loaded in full into every session.

When invoked 807 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.

Model	Per session	Once invoked
Fable 5.1	$0.00807	$0.00807
Opus 5.5	$0.00323	$0.00323
Sonnet 5.5	$0.00161	$0.00161
Haiku 4.5	$0.00081	$0.00081

Measured 2mo ago against content hash 7408ce19ebfa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

macwright 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 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.

CLAUDE.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MacWright

What Is This?

MacWright is an MCP server for reliable native macOS desktop control from AI agents. It targets macOS, uses Node.js and TypeScript, and exposes tools for screenshots, mouse, keyboard, scroll, clipboard, window management, native Accessibility UI automation, Safari automation, AppleScript, shell commands, notifications, waits, and visual UI parsing.

This is not a Linux desktop automation server. The core tools depend on macOS APIs and commands such as Accessibility/System Events, AppleScript/JXA, Safari Apple Events, screencapture, pbcopy/pbpaste, and cliclick.

Key Commands

Build: npm run build
Portable schema validation: npm test
Native macOS smoke tests: npm run test:macos-smoke
Setup and permission doctor: ./setup.sh
Checks only: ./setup.sh --doctor
Open macOS Privacy panes: ./setup.sh --open-settings

Requirements

macOS, tested on Apple Silicon.
Node.js >= 18.
cliclick, installed by ./setup.sh or manually with brew install cliclick.
Optional OmniParser server on port 8650 for screen_parse.

Required macOS permissions are granted to the app that launches MacWright, not to MacWright itself:

Accessibility for mouse, keyboard, scroll, native UI reads/clicks, and window control.
Screen Recording for screenshots, visual verification, wait_for_change, and screen_parse.
Automation prompts for AppleScript, System Events, Safari, and app-specific control.
Input Monitoring may be requested by macOS for some keyboard/input paths.
Safari JavaScript from Apple Events is required for Safari JS tools.

After changing macOS privacy permissions, restart the controlling app before retesting.

Architecture

Server entry: src/index.ts.
Tool implementations: src/tools/**.
Shared helpers: src/utils/**.
Built server: dist/index.js.
Tools are registered through registerXxxTools(server) functions.
Tool inputs use Zod schemas; descriptions are part of the public MCP contract and should stay clear and actionable.

Read the full file on GitHub · 87 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.

2mo ago First seen · 87 lines · 807 tokens per session scan A 7408ce19ebfa

Subscribe to this mod's changes

macwright CLAUDE.md is an instructions file published in the GitHub repository ruchit-p/macwright (0 stars, last pushed 2mo ago), licensed MIT. It adds 807 tokens to every session, about $0.0032 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 2026-08-31.

accessibility ai-agents automation desktop-control hermes-agent macos

macwright CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
macwright CLAUDE.mdruchit-p/macwright	Instructions file	0	2mo ago	MIT	A	807	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

macwright: Instructions file for Claude Code