agentmods.dev

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.

In plain words
What is it for?
Use it when developing, building, testing, or setting up MacWright for native macOS desktop and Safari automation.
Why use it?
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.

Instructions file

0 20d ago A scan 807 tokens original MIT
View the source file ruchit-p/macwright
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/ruchit-p/macwright/claude-md
Clone the repo
git clone --depth 1 https://github.com/ruchit-p/macwright
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. Scan, not verified.
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 $0.00807 $0.00807
Opus 5 $0.00404 $0.00404
Sonnet 5 $0.00161 $0.00161
Haiku 4.5 $0.00081 $0.00081

Measured yesterday against content hash 7408ce19ebfa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

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.

  1. yesterday 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 20d ago), licensed MIT. It adds 807 tokens to every session, about $0.0040 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.

accessibilityai-agentsautomationdesktop-controlhermes-agentmacos
Related

Other instructions, from other repositories

barkeep AGENTS.md

Instructions for iannuttall/barkeep, covering agent notes, product rules, repo map, commands and app structure.

iannuttall/barkeep · 1,560 tokens

Loupe CLAUDE.md

Instructions for smughead/Loupe, covering claude.md, build commands, build the app (from project root), run all tests (unit + ui) and run only spm package unit tests.

smughead/Loupe · 709 tokens

blurt AGENTS.md

Instructions for AssemblyAI/blurt, covering agents.md, start here, the two layers, repository map and verifying your work.

AssemblyAI/blurt · 22,629 tokens

blurt CLAUDE.md

Instructions for AssemblyAI/blurt, covering claude.md, hooks (.claude/settings.json), skills (.claude/skills/), subagents (.claude/agents/) and permissions.

AssemblyAI/blurt · 1,387 tokens

OpenAra AGENTS.md

Instructions for Aradotso/OpenAra, covering openara agent guide, read first, working rules and where things live.

Aradotso/OpenAra · 319 tokens

barkeep CLAUDE.md

Instructions for iannuttall/barkeep, a project described as: Manage hidden macOS menu bar items from one place.

iannuttall/barkeep · 3 tokens