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.
npx agentmods add skills/ruchit-p/macwright/macwright-devnpx skills add ruchit-p/macwright --skill macwright-devgit clone --depth 1 https://github.com/ruchit-p/macwrightWhat 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 | $0.00089 | $0.01290 |
| Opus 5 | $0.00044 | $0.00645 |
| Sonnet 5 | $0.00018 | $0.00258 |
| Haiku 4.5 | $0.00009 | $0.00129 |
Grade A, and why
macwright-dev 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.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MacWright MCP Server Development
Project Structure
macwright/
├── src/
│ ├── index.ts — Server entry, registers all tools
│ └── tools/
│ ├── mouse.ts — click, double_click, right_click, move_mouse, get_mouse_position, drag
│ ├── keyboard.ts — type_text, press_key
│ ├── screenshot.ts — screenshot (supports x,y,width,height region capture)
│ ├── screen.ts — get_screen_size
│ ├── scroll.ts — scroll
│ ├── shell.ts — run_shell (spawn-based, supports stdin input, timeout, cwd)
│ ├── safari.ts — safari_url, safari_js, safari_navigate_back, safari_reload,
│ │ scroll_page, find_element, click_element, wait_for_element,
│ │ get_page_text, fill_form, get_element_attr, screenshot_element,
│ │ safari_tabs
│ ├── clipboard.ts — get_clipboard, set_clipboard
│ ├── applescript.ts — run_applescript
│ ├── notification.ts — send_notification
│ └── wait.ts — wait
├── src/utils/
│ ├── exec.ts — execCommand helper
│ └── capture.ts — afterAction (wait + screenshot chaining)
└── dist/ — Compiled JS (auto-generated)
Build & Test Workflow
npm run build # TypeScript → dist/
CRITICAL: After npm run build, the MCP server process must be restarted to pick up new tools. The server runs from dist/index.js — changes only take effect after restart + rebuild. The Claude Code IDE integration will restart on reconnect.
To verify a new tool works: use run_applescript to test the underlying AppleScript first (no restart needed), then rebuild and use the actual MCP tool after restart.
Adding a New Tool
- Find the appropriate
src/tools/*.tsfile (or create one) - Add
server.registerTool(name, schema, handler)call - Export the registration function from the file
- Import and call it in
src/index.tsif new file npm run build- Test via AppleScript equivalent first to validate logic
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.
- yesterday First seen · 113 lines · 89 tokens per session scan A eb2d8c4f0733
macwright-dev is a skill published in the GitHub repository ruchit-p/macwright (0 stars, last pushed 20d ago), licensed MIT. It adds 89 tokens to every session and 1,290 once invoked, about $0.0004 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.
Other skills, from other repositories
macos-harness
Control a whole Mac from one persistent Python session with screenshots, PID-targeted input, an animated virtual pointer, targeted Apple Accessibility, Apple Events, Browser Harness CDP, and filesystem access. Use for native, Electron, browser, dialog, file, or cross-app tasks without moving the physical cursor or…
web-navigator
Web 浏览器自动化路由规则。通过 webnavigator 将 Web 场景路由到 Playwright MCP 或 mcp-chrome。.
peekaboo
Use Peekaboo for macOS desktop automation, screenshots, visual UI maps, native accessibility inspection, app/window/menu/dialog control, native app and browser chrome control, browser-page MCP tooling, MCP diagnostics, and Peekaboo repo validation. Use when Codex needs current macOS UI state, direct desktop control…
performance
Optimize web performance for faster loading and better user experience. Use when asked to "speed up my site", "optimize performance", "reduce load time", "fix slow loading", "improve page speed", or "performance audit".
core-web-vitals
Optimize Core Web Vitals (LCP, INP, CLS) for better page experience using field and lab evidence. Use when asked to "improve Core Web Vitals", "fix LCP", "reduce CLS", "optimize INP", "page experience optimization", or "fix layout shifts".
scarf-miniapp-author
Author a Scarf mini-app — a small sandboxed web surface (HTML/CSS/JS) that renders inside a project's cockpit and talks to the bound Hermes session + project data through the versioned window.scarf bridge. Use to build a bespoke panel (a task board, an approval queue, a chart, a data table) for a project.