computer-use-macos

computer-use-macos is a skill for Claude Code, Codex from wimi321/macos-computer-use-skill. It costs 37 tokens per session (463 once invoked), scanned A, original, MIT.

A macOS-only computer-control skill with its own bundled runtime and MCP server. It lets an agent interact with a Mac without depending on a separate local Claude installation or private app files.

In plain words
What is it for?
Use it when an agent needs to control or inspect a macOS desktop. It builds the bundled server and installs its public runtime dependencies when first used.
Why use it?
It provides a self-contained way to automate computer tasks on macOS and reduces setup dependencies.

Skill for Claude CodeCodex

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 skills/wimi321/macos-computer-use-skill/computer-use-macos
Any agent
npx skills add wimi321/macos-computer-use-skill --skill computer-use-macos
Clone the repo
git clone --depth 1 https://github.com/wimi321/macos-computer-use-skill

Made for: Claude Code, Codex.

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 computer-use-macos

README.md
[![agentmods](https://agentmods.dev/badge/skills/wimi321/macos-computer-use-skill/computer-use-macos.svg)](https://agentmods.dev/skills/wimi321/macos-computer-use-skill/computer-use-macos)
Your own site
<a href="https://agentmods.dev/skills/wimi321/macos-computer-use-skill/computer-use-macos"><img src="https://agentmods.dev/badge/skills/wimi321/macos-computer-use-skill/computer-use-macos.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 463 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00037 $0.00463
Opus 5 $0.00018 $0.00231
Sonnet 5 $0.00007 $0.00093
Haiku 4.5 $0.00004 $0.00046

Measured 5d ago against content hash 8c3d4d96db2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

computer-use-macos 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 5d ago.

The scan reads SKILL.md. This mod also ships 33 executable files (project/runtime/mac_helper.py, project/src/cli.ts, project/src/computer-use/appNames.ts, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skill/computer-use-macos/SKILL.md · 65 lines

What it actually says

macOS Computer-Use Skill

Use this skill when the task needs a portable macOS computer-use skill bundled with its own standalone runtime and MCP server.

What this skill does

  • uses the bundled macos-computer-use-skill project under the installed skill directory
  • builds the standalone MCP server
  • lets the server auto-bootstrap its Python runtime on first launch
  • avoids any dependency on local Claude binaries, .node modules, or extracted app assets
  • stays explicitly macOS-only because the underlying desktop-control backend is macOS-specific

Default bundled project path

After installation, assume the standalone project lives at:

~/.codex/skills/computer-use-macos/project

If the user installed the skill under a custom CODEX_HOME, use that equivalent path instead.

Build

Always build from the bundled project:

cd ~/.codex/skills/computer-use-macos/project
npm install
npm run build

Run

cd ~/.codex/skills/computer-use-macos/project
node dist/cli.js

The first real run will automatically create .runtime/venv and install the public Python dependencies.

Validation notes

  • On real macOS hosts, prefer validating typing through the MCP type tool path, not only low-level helper calls.
  • Version 0.2.2 routes ordinary macOS text input through clipboard paste when available, avoiding IME/input-source corruption seen with per-key typing under Chinese input methods.

Guardrails

  • Treat this host as trusted-local only.
  • Do not tell the user to search their local Claude install for binaries or hidden assets.
  • Be explicit that this runtime is standalone and uses public dependencies only.
  • Mention that the current runtime reports screenshotFiltering: none, so action gating is handled at the MCP layer.
Files

What ships with it

48 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 65 lines · 37 tokens per session scan A 8c3d4d96db2d

Subscribe to this mod's changes

computer-use-macos is a skill published in the GitHub repository wimi321/macos-computer-use-skill (18 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 463 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

computer-use-windows

Top-level Windows computer-use skill with a bundled standalone runtime that bootstraps itself without any local Claude installation, private native modules, or extracted app assets.

wimi321/windows-computer-use-skill · 36 tokens

computer-use

Windows 桌面自动化执行规则。使用 screeninteractor 观察与操作原生桌面应用。.

Plocr/Reasonix-computer-use · 23 tokens

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。.

Plocr/Reasonix-computer-use · 30 tokens

computer-use-linux

Top-level Linux computer-use skill with a bundled standalone runtime that bootstraps itself without any local Claude installation, private native modules, or extracted app assets.

wimi321/linux-computer-use-skill · 35 tokens

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…

browser-use/macos-harness · 71 tokens

browser-control

Control web pages in an existing Chromium remote-debugging session with deterministic sagui commands or the browser-only AI Agent. Use when Claude Code needs to inspect tabs, observe semantic elements, navigate, click, type, send keys, scroll, or complete a browser goal through CDP without controlling native macOS UI…

NakaokaRei/SwiftAutoGUI · 72 tokens