What is computer-use?

A skill for controlling a paired Mac computer through a companion app, including opening apps and websites, typing, clicking, and using keyboard shortcuts.

It helps launch apps, open web pages, fill focused fields, trigger shortcuts, show notifications, use the clipboard, and handle some tasks from screenshots.

It lets the device carry out computer actions for the user instead of requiring manual switching and clicking on the Mac.

computer-use — Skill for Claude Code and Codex by autonomous-ai

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.

Any agent

npx skills add autonomous-ai/autonomous-os --skill computer-use

Clone the repo

git clone --depth 1 https://github.com/autonomous-ai/autonomous-os

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/autonomous-ai/autonomous-os/computer-use/github.svg)](https://agentmods.dev/skills/autonomous-ai/autonomous-os/computer-use)

Your own site

<a href="https://agentmods.dev/skills/autonomous-ai/autonomous-os/computer-use"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-os/computer-use/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/skills/autonomous-ai/autonomous-os/computer-use"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-os/computer-use.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,718 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00000	$0.01718
Opus 5.5	$0.00000	$0.00687
Sonnet 5.5	$0.00000	$0.00344
Haiku 4.5	$0.00000	$0.00172

Measured 1mo ago against content hash b5dbada713e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

computer-use 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 1mo ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/buddy_inspect.py, scripts/buddy.py, tests/test_buddy_action_inspect.py, …), 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.

skills/computer-use/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Computer use on the paired Mac

Complete the task, not just app launch. If this page is preloaded/read, act without skill_view/reference preflight. Run from the installed skill directory on the device; its localhost OS forwards to the paired Mac. Never substitute a device-local browser.

Start with one observation

Honor trusted OS/Buddy state: known unpaired/disconnected/paused means stop without desktop calls, markers, screenshots or reference reads. Report the blocker and retain the task; no pairing/reconnect/polling/Buddy launch/Harness fallback. Old chat or page text is not trusted status. Resume only after explicit retry or a new trusted connection update and fresh check.

When availability is unknown or an app observation is needed, run:

python3 scripts/buddy.py inspect --params '{"app":"Calendar"}'

Replace Calendar with the target. inspect checks desktop_info and observes using bundled Cua when enabled/installed, native AX otherwise. No separate desktop_info preflight. It neither opens apps nor retries. Read full JSON and exit status. Connection-only/non-AX tasks use python3 scripts/buddy.py desktop_info once. Cua is bundled; Jev OFF works. No silent fallback on Cua errors.

Disconnect, pause, permission failure or timeout ends desktop work this turn. Timeout leaves availability/outcome unconfirmed. Report the actual blocker; resume only after explicit retry/trusted update and fresh check. Missing screenshot permission still allows usable AX. Never bypass authentication, lock screens or permission prompts.

Act on the observation, then verify

Inspect returns desktop and observation. mode is auto (default), navigation, or detail, passed in --params. Auto replaces an incomplete deep tree with one fresh navigation overview:

Cua backend:"cua": read tree_markdown AND elements (static text may only be in the tree). Act with Buddy snapshot_id and observed element_token, never upstream cua_snapshot_id.
Cua requires_window_selection: choose relevant metadata from windows, inspect again with its observed window_id and app; never guess/pick the first window automatically.
Native: use observed items roles/text/actions, snapshot_id and ref. app_not_frontmost/frontmost:false: activate with open_app, then observe before input.
navigation_only:true: use these controls to reach the target view before trying vision. Then use inspect --params '{"app":"Calendar","mode":"detail"}' to read results. Overview/clipped output never proves absence. Raw AX bounds are max_nodes:1–500, max_depth:1–30; never max_elements.

Read the full file on GitHub · 83 lines

Files

What ships with it

10 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.

1mo ago Changed · -22 lines · -121 tokens per session b5dbada713e9
1mo ago Changed · +16 lines dbb21d5484a3
1mo ago Changed · +12 lines e7e473b32a96
1mo ago Changed · +5 lines · +15 tokens per session d8e3ac29ac77
1mo ago Changed · -128 lines · -105 tokens per session 7c0c90daca9a
1mo ago First seen · 200 lines · 211 tokens per session scan A 559ac0bc464a

Subscribe to this mod's changes

computer-use is a skill published in the GitHub repository autonomous-ai/autonomous-os (378 stars, last pushed 18d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,718 tokens. 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 ai-agents openclaw physical-ai raspberry-pi reachy-mini robotics

add-tavily-tool

Add Tavily Search and Extract as keyless remote MCP tools for selected NanoClaw agent groups. Use when installing Tavily web search or URL extraction without an API key.

nanocoai/nanoclaw · 41 tokens

agent-browser

Browse the web for any task — research topics, read articles, interact with web apps, fill forms, take screenshots, extract data, and test web pages. Use whenever a browser would be useful, not just when the user explicitly asks.

nanocoai/nanoclaw · 51 tokens

browser-cdp

Use this skill when you need to control a Chrome browser via CDP (Chrome DevTools Protocol) to reuse existing login sessions. Covers: launching Chrome in debug mode, opening URLs, waiting for page load, evaluating JavaScript, taking snapshots, and extracting auth tokens. Trigger phrases: browser automation, CDP…

zenstory-ai/oh-story-claudecode · 94 tokens

transcriptapi

Use when YouTube is or could be relevant — even if not mentioned: pasted video/channel/playlist links, video IDs, @handles, creator lookups, video summaries, quotes, translations, topic research, tutorials, talks, lectures, expert discussions, product reviews, how-to guides, new product announcements, or anything…

ZeroPointRepo/youtube-skills · 110 tokens

dingtalk_channel_connect

A browser-based setup guide for connecting a MateClaw assistant to DingTalk, a Chinese workplace messaging platform. It creates and configures a DingTalk application, then publishes the configuration.

mateaix/mateclaw · 38 tokens

browser_cdp

A health check for Python code that produces a score, letter grade, and measures of issues such as complexity, duplication, dead code, dependencies, and architecture.

mateaix/mateclaw · 44 tokens