Agent skill

Agent Desktop

by superagent-ai in superagent-ai/grok-cli

Use the built-in Computer sub-agent with agent-desktop for macOS desktop automation.

MITAuto-check passedProductivity & Automation

Install Agent Desktop

skills CLI
$ npx skills add superagent-ai/grok-cli --skill agent-desktop -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install superagent-ai/grok-cli agent-desktop --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/superagent-ai/grok-cli.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/agent-desktop .claude/skills/agent-desktop && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
agent-desktop
GitHub stars
3.5k
Token cost
~720 tokens
SKILL.md length
356 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

Use the built-in Computer sub-agent with agent-desktop for macOS desktop automation.

  • Works in 5 steps: Delegate to task with agent: "computer"… → Use computer_launch,… → Start with computer_snapshot. → …
  • Tasks that involve Subagents
  • SKILL.md covers When to use it, Requirements, Preferred flow and Tool guidance, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Agent Desktop is an agent skill from superagent-ai/grok-cli. Use the built-in Computer sub-agent with agent-desktop for macOS desktop automation. Apply when a task needs application launching, accessibility snapshots, stable element refs, window focusing, semantic clicks/typing, or visual confirmation outside the browser sandbox.

Its SKILL.md is about 720 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Productivity & Automation, covering Subagents, Desktop control and Accessibility. It works with macOS. The repository describes itself as: An open-source coding agent for the Grok API. The licence is MIT.

When your agent uses it

  • Tasks that involve Subagents
  • Tasks that involve Desktop control
  • Tasks that involve Accessibility

Example prompts

  • “/agent-desktop”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Delegate to task with agent: "computer" unless the current agent already has the computer_* tools and the task is tiny.
  2. Use computer_launch, computer_list_windows, or computer_focus_window to get the target app/window ready.
  3. Start with computer_snapshot.
  4. Pick one ref-based action.
  5. After any UI transition, snapshot again before reusing refs.

What it can do on your machine

Read from SKILL.md and the folder at commit fb97af8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agent Desktop loads about 720 tokens when it runs. Until then it costs about 72 tokens; SKILL.md has 356 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~72
When it runs · the whole SKILL.md, loaded when a task matches
~720

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from superagent-ai/grok-cli at commit fb97af8, republished under its MIT licence (© superagent-ai). 356 words, ~720 tokens.

Download SKILL.mdSave it as .claude/skills/agent-desktop/SKILL.md (or your agent's skills folder).
name
agent-desktop
description
Use the built-in `Computer` sub-agent with `agent-desktop` for macOS desktop automation. Apply when a task needs application launching, accessibility snapshots, stable element refs, window focusing, semantic clicks/typing, or visual confirmation outside the browser sandbox.

agent-desktop

Use this skill when the task involves the host macOS desktop rather than repository files, shell output, or browser-only verification.

This project uses agent-desktop on the host. Prefer the built-in Computer sub-agent for these tasks instead of trying to drive the desktop with plain shell commands.

When to use it

  • The user wants to inspect or interact with a native macOS application.
  • The task needs app launch, window focus, accessibility snapshots, semantic element refs, clicks, typing, keypresses, or scrolling.
  • A browser-only workflow is not enough, or the target is not a web page.

Requirements

  • agent-desktop must be installed and its native binary available.
  • On macOS, the terminal app running grok needs Accessibility permission.
  • Refs from computer_snapshot are only valid until the next snapshot.

Preferred flow

  1. Delegate to task with agent: "computer" unless the current agent already has the computer_* tools and the task is tiny.
  2. Use computer_launch, computer_list_windows, or computer_focus_window to get the target app/window ready.
  3. Start with computer_snapshot.
  4. Pick one ref-based action.
  5. After any UI transition, snapshot again before reusing refs.
Show full SKILL.md (178 more words)Show less

Tool guidance

  • computer_snapshot: primary observation tool; prefer interactive_only.
  • computer_click: use ref values from the latest snapshot whenever possible.
  • computer_type: requires a target ref and is preferred over coordinate typing.
  • computer_press: use for shortcuts and special keys such as Enter, Tab, cmd+space, or cmd+k.
  • computer_scroll: pass an element ref, not raw coordinates.
  • computer_get: read text, value, bounds, role, or states from a ref.
  • computer_screenshot: use for visual confirmation or when the accessibility tree is not enough.

Reliability rules

  • Use a snapshot -> act -> snapshot loop.
  • Prefer refs over coordinates.
  • Refs go stale after the next snapshot; do not reuse them blindly.
  • Keep actions reversible and low risk unless the user explicitly asked for something destructive.
  • If the accessibility tree is poor or ambiguous, use computer_screenshot for confirmation and explain the limitation.

Blockers

Stop and report clearly if:

  • Accessibility permission is missing.
  • agent-desktop is unavailable or its native binary is missing.
  • The target app/window cannot be found.
  • Refs are stale or ambiguous after a UI transition.
  • The requested action could be destructive and the user did not explicitly ask for it.

© superagent-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/agent-desktop of superagent-ai/grok-cli.

Open the folder on GitHubat commit fb97af8

Compare with similar skills

Agent Desktop next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Agent Desktop compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agent Desktop this skillsuperagent-ai/grok-cli3.5k—~720Automated safety check: PassMIT
Cmux Cuamanaflow-ai/cmux28k—~4.5kAutomated safety check: PassCustom licence
Apple Notes Install Authjeremylongshore/tons-of-skills-marketplace2.8k—~1.3kAutomated safety check: PassMIT
Computer Usekunpengtalk/PeakCode166—~2.5kAutomated safety check: PassMIT
Agent Desktopmvanhorn/printing-press-library2.1k—~2.3kAutomated safety check: NotesApache-2.0
Cua Driver Rsmajiayu000/claude-skill-registry6661 repos~7.1kAutomated safety check: PassMIT

Similar skills

  • Cmux Cua

    manaflow-ai/cmux

    Use only after the user explicitly asks for cmux Computer Use through the cmux-cua skill: drive real macOS apps from a cmux agent session via the bundled engine (accessibility tree + screenshots…

    28k GitHub stars~4.5k tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Apple Notes Install Auth

    jeremylongshore/tons-of-skills-marketplace

    Set up macOS automation access for Apple Notes via AppleScript, JXA, and Shortcuts.

    2.8k GitHub stars~1.3k tokensUpdated today
    Frontend & DesignAuto-check passed
  • Computer Use

    kunpengtalk/PeakCode

    Drive a macOS app through the computer tool — read its accessibility tree, act on elements, and use real input only when the tree cannot reach the target.

    166 GitHub stars~2.5k tokensUpdated 16 days ago
    Productivity & AutomationAuto-check passed
  • Agent Desktop

    mvanhorn/printing-press-library

    Desktop automation through the real Rust agent-desktop CLI, published in Printing Press through a small bridge.

    2.1k GitHub stars~2.3k tokensUpdated yesterday
    Productivity & AutomationAuto-check: notes
  • Cua Driver Rs

    majiayu000/claude-skill-registry

    Drive a native GUI app (macOS, Windows, Linux) via the cua-driver CLI (default) or MCP server — snapshot its accessibility tree, click/type/scroll by elementindex or pixel coords, verify via…

    666 GitHub starsUsed in 1 repo~7.1k tokens
    Frontend & DesignAuto-check passed
  • Jarvis Setup

    ethanplusai/jarvis

    A skill your agent uses when helping someone install, configure, or debug a fresh clone of JARVIS (this repo) — especially "the mic doesn't work", "JARVIS says his language systems are down", any…

    838 GitHub stars~2.5k tokensUpdated 28 days ago
    Frontend & DesignAuto-check: notes

More from superagent-ai/grok-cli

  • Agent Browser

    superagent-ai/grok-cli

    Use the host-side agent-browser CLI for local browser smoke tests, screenshots, snapshots, and simple UI validation against forwarded localhost URLs.

    3.5k GitHub starsUsed in 1 repo~633 tokens
    Auto-check passed

Works with

Questions about Agent Desktop

What does Agent Desktop do?

Use the built-in Computer sub-agent with agent-desktop for macOS desktop automation. Agent Desktop is an agent skill from superagent-ai/grok-cli. Use the built-in Computer sub-agent with agent-desktop for macOS desktop automation.

When should I use Agent Desktop?

Agent Desktop fits situations like: tasks that involve Subagents; tasks that involve Desktop control; tasks that involve Accessibility.

How do I install Agent Desktop in Claude Code?

Run `npx skills add superagent-ai/grok-cli --skill agent-desktop -a claude-code`. Or copy the skill folder (.agents/skills/agent-desktop in superagent-ai/grok-cli) into .claude/skills/agent-desktop in your project. Claude Code loads it when a task matches its description.

How do I install Agent Desktop in Codex?

Run `npx skills add superagent-ai/grok-cli --skill agent-desktop -a codex`. Or copy the skill folder (.agents/skills/agent-desktop in superagent-ai/grok-cli) into .agents/skills/agent-desktop in your project. Codex loads it when a task matches its description.

Can I use Agent Desktop in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add superagent-ai/grok-cli --skill agent-desktop -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-desktop, .gemini/skills/agent-desktop, .github/skills/agent-desktop and .opencode/skills/agent-desktop in your project.

What does Agent Desktop need to run?

SKILL.md names no scripts, command-line tools or credentials: Agent Desktop is instructions for the agent only.

Does Agent Desktop access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Agent Desktop safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Agent Desktop use?

Agent Desktop is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Agent Desktop use?

About 720 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Agent Desktop?

Skills that share tags, products or a category with Agent Desktop: Cmux Cua (manaflow-ai/cmux, 28k stars), Apple Notes Install Auth (jeremylongshore/tons-of-skills-marketplace, 2.8k stars), Computer Use (kunpengtalk/PeakCode, 166 stars) and Agent Desktop (mvanhorn/printing-press-library, 2.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent Desktop?

superagent-ai (a GitHub organization) maintains it in superagent-ai/grok-cli, which has 3,487 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on July 6, 2026.

Source: superagent-ai/grok-cli on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.