Agent skill

Computer Control

Automates desktop GUI workflows via computer use API with screenshot capture.

MITAuto-check: notesProductivity & Automation

Install Computer Control

skills CLI

$ npx skills add athola/claude-night-market --skill computer-control -a claude-code

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

GitHub CLI

$ gh skill install athola/claude-night-market computer-control --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/athola/claude-night-market.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/phantom/skills/computer-control .claude/skills/computer-control && 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/

Paste into Claude Code

Install the "computer-control" agent skill from https://github.com/athola/claude-night-market/tree/master/plugins/phantom/skills/computer-control into .claude/skills/computer-control/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "computer-control", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/athola/claude-night-market/tree/master/plugins/phantom/skills/computer-control

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add athola/claude-night-market --skill computer-control -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install athola/claude-night-market computer-control --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/athola/claude-night-market.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/phantom/skills/computer-control .agents/skills/computer-control && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "computer-control" agent skill from https://github.com/athola/claude-night-market/tree/master/plugins/phantom/skills/computer-control into .agents/skills/computer-control/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "computer-control", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add athola/claude-night-market --skill computer-control -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install athola/claude-night-market computer-control --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/athola/claude-night-market.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/phantom/skills/computer-control .cursor/skills/computer-control && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "computer-control" agent skill from https://github.com/athola/claude-night-market/tree/master/plugins/phantom/skills/computer-control into .cursor/skills/computer-control/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "computer-control", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/athola/claude-night-market.git --path plugins/phantom/skills/computer-control

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add athola/claude-night-market --skill computer-control -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install athola/claude-night-market computer-control --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/athola/claude-night-market.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/phantom/skills/computer-control .gemini/skills/computer-control && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "computer-control" agent skill from https://github.com/athola/claude-night-market/tree/master/plugins/phantom/skills/computer-control into .gemini/skills/computer-control/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "computer-control", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install athola/claude-night-market computer-control

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add athola/claude-night-market --skill computer-control -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/athola/claude-night-market.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/phantom/skills/computer-control .github/skills/computer-control && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "computer-control" agent skill from https://github.com/athola/claude-night-market/tree/master/plugins/phantom/skills/computer-control into .github/skills/computer-control/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "computer-control", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add athola/claude-night-market --skill computer-control -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install athola/claude-night-market computer-control --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/athola/claude-night-market.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/phantom/skills/computer-control .opencode/skills/computer-control && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "computer-control" agent skill from https://github.com/athola/claude-night-market/tree/master/plugins/phantom/skills/computer-control into .opencode/skills/computer-control/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "computer-control", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: computer-control
GitHub stars: 342
Token cost: ~1.3k tokens
SKILL.md length: 483 words
Files: 1
Skills in repo: 159
Repo updated: Oct 6, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Automates desktop GUI workflows via computer use API with screenshot capture.

Works in 3 steps: Display Toolkit (phantom.display) -… → Agent Loop (phantom.loop) - manages the… → CLI (phantom.cli) - command-line…
Scripting GUI interactions
SKILL.md covers When To Use, When NOT To Use, Architecture and Quick Start, plus 6 more sections
Calls uv and apt; needs ANTHROPIC_API_KEY

What it does

Computer Control is an agent skill from athola/claude-night-market. Automates desktop GUI workflows via computer use API with screenshot capture. Use when scripting GUI interactions or recording browser sessions for tutorials.

Its SKILL.md is about 1.3k 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 Desktop control. The repository describes itself as: 23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project lifecycle, fix-from-error, maintenance automation, context… The licence is MIT.

When your agent uses it

Scripting GUI interactions
Recording browser sessions for tutorials

Example prompts

“Use the computer-control skill to automate desktop GUI workflows via computer use API with screenshot capture”
“/computer-control”

Requirements

Python 3
Docker
A credential in ANTHROPIC_API_KEY

Workflow steps

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

Display Toolkit (phantom.display) - executes OS-level
Agent Loop (phantom.loop) - manages the conversation
CLI (phantom.cli) - command-line interface for running

What it can do on your machine

Read from SKILL.md and the folder at commit 9f3eb00. 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
Shell commands in SKILL.md call:
- uv
- apt
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
- ANTHROPIC_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Computer Control loads about 1.3k tokens when it runs. Until then it costs about 44 tokens; SKILL.md has 483 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~44
When it runs · the whole SKILL.md, loaded when a task matches: ~1.3k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

NoteRuns commands with sudoSKILL.md:144
```
sudo apt install xdotool scrot xclip
```

NoteRuns commands with sudoSKILL.md:151

sudo apt install xvfb xdotool scrot xclip

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 athola/claude-night-market at commit 9f3eb00, republished under its MIT licence (© athola). 483 words, ~1,301 tokens.

Download SKILL.mdSave it as .claude/skills/computer-control/SKILL.md (or your agent's skills folder).

name: computer-control
description: Automates desktop GUI workflows via computer use API with screenshot capture. Use when scripting GUI interactions or recording browser sessions for tutorials.
alwaysApply: false
model_hint: standard

Computer Control Skill

Use Claude's Computer Use API to see and control desktop environments through screenshots and mouse/keyboard actions.

When To Use

Automating GUI-based workflows that lack CLI alternatives
Testing web applications through visual interaction
Filling forms, navigating menus, or interacting with desktop apps
Building automation pipelines that need visual verification

When NOT To Use

Tasks achievable through CLI or API (no GUI needed)
Browser automation better served by Playwright or CDP

Why this stays opt-in. Per docs/inclusive-defaults.md (TRUE-exception category 4), Computer Use takes screenshots and synthesizes keyboard/mouse input: cross-process side effects that must always be explicitly invoked, never default-on.

Architecture

The computer use system has three layers:

Display Toolkit (phantom.display) - executes OS-level actions via xdotool/scrot on the real or virtual display
Agent Loop (phantom.loop) - manages the conversation cycle between Claude API and the display toolkit
CLI (phantom.cli) - command-line interface for running tasks or checking environment readiness

User Task
    |
    v
Agent Loop  <---->  Claude API (beta)
    |                   |
    v                   v
Display Toolkit    tool_use responses
    |              (click, type, screenshot)
    v
OS Commands (xdotool, scrot)
    |
    v
Display (X11 / Xvfb / WSLg)

Quick Start

Check environment

bash

cd plugins/phantom
uv run python -m phantom.cli --check

Run a task

bash

export ANTHROPIC_API_KEY="sk-ant-..."
uv run python -m phantom.cli "Open Firefox and search for Claude AI"

Use in Python

python

from phantom.display import DisplayConfig, DisplayToolkit
from phantom.loop import LoopConfig, run_loop

result = run_loop(
    task="Take a screenshot of the desktop",
    api_key="sk-ant-...",
    loop_config=LoopConfig(
        model="claude-sonnet-5",
        max_iterations=10,
    ),
    display_config=DisplayConfig(width=1920, height=1080),
)

print(f"Done in {result.iterations} iterations")
print(result.final_text)

API Versions

Model	Tool Version	Beta Flag
Opus 4.6, Sonnet 4.6, Opus 4.5	`computer_20251124`	`computer-use-2025-11-24`
Sonnet 4.5, Haiku 4.5, older	`computer_20250124`	`computer-use-2025-01-24`

The resolve_tool_version() function handles this mapping automatically based on the model name.

Available Actions

All versions:

screenshot - capture display
left_click - click at [x, y]
type - type text string
key - press key combo (e.g., ctrl+s)
mouse_move - move cursor

Enhanced (20250124+):

scroll - scroll with direction and amount
left_click_drag - drag between coordinates
right_click, middle_click, double_click, triple_click
hold_key - hold key for duration
wait - pause between actions

Latest (20251124):

zoom - inspect screen region at full resolution

Show full SKILL.md (228 more words)Show less

Safety

Computer use carries risks. Follow these guidelines:

Use a sandbox: Run in Docker or a VM, not your main OS
Limit access: Do not provide login credentials unless necessary, and never for banking or sensitive services
Set iteration caps: Always use max_iterations to prevent runaway API costs
Human approval: For actions with real-world consequences, add confirmation callbacks via on_action
Close sensitive apps: Claude sees the full screen via screenshots; close anything private before starting

Environment Requirements

Linux (native or WSL2 with WSLg):

bash

sudo apt install xdotool scrot xclip

Headless (Docker/CI):

bash

# Install Xvfb for virtual display
sudo apt install xvfb xdotool scrot xclip
Xvfb :1 -screen 0 1920x1080x24 &
export DISPLAY=:1

Prompting Tips

Be specific about each step of the task
Add "After each step, take a screenshot and verify" to catch mistakes early
Use keyboard shortcuts when UI elements are hard to click
Provide example screenshots for repeatable workflows
Set a system prompt with domain-specific instructions

Exit Criteria

uv run python -m phantom.cli --check exits 0 before any task is launched; if it fails, required OS tools (xdotool, scrot, xclip) are installed or Xvfb is started before proceeding
max_iterations set on every run_loop() call; no task launched without an explicit iteration cap to prevent runaway API costs
Final result includes result.iterations count and result.final_text confirming the task outcome; empty final_text treated as failure, not success
Sensitive applications (password managers, banking, private files) closed before task starts; task prompt does not contain raw credentials

Files

Just SKILL.md in plugins/phantom/skills/computer-control of athola/claude-night-market.

Open the folder on GitHubat commit 9f3eb00

Compare with similar skills

Computer Control 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.

Computer Control compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Computer Control this skillathola/claude-night-market	342	—	~1.3k	Automated safety check: Notes	MIT	2 days ago
Vision SkillsAnionex/agent-vision-toolkit	1.2k	1 repos	~4k	Automated safety check: Pass	MIT	today
Mac Computer UseTo3akaRin/mac-computer-use	1.1k	1 repos	~495	Automated safety check: Pass	MIT	14 days ago
Crabbox Appsopenclaw/openclaw	392k	—	~1.5k	Automated safety check: Pass	MIT	today
Agent Managementautonomous-ai/Physical-AI-Operating-System	381	—	~1.7k	Automated safety check: Pass	Apache-2.0	today
Computer Usebam-bam-2/solo-skills	367	1 repos	~915	Automated safety check: Pass	MIT	24 days ago

Similar skills

Vision Skills
Anionex/agent-vision-toolkit
Local vision CLIs: glance (describe/ask/OCR an image), ground (locate a target, pixel box), detect (element inventory), trace (image to SVG geometry), crop (cut a pixel box to a file), and…
1.2k GitHub starsUsed in 1 repo~4k tokens
Productivity & AutomationAuto-check passed
Mac Computer Use
To3akaRin/mac-computer-use
操作 macOS 桌面应用，探测窗口和自动化接口、截图、读取或修改辅助功能元素、执行鼠标键盘动作，以及通过 CDP 操作内嵌 Chromium 页面。适用于桌面应用自动化与界面验收；普通网页任务优先使用已有浏览器工具。
1.1k GitHub starsUsed in 1 repo~495 tokens
Productivity & AutomationAuto-check passed
Crabbox Apps
openclaw/openclaw
A skill your agent uses when asked to open, run, test, or show an app in Crabbox, including native desktops, web previews, and computer use on a temporary machine.
392k GitHub stars~1.5k tokensUpdated today
Productivity & AutomationAuto-check passed
Agent Management
autonomous-ai/Physical-AI-Operating-System
Legacy Autonomous Buddy control for explicitly requested Buddy coding sessions.
381 GitHub stars~1.7k tokensUpdated today
Productivity & AutomationAuto-check passed
Computer Use
bam-bam-2/solo-skills
Use Orca's computer-use CLI to inspect and operate local desktop app windows through accessibility trees, screenshots, and safe UI actions.
367 GitHub starsUsed in 1 repo~915 tokens
Productivity & AutomationAuto-check passed
Cloud Computer Use
davidondrej/cloudroom-core
See and control desktop apps on this Cloud sandbox’s virtual Linux screen with cloudroom computer-use: launch GUI apps you build or install, read their UI, click, type, and take screenshots.
272 GitHub stars~881 tokensUpdated yesterday
Productivity & AutomationAuto-check: notes

Questions about Computer Control

What does Computer Control do?

Automates desktop GUI workflows via computer use API with screenshot capture. Computer Control is an agent skill from athola/claude-night-market. Automates desktop GUI workflows via computer use API with screenshot capture.

When should I use Computer Control?

Computer Control fits situations like: scripting GUI interactions; recording browser sessions for tutorials.

How do I install Computer Control in Claude Code?

Run `npx skills add athola/claude-night-market --skill computer-control -a claude-code`. Or copy the skill folder (plugins/phantom/skills/computer-control in athola/claude-night-market) into .claude/skills/computer-control in your project. Claude Code loads it when a task matches its description.

How do I install Computer Control in Codex?

Run `npx skills add athola/claude-night-market --skill computer-control -a codex`. Or copy the skill folder (plugins/phantom/skills/computer-control in athola/claude-night-market) into .agents/skills/computer-control in your project. Codex loads it when a task matches its description.

Can I use Computer Control 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 athola/claude-night-market --skill computer-control -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/computer-control, .gemini/skills/computer-control, .github/skills/computer-control and .opencode/skills/computer-control in your project.

What does Computer Control need to run?

Going by SKILL.md and its folder, Computer Control needs the command-line tools its instructions call (uv and apt) and credentials named ANTHROPIC_API_KEY. Our summary lists: Python 3; Docker; A credential in ANTHROPIC_API_KEY.

Does Computer Control access the network?

SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Computer Control safe to install?

Our automated static check of SKILL.md found notes only (runs commands with sudo), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Computer Control use?

Computer Control 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 Computer Control use?

About 1.3k tokens (SKILL.md is roughly 5.2k 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 Computer Control?

Skills that share tags, products or a category with Computer Control: Vision Skills (Anionex/agent-vision-toolkit, 1.2k stars), Mac Computer Use (To3akaRin/mac-computer-use, 1.1k stars), Crabbox Apps (openclaw/openclaw, 392k stars) and Agent Management (autonomous-ai/Physical-AI-Operating-System, 381 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Computer Control?

athola (a GitHub user) maintains it in athola/claude-night-market, which has 342 GitHub stars. The repository holds 159 skills in this directory. The repository was last updated on October 6, 2026.

Source: athola/claude-night-market on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Computer Control

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Computer Control Skill

When To Use

When NOT To Use

Architecture

Quick Start

Check environment

Run a task

Use in Python

API Versions

Available Actions

Safety

Environment Requirements

Prompting Tips

Exit Criteria

Files

Compare with similar skills

Similar skills

More from athola/claude-night-market

Related

Questions about Computer Control