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 skills add zrtch/awesome-skills --skill desktop-controlgit clone --depth 1 https://github.com/zrtch/awesome-skillsWrote 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.
[](https://agentmods.dev/skills/zrtch/awesome-skills/desktop-control)<a href="https://agentmods.dev/skills/zrtch/awesome-skills/desktop-control"><img src="https://agentmods.dev/badge/skills/zrtch/awesome-skills/desktop-control/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.
<a href="https://agentmods.dev/skills/zrtch/awesome-skills/desktop-control"><img src="https://agentmods.dev/badge/skills/zrtch/awesome-skills/desktop-control.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00011 | $0.03756 |
| Opus 5 | $0.00005 | $0.01878 |
| Sonnet 5 | $0.00002 | $0.00751 |
| Haiku 4.5 | $0.00001 | $0.00376 |
Grade A, and why
desktop-control 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 9d ago.
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 — 624 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Desktop Control Skill
The most advanced desktop automation skill for OpenClaw. Provides pixel-perfect mouse control, lightning-fast keyboard input, screen capture, window management, and clipboard operations.
🎯 Features
Mouse Control
- ✅ Absolute positioning - Move to exact coordinates
- ✅ Relative movement - Move from current position
- ✅ Smooth movement - Natural, human-like mouse paths
- ✅ Click types - Left, right, middle, double, triple clicks
- ✅ Drag & drop - Drag from point A to point B
- ✅ Scroll - Vertical and horizontal scrolling
- ✅ Position tracking - Get current mouse coordinates
Keyboard Control
- ✅ Text typing - Fast, accurate text input
- ✅ Hotkeys - Execute keyboard shortcuts (Ctrl+C, Win+R, etc.)
- ✅ Special keys - Enter, Tab, Escape, Arrow keys, F-keys
- ✅ Key combinations - Multi-key press combinations
- ✅ Hold & release - Manual key state control
- ✅ Typing speed - Configurable WPM (instant to human-like)
Screen Operations
- ✅ Screenshot - Capture entire screen or regions
- ✅ Image recognition - Find elements on screen (via OpenCV)
- ✅ Color detection - Get pixel colors at coordinates
- ✅ Multi-monitor - Support for multiple displays
Window Management
- ✅ Window list - Get all open windows
- ✅ Activate window - Bring window to front
- ✅ Window info - Get position, size, title
- ✅ Minimize/Maximize - Control window states
Safety Features
- ✅ Failsafe - Move mouse to corner to abort
- ✅ Pause control - Emergency stop mechanism
- ✅ Approval mode - Require confirmation for actions
- ✅ Bounds checking - Prevent out-of-screen operations
- ✅ Logging - Track all automation actions
🚀 Quick Start
Installation
First, install required dependencies:
pip install pyautogui pillow opencv-python pygetwindow
Basic Usage
from skills.desktop_control import DesktopController
# Initialize controller
dc = DesktopController(failsafe=True)
# Mouse operations
dc.move_mouse(500, 300) # Move to coordinates
dc.click() # Left click at current position
dc.click(100, 200, button="right") # Right click at position
# Keyboard operations
dc.type_text("Hello from OpenClaw!")
dc.hotkey("ctrl", "c") # Copy
dc.press("enter")
# Screen operations
screenshot = dc.screenshot()
position = dc.get_mouse_position()
What ships with it
6 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.
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.
- 9d ago First seen · 624 lines · 11 tokens per session scan A d900c0650cfb
desktop-control is a skill published in the GitHub repository zrtch/awesome-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 11 tokens to every session and 3,756 once invoked, about $0.0001 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…