desktop-controller

desktop-controller is a skill for Claude Code, Codex from 24kchengYe/desktop-controller-skill. It costs 304 tokens per session (3,574 once invoked), scanned A, original, MIT.

A guide for controlling Windows desktop applications with mouse, keyboard, browser, and screenshot automation. It chooses Playwright for web or Electron apps and Windows APIs for native desktop apps.

In plain words
What is it for?
Use it to click buttons, type text, send messages, fill web forms, control native Windows programs, and take screenshots.
Why use it?
It provides a way to automate applications that may not offer an agent-specific interface. Selecting the appropriate control method helps web tasks use page elements and native tasks use desktop controls.

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/24kchengye/desktop-controller-skill/desktop-controller-skill
Any agent
npx skills add 24kchengYe/desktop-controller-skill --skill desktop-controller-skill
Clone the repo
git clone --depth 1 https://github.com/24kchengYe/desktop-controller-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 desktop-controller

README.md
[![agentmods](https://agentmods.dev/badge/skills/24kchengye/desktop-controller-skill/desktop-controller-skill.svg)](https://agentmods.dev/skills/24kchengye/desktop-controller-skill/desktop-controller-skill)
Your own site
<a href="https://agentmods.dev/skills/24kchengye/desktop-controller-skill/desktop-controller-skill"><img src="https://agentmods.dev/badge/skills/24kchengye/desktop-controller-skill/desktop-controller-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 304 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,574 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00304 $0.03574
Opus 5 $0.00152 $0.01787
Sonnet 5 $0.00061 $0.00715
Haiku 4.5 $0.00030 $0.00357

Measured 5d ago against content hash cba34b20c0bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

desktop-controller scanned grade A with 1 finding 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.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl --noproxy localhost -s http://localhost:9222/json/version
SKILL.md · 331 lines

How it starts

The opening of the file, as written. The whole thing — 331 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Universal Desktop Controller

Automate any Windows desktop application using a combination of Win32 API, Playwright (for web/Electron apps), and screenshot-based visual feedback. Inspired by OpenAI's playwright-interactive Codex skill, adapted for Claude Code.

Smart Routing: Choose the Right Engine

CRITICAL DECISION: Before any action, determine which engine to use:

User Request → Is it a web/browser/Electron app?
                 ├── YES → Playwright (CSS selectors, instant, precise)
                 │         Examples: email webmail, Slack, browser tasks, web forms
                 │         ✅ page.click('#compose')  — instant, 100% accurate
                 │
                 └── NO  → Win32 API (native desktop automation)
                           Examples: WeChat, QQ, DingTalk, Notepad, File Explorer
                           ✅ SetCursorPos + mouse_event — works for any native app

Why this matters: For the Tsinghua email (a web app), using Playwright CSS selectors is 10-50x faster than screenshot→analyze→click. OpenAI's playwright-interactive proved this: DOM selectors beat vision-based coordinate guessing every time for web content.

Engine Speed Precision Use For
Playwright <1s per action 100% (DOM selector) Web apps, Electron apps, browser tasks
Win32 API 2-3s per action 95% (coordinate-based) Native desktop apps (WeChat, QQ, etc.)
Screenshot+Vision 10-15s per action 80% (AI guessing) Last resort / unknown UI

Architecture

┌──────────────────────────────────────────────────┐
│             Desktop Controller Skill              │
├──────────────┬──────────────┬────────────────────┤
│  Win32 Layer │ Playwright   │  Visual Feedback   │
│  (Native)    │ (Web/Electron)│  (Screenshot+AI)   │
├──────────────┼──────────────┼────────────────────┤
│ FindWindow   │ Browser      │ CaptureScreen      │
│ SendKeys     │ Page.click   │ CaptureWindow      │
│ SetCursorPos │ Page.fill    │ → Claude Vision    │
│ mouse_event  │ Page.goto    │ → Verify State     │
│ Clipboard    │ Locator      │ → Decide Next Step │
└──────────────┴──────────────┴────────────────────┘

Read the full file on GitHub · 331 lines

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 · 331 lines · 304 tokens per session scan A cba34b20c0bb

Subscribe to this mod's changes

desktop-controller is a skill published in the GitHub repository 24kchengYe/desktop-controller-skill (10 stars, last pushed 5mo ago), licensed MIT. It adds 304 tokens to every session and 3,574 once invoked, about $0.0015 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

browser-use

Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.

browser-use/browser-use · 26 tokens

opencli-autofix

Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.

jackwener/OpenCLI · 61 tokens

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

opencli-browser-sitemap

Use when driving a website with opencli browser and sitemap context is available, requested, or needed to avoid blind navigation. Guides agents to consume site sitemap files lazily, choose adapter/browser fallback paths, resume from state signatures, and mark stale sitemap entries without trusting them over live…

jackwener/OpenCLI · 64 tokens

pinchtab

Use this skill when a task needs browser automation through PinchTab: open a website, inspect interactive elements, click through flows, fill out forms, scrape page text, reuse a dedicated automation profile with user approval, export screenshots or PDFs, manage multiple browser instances, or fall back to the HTTP API…

pinchtab/pinchtab · 94 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens