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 agentmods add skills/qwenlm/qwen-code/computer-usenpx skills add QwenLM/qwen-code --skill computer-usegit clone --depth 1 https://github.com/QwenLM/qwen-codeWhat 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 | $0.00033 | $0.01326 |
| Opus 5 | $0.00016 | $0.00663 |
| Sonnet 5 | $0.00007 | $0.00265 |
| Haiku 4.5 | $0.00003 | $0.00133 |
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 today.
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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Computer Use with the CUA SDK
- Prefer a dedicated connector or API. Use Computer Use only for UI state or interactions the dedicated interface does not expose.
- Perform Computer Use through
node_repland the typedComputerUseAPI. Do not use genericcallTool, direct driver imports, AppleScript, JXA, or synthesized-input utilities. - Observe the exact current window before acting. Prefer current element tokens over screenshot coordinates; use coordinates only when accessibility is incomplete and the screenshot provides the target.
- Treat an action result as delivery evidence, not task completion. Decide from fresh state and require stable postcondition evidence.
Setup
If node_repl is unavailable, run these commands yourself:
qwen mcp add --scope user node-repl npx -y @qwen-code/[email protected]
npm install --no-save --package-lock=false @qwen-code/[email protected]
Tell the user to restart Qwen Code, then stop. If only the SDK import is missing, run the second command and retry.
Create one persistent client per REPL kernel:
globalThis.computer = await (
await import('@qwen-code/cua-sdk/computer-use')
).ComputerUse.create();
globalThis.cuaRevisions ??= new Map();
Target and observe
Use listApps({signal:nodeRepl.signal}) and filter in JavaScript; print only
likely matches. After selecting a real PID, call
listWindows({pid,signal:nodeRepl.signal}) and choose from returned
metadata. Never guess a PID, window ID, element token, or coordinate. If the
app is not running, start it with ordinary Node.js process APIs and refresh the
lists.
Maintain one revision cursor per window surface. The first observation has no base; later observations use only the last revision actually consumed for that same surface:
globalThis.observeCuaWindow = async (target, options = {}) => {
const key = `${target.pid}:${target.windowId}`;
const state = await computer.observeWindow({
...target,
...options,
baseRevisionId: cuaRevisions.get(key),
signal: nodeRepl.signal,
});
if (state.revisionId) cuaRevisions.set(key, state.revisionId);
return state;
};
What ships with it
2 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.
- today Changed · -64 lines 77f5e17bebd1
- 3d ago First seen · 230 lines · 33 tokens per session scan A fcfac31c91cf
computer-use is a skill published in the GitHub repository QwenLM/qwen-code (27,559 stars, last pushed yesterday), licensed Apache-2.0. It adds 33 tokens to every session and 1,326 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
research-agent
Use for current web/X research, library/API verification, competitive analysis, source-backed technical decisions, or updating docs with recent facts.
youtube-watcher
Fetch and read transcripts from YouTube videos. Use when you need to summarize a video, answer questions about its content, or extract information from it.
Agent Browser
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…
argent-tv-interact
Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…