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 autohandai/code-cli --skill computer-controlgit clone --depth 1 https://github.com/autohandai/code-cliWrote 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/autohandai/code-cli/computer-control)<a href="https://agentmods.dev/skills/autohandai/code-cli/computer-control"><img src="https://agentmods.dev/badge/skills/autohandai/code-cli/computer-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/autohandai/code-cli/computer-control"><img src="https://agentmods.dev/badge/skills/autohandai/code-cli/computer-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 | $0.00051 | $0.00966 |
| Opus 5.5 | $0.00020 | $0.00386 |
| Sonnet 5.5 | $0.00010 | $0.00193 |
| Haiku 4.5 | $0.00005 | $0.00097 |
Grade A, and why
computer-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 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.
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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Native computer control
Operate one exact local app or window, observe before input, perform the requested action, and verify the visible result from fresh state.
Tool boundary
Use the tools advertised by the autohand-computer-use MCP server. Their names start with mcp__autohand-computer-use__, including app and window discovery, launch, state capture, click, text, key, scroll, and verification tools. Follow each tool's current schema instead of guessing fields.
Older manually configured integrations may advertise the legacy mcp__cua-driver__* or mcp__cua__* prefixes. Use those only when the canonical Autohand tools are absent. In user-facing responses, call the capability Autohand Computer Use and do not present the underlying engine or an MCP tool prefix as a separate product the user must install.
When this instruction is present in the request context, the skill is already active. Do not call skill activate, skill info, or read this file again. If canonical or legacy computer-control tools are advertised, call the relevant app-discovery tool immediately. Do not call tool_search or tools_registry to rediscover them.
If those tools are absent, tell the user that native computer control is unavailable and give the exact repair command:
autohand computer install
autohand computer doctor
Do not silently install, upgrade, change OS permissions, or switch to a different automation route during an app-control request. Do not inspect shell paths, home-directory configuration, running processes, or the web as a substitute for the missing native tools.
Workflow
- Discover the requested application with
list_apps; launch it only when it is not already running. Reuse a known live process/window instead of repeating discovery. - Resolve the exact live target with
list_windowsand observe it withget_window_state. Prefer a targeted element query and structuredelements; do not request both a full AX tree and its structured duplicate. Keep default observation limits; increase them only when truncation hides the needed target. Use desktop state only for a desktop task. - Act once using a fresh element token and the exact process and window target. Prefer semantic elements over coordinates. If coordinates are necessary, derive them from a fresh screenshot of that same target.
- Re-observe or call
verify_stateafter each meaningful action. A successful tool return alone does not prove the user-visible outcome. - Stop when the requested postcondition is visible. End only this run's session when the server offers session lifecycle tools; do not stop a shared driver daemon.
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.
- 5d ago Changed · +3 lines 88469d7a60ba
- 16d ago Changed · +5 lines ab0c9f58d302
- 18d ago First seen · 45 lines · 51 tokens per session scan A e2620b658613
computer-control is a skill published in the GitHub repository autohandai/code-cli (205 stars, last pushed today), licensed Apache-2.0. It adds 51 tokens to every session and 966 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-28.
Other skills, from other repositories
checking-a-page
Check that a web page you wrote or changed actually works, by opening it in a browser and driving every control on it. Use after creating or editing an HTML page, or the JavaScript or CSS that a page loads.
e2e-testing-standards
End-to-end testing with Playwright - browser automation, visual regression, test data management.
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.
browser
Drive a live browser with async Python against QwenPaw's builtin Browser SDK. The full reference is below; re-load this browser skill after context compaction.
computer-use
Read and drive native desktop apps through the accessibility layer — list apps, snapshot a window as a numbered element tree, then click/type/scroll/drag by element index or screen coordinates. Use for a desktop app, not a web page. macOS + Windows; off unless enabled in Settings.
feature-demo-recording
Record a demo video of a web feature from a real browser. Two modes -- a NARRATED film where measured voiceover drives the timeline (designed slides, subtitles, punch-in camera, rendered from an HTML timeline), and a SILENT evidence clip for a PR or a QA pass. Use when the user asks to record a video, demo, or screen…