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 zavora-ai/computer-use-mcp --skill computer-use-windows-admingit clone --depth 1 https://github.com/zavora-ai/computer-use-mcpWrote 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/zavora-ai/computer-use-mcp/computer-use-windows-admin)<a href="https://agentmods.dev/skills/zavora-ai/computer-use-mcp/computer-use-windows-admin"><img src="https://agentmods.dev/badge/skills/zavora-ai/computer-use-mcp/computer-use-windows-admin/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/zavora-ai/computer-use-mcp/computer-use-windows-admin"><img src="https://agentmods.dev/badge/skills/zavora-ai/computer-use-mcp/computer-use-windows-admin.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 | $0.00026 | $0.00300 |
| Opus 5.5 | $0.00010 | $0.00120 |
| Sonnet 5.5 | $0.00005 | $0.00060 |
| Haiku 4.5 | $0.00003 | $0.00030 |
Grade A, and why
computer-use-windows-admin 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 15d 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.
What it actually says
Windows admin tools
Prefer:
| Task | Tool |
|---|---|
| Files | filesystem (read/write/list/search/copy/move/delete) |
| Registry | registry (PowerShell-style HKCU:\… paths; Windows only) |
| Processes | process_kill (list or kill by name/PID) |
| Complex automation | run_script language powershell |
| Notify user | notification (Windows only) |
Relative filesystem paths resolve from Desktop. Absolute paths are unrestricted by default — treat delete/write carefully (COMPUTER_USE_FS_ROOTS confines filesystem).
process_kill refuses a pid below 2 and matches name exactly; an ambiguous name returns ambiguous_name unless you pass all: true.
Set COMPUTER_USE_PROFILE=windows-admin for a focused tool surface if desired. These tools are not in the default desktop profile (registry and notification are listed only on Windows). If COMPUTER_USE_REQUIRE_APPROVAL_FOR or COMPUTER_USE_DESTRUCTIVE_REQUIRES_APPROVAL is set, the operator's token goes in the call's _meta["computer-use/approval_token"], not in the arguments you see.
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.
- 15d ago Changed · +2 lines f90957fcc9cb
- 1mo ago First seen · 21 lines · 26 tokens per session scan A c1cd8121fa07
computer-use-windows-admin is a skill published in the GitHub repository zavora-ai/computer-use-mcp (86 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 300 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
turix-mac
Computer Use Agent (CUA) for macOS automation using TuriX. Use when you need to perform visual tasks on the desktop, such as opening apps, clicking buttons, or navigating UIs that don't have a CLI or API.
desktop-gui-inspect
Full-desktop automation for targets that have no browser and no API at all — a legacy Java-based NMS client, a vendor's Windows-only configuration utility, a terminal emulator with no scriptable interface. Drives OpenClaw's ClawHub computer-use skill (Xvfb+XFCE virtual desktop, xdotool input automation) to read…
agent-orchestration
A guide for coordinating independent AI coding agents such as Claude Code, OpenCode, or Hermes. It explains how to register each agent, check which ones are running, choose one for a task, and record stable information about how to use it.
workflow-design
A method for designing and testing multi-step computer workflows, including their inputs, actions, conditions, and error handling.
release-poster
A fixed process for creating social-media release graphics in horizontal and vertical formats from a supplied template.
mcp-tools
A reference guide for connecting outside services to an AI workflow through MCP, a standard way for AI systems to call external tools. It describes how to identify a server and tool, provide inputs, and save the result for later workflow steps.