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 xxww0098/skills-hub --skill cua-computer-usegit clone --depth 1 https://github.com/xxww0098/skills-hubWrote 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/xxww0098/skills-hub/cua-computer-use)<a href="https://agentmods.dev/skills/xxww0098/skills-hub/cua-computer-use"><img src="https://agentmods.dev/badge/skills/xxww0098/skills-hub/cua-computer-use/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/xxww0098/skills-hub/cua-computer-use"><img src="https://agentmods.dev/badge/skills/xxww0098/skills-hub/cua-computer-use.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 | $0.00153 | $0.01717 |
| Opus 5 | $0.00077 | $0.00859 |
| Sonnet 5 | $0.00031 | $0.00343 |
| Haiku 4.5 | $0.00015 | $0.00172 |
Grade A, and why
cua-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 6d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
39 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.
- fixtures/cua-lab/electron/.gitignore 14 B
- fixtures/cua-lab/electron/main.js 858 B runs code
- fixtures/cua-lab/electron/package-lock.json 29 KB
- fixtures/cua-lab/electron/package.json 239 B
- fixtures/cua-lab/gtk/cua-lab-gtk.py 6.8 KB runs code
- fixtures/cua-lab/qt/cua-lab-qt.py 6.0 KB runs code
- fixtures/cua-lab/README.md 1.1 KB
- fixtures/cua-lab/tauri/src-tauri/build.rs 39 B
- fixtures/cua-lab/tauri/src-tauri/capabilities/default.json 147 B
- fixtures/cua-lab/tauri/src-tauri/Cargo.toml 365 B
- fixtures/cua-lab/tauri/src-tauri/gen/schemas/acl-manifests.json 64 KB
- fixtures/cua-lab/tauri/src-tauri/gen/schemas/capabilities.json 154 B
- fixtures/cua-lab/tauri/src-tauri/gen/schemas/desktop-schema.json 113 KB
- fixtures/cua-lab/tauri/src-tauri/gen/schemas/linux-schema.json 113 KB
- fixtures/cua-lab/tauri/src-tauri/icons/icon.png 105 B
- fixtures/cua-lab/tauri/src-tauri/rust-toolchain.toml 31 B
- fixtures/cua-lab/tauri/src-tauri/src/lib.rs 183 B
- fixtures/cua-lab/tauri/src-tauri/src/main.rs 105 B
- fixtures/cua-lab/tauri/src-tauri/tauri.conf.json 458 B
- fixtures/cua-lab/web/index.html 8.8 KB
- fixtures/cua-lab/webkit/cua-lab-webkit.py 1008 B runs code
- README.md 1.8 KB
- references/adversary.md 4.1 KB
- references/frameworks.md 10 KB
- scripts/cua-use 13 KB
- scripts/cua-use.ps1 7.4 KB runs code
- scripts/linux-lab 1.1 KB
- tests/evidence/electron-before.png 49 KB
- tests/evidence/electron-calc-42.png 49 KB
- tests/evidence/gtk-calc-42.png 32 KB
- tests/evidence/gtk-type-ada.png 34 KB
- tests/evidence/qt-calc-42.png 27 KB
- tests/evidence/README.md 1.4 KB
- tests/evidence/tauri-ax-calc-42.png 47 KB
- tests/evidence/tauri-paint-calc-42.png 47 KB
- tests/evidence/tauri-paint-surface.png 47 KB
- tests/evidence/webkitgtk-calc-42.png 47 KB
- tests/linux-lab-drive.py 11 KB runs code
- tests/linux-smoke.sh 3.0 KB runs code
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.
- 6d ago Changed · +2 lines 6b20471edcd5
- 11d ago First seen · 132 lines · 153 tokens per session scan A e345228e48cc
cua-computer-use is a skill published in the GitHub repository xxww0098/skills-hub (5 stars, last pushed 9d ago), with no licence file. It adds 153 tokens to every session and 1,717 once invoked, about $0.0008 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
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.
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
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.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…