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/perasyudha/nyxora/computer-usenpx skills add perasyudha/Nyxora --skill computer-usegit clone --depth 1 https://github.com/perasyudha/NyxoraWrote 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/perasyudha/nyxora/computer-use)<a href="https://agentmods.dev/skills/perasyudha/nyxora/computer-use"><img src="https://agentmods.dev/badge/skills/perasyudha/nyxora/computer-use.svg" alt="Measured on agentmods" 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 | $0.00068 | $0.02755 |
| Opus 5 | $0.00034 | $0.01378 |
| Sonnet 5 | $0.00014 | $0.00551 |
| Haiku 4.5 | $0.00007 | $0.00276 |
Grade F, and why
computer-use scanned grade F with 4 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
| `blocked pattern in type text` | You tried to `type` a shell command matching the dangerous-pattern block list (`curl ... \| bash`, `sudo rm -rf`, etc.). Break the command up or reconsider | Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
| `blocked pattern in type text` | You tried to `type` a shell command matching the dangerous-pattern block list (`curl ... \| bash`, `sudo rm -rf`, etc.). Break the command up or reconsider | Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
| `blocked pattern in type text` | You tried to `type` a shell command matching the dangerous-pattern block list (`curl ... \| bash`, `sudo rm -rf`, etc.). Break the command up or reconsider | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `blocked pattern in type text` | You tried to `type` a shell command matching the dangerous-pattern block list (`curl ... \| bash`, `sudo rm -rf`, etc.). Break the command up or reconsider | This is a copy
89% identical to computer-use — 22 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Computer Use (universal, any-model, cross-platform)
You have a computer_use tool that drives the user's desktop in the
background — your actions do NOT move the user's cursor, steal
keyboard focus, or switch virtual desktops / Spaces. The user can keep
typing in their editor while you click around in a browser in another
window. This is the opposite of pyautogui-style automation.
Everything here works with any tool-capable model — Claude, GPT, Gemini, or an open model on a local OpenAI-compatible endpoint. There is no Anthropic-native schema to learn.
Nyxora drives cua-driver under the hood
for the platform plumbing. The Nyxora-side computer_use tool exposed
in this skill is a higher-level Nyxora vocabulary; the raw cua-driver
MCP tools (which a different agent harness would see) are NOT what you
call — call the computer_use actions documented below.
The canonical workflow
Step 1 — Capture first. Almost every task starts with:
computer_use(action="capture", mode="som", app="<the app you're driving>")
Returns a screenshot with numbered overlays on every interactable element AND an AX-tree index like:
#1 AXButton 'Back' @ (12, 80, 28, 28) [Chrome]
#2 AXTextField 'Address bar' @ (80, 80, 900, 32) [Chrome]
#7 Link 'Sign In' @ (900, 420, 80, 24) [Chrome]
...
The role names match the host platform's accessibility framework
(AXButton on macOS, Button on Windows UIA, push button on Linux
AT-SPI) — treat them as labels, not as strict types.
Step 2 — Click by element index. This is the single most important habit:
computer_use(action="click", element=7)
Much more reliable than pixel coordinates for every model. Claude was trained on both; other models are often only reliable with indices.
Step 3 — Verify. After any state-changing action, re-capture. You can save a round-trip by asking for the post-action capture inline:
computer_use(action="click", element=7, capture_after=True)
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 First seen · 264 lines · 68 tokens per session scan F aad11ade6bad
computer-use is a skill published in the GitHub repository perasyudha/Nyxora (5 stars, last pushed 5d ago), licensed MIT. It adds 68 tokens to every session and 2,755 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it F with 4 findings (asks for root, downloads and executes remote code, recursive force delete). It is 89% identical to computer-use, differing in 22 lines, and is treated as a copy.
Other skills, from other repositories
feature-walkthrough
Autonomously test the running binance-trading-bot app in a real browser. The agent drives the browser itself via the Playwright MCP - logs in, looks at each screen, and works through every feature end-to-end like a real operator, finding and fixing bugs. Use when asked to test the app, smoke-test or walk through the…
browser-qa
自动化视觉测试与 UI 交互验证。部署功能后使用浏览器自动化验证关键页面、核心路径和发布前回归。 当任务需要真实浏览器验证渲染、导航、交互或前端上线风险时使用。.
alibaba-supplier-outreach
Codex-native supplier sourcing and outreach workflow for Alibaba using LaunchFast research. Use when the user wants supplier shortlists, outreach messages, reply triage, or negotiation support. Requires supplierresearch. Browser automation is optional but useful when the user wants Codex to interact with Alibaba…
separateweb-capture
Capture a URL into a full-page screenshot, cropped UI item PNGs, and a JSON manifest. Use when the user says separateweb capture , asks to capture a website, or wants UI extraction assets without running the SeparateWeb web app.
generate
Generate Playwright tests. Use when user says "write tests", "generate tests", "add tests for", "test this component", "e2e test", "create test for", "test this page", or "test this feature".
init
Set up Playwright in a project. Use when user says "set up playwright", "add e2e tests", "configure playwright", "testing setup", "init playwright", or "add test infrastructure".