computer-use-os-agent-expert

computer-use-os-agent-expert is a skill for Cursor from roedyrustam/vibes-plug. It costs 72 tokens per session (3,473 once invoked), scanned A, original, MIT.

A guide to computer-using agents that operate desktop and web applications through screen information, accessibility data, and simulated mouse and keyboard actions. It covers isolated virtual machines or containers and approval gates for risky actions.

In plain words
What is it for?
Use it for desktop GUI automation, browser or Electron applications, remote desktop software, legacy systems, and agent actions that need human approval.
Why use it?
It helps automate applications that lack a direct programming interface while limiting the damage an automated agent could cause. It also provides ways to locate interface controls across different screen sizes.

Skill for Cursor

Written for Cursor: shipped in a Cursor plugin.

Part of the vibes-plug plugin — 176 skills, 9 agents, 2 MCP servers shipped together

Good fit Use it for desktop GUI automation, browser or Electron applications, remote desktop software, legacy systems, and agent actions that need human approval.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/roedyrustam/vibes-plug/computer-use-os-agent-expert
Install

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.

Any agent
npx skills add roedyrustam/vibes-plug --skill computer-use-os-agent-expert
Clone the repo
git clone --depth 1 https://github.com/roedyrustam/vibes-plug

Made for: Cursor.

Or install vibes-plug, the plugin that ships this one along with the rest of its 176 skills, 9 agents, 2 MCP servers.

Wrote 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.

agentmods badge for computer-use-os-agent-expert

README.md
[![agentmods](https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/computer-use-os-agent-expert/github.svg)](https://agentmods.dev/skills/roedyrustam/vibes-plug/computer-use-os-agent-expert)
Your own site
<a href="https://agentmods.dev/skills/roedyrustam/vibes-plug/computer-use-os-agent-expert"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/computer-use-os-agent-expert/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.

agentmods 80×15 button for computer-use-os-agent-expert

Your own site · 80×15
<a href="https://agentmods.dev/skills/roedyrustam/vibes-plug/computer-use-os-agent-expert"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/computer-use-os-agent-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,473 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00072 $0.03473
Opus 5.5 $0.00029 $0.01389
Sonnet 5.5 $0.00014 $0.00695
Haiku 4.5 $0.00007 $0.00347

Measured yesterday against content hash 765d6440cb65, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

computer-use-os-agent-expert 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 yesterday.

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.

skills/computer-use-os-agent-expert/SKILL.md · 293 lines

How it starts

The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Computer-Use & OS Agent Expert / Ahli Agen Pengguna Komputer & OS


English

Overview

You are a Principal Autonomous Systems & Computer-Using Agent (CUA) Architect. You design agents capable of operating arbitrary desktop and web applications via visual screen perception (1000x1000 normalized coordinate grounding), hybrid DOM/Accessibility-tree fusion, ephemeral VM sandboxes, and strict action-level safety gates.

1. CUA Perception & Action Architecture (2026)

Modality Primary Signal Fallback Signal Precision & Latency Target Environment
Web / Electron Apps Accessibility Tree (AXTree) + Set-of-Marks (SoM) IDs Normalized Vision Bounding Boxes ([y_min, x_min, y_max, x_max]) 99.4% accuracy, < 150ms Chromium / Playwright / Electron
Legacy Desktop / Remote VNC / Citrix High-DPI Vision Grounding (1000x1000 normalized grid) OCR Text Box Detection 94.8% accuracy, < 450ms Linux Xvfb / macOS Virtualization / Windows Sandbox

2. Normalized Coordinate Mapping & Action Policy Gate

Vision models output coordinates in a resolution-independent [0, 1000] scale. Your runtime must:

  1. Convert normalized [x_norm, y_norm] coordinates accurately to physical viewport pixels while accounting for devicePixelRatio (Retina/HiDPI scaling).
  2. Intercept high-risk actions (terminal execution, file deletion, credential submission, financial confirmation) with a deterministic policy verifier before dispatching OS input events.
// src/cua/os-agent-executor.ts
import { z } from 'zod';

export const CuaActionSchema = z.discriminatedUnion('type', [
  z.object({
    type: z.literal('click'),
    xNorm: z.number().min(0).max(1000),
    yNorm: z.number().min(0).max(1000),
    button: z.enum(['left', 'right', 'double']).default('left'),
    targetDescription: z.string().min(1),
  }),
  z.object({
    type: z.literal('type_text'),
    text: z.string(),
    pressEnter: z.boolean().default(false),
    isSensitiveInput: z.boolean().default(false),
  }),
  z.object({
    type: z.literal('key_combo'),
    keys: z.array(z.string()).min(1).max(4),
  }),
  z.object({
    type: z.literal('screenshot'),
  }),
]);

export type CuaAction = z.infer<typeof CuaActionSchema>;

export interface ViewportMetrics {
  widthPx: number;
  heightPx: number;
  devicePixelRatio: number;
}

const BLOCKED_KEY_COMBOS = new Set([
  'Meta+Q',
  'Alt+F4',
  'Control+Alt+Delete',
  'Meta+Shift+Backspace',
]);

export function mapNormalizedToViewportPx(
  xNorm: number,
  yNorm: number,
  viewport: ViewportMetrics
): { xPx: number; yPx: number } {
  const xPx = Math.round((xNorm / 1000) * viewport.widthPx);
  const yPx = Math.round((yNorm / 1000) * viewport.heightPx);
  return {
    xPx: Math.max(0, Math.min(viewport.widthPx - 1, xPx)),
    yPx: Math.max(0, Math.min(viewport.heightPx - 1, yPx)),
  };
}

export function evaluateActionSafety(action: CuaAction): {
  decision: 'ALLOW' | 'REQUIRE_HITL' | 'DENY';
  reason: string;
} {
  if (action.type === 'key_combo') {
    const combo = action.keys.join('+');
    if (BLOCKED_KEY_COMBOS.has(combo)) {
      return { decision: 'DENY', reason: `Blocked destructive OS shortcut: ${combo}` };
    }
  }

  if (action.type === 'click') {
    const riskyKeywords = /\b(delete|transfer|pay|submit order|drop|format|uninstall)\b/i;
    if (riskyKeywords.test(action.targetDescription)) {
      return {
        decision: 'REQUIRE_HITL',
        reason: `Irreversible UI target detected: "${action.targetDescription}"`,
      };
    }
  }

  if (action.type === 'type_text' && action.isSensitiveInput) {
    return {
      decision: 'REQUIRE_HITL',
      reason: 'Sensitive credential or financial input requires human approval.',
    };
  }

  return { decision: 'ALLOW', reason: 'Standard UI navigation action.' };
}

Read the full file on GitHub · 293 lines

Changes

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.

  1. yesterday Changed · +141 lines 765d6440cb65
  2. 2d ago First seen · 152 lines · 72 tokens per session scan A 84b2763f6c2c

Subscribe to this mod's changes

computer-use-os-agent-expert is a skill published in the GitHub repository roedyrustam/vibes-plug (113 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 3,473 once invoked, about $0.0003 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 2026-10-24.

Related

Other skills, from other repositories

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

chidekina/aria-superpowers · 35 tokens

ai-engineering-toolkit

Overview of six AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.

sickn33/agentic-awesome-skills · 47 tokens

ai-prompt-regression-testing

Use when comparing prompt changes against a fixed evaluation set: record actual model settings, required checks, missing results, judge limitations and case-level regression evidence.

sickn33/agentic-awesome-skills · 37 tokens

browser-testing-with-devtools

Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be…

addyosmani/agent-skills · 68 tokens

cue

Writing and producing product videos: scripts, storyboards, narration, and reproducible Playwright demo recordings. Use for explainers, onboarding, feature walkthroughs, multi-aspect exports, captions, and video quality checks.

simota/agent-skills · 46 tokens

control-ui

Drive and inspect a local web, IDE, or Electron UI with browser or CDP automation and evidence. Use for UI regressions, screenshots, accessibility snapshots, visual diffs, focus, keyboard, scrolling, resize, console, network, performance, or heap checks. Do not use for backend-only changes or for a screenshot without…

AnastasiyaW/codex-claude-code-config · 73 tokens