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/ezesubu/vera/computer-usenpx skills add ezesubu/VERA --skill computer-usegit clone --depth 1 https://github.com/ezesubu/VERAWrote 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/ezesubu/vera/computer-use)<a href="https://agentmods.dev/skills/ezesubu/vera/computer-use"><img src="https://agentmods.dev/badge/skills/ezesubu/vera/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 | $0.00000 | $0.00257 |
| Opus 5 | $0.00000 | $0.00129 |
| Sonnet 5 | $0.00000 | $0.00051 |
| Haiku 4.5 | $0.00000 | $0.00026 |
Grade A, and why
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 4d 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
Computer Use
Screen capture + click for editor UI that has no Python API. This is a last resort — it is fragile and needs the editor window in the foreground.
When to use
- A control lives in a panel/menu/dialog you cannot reach via the
unrealmodule or a dedicated tool (e.g. some Project Settings pages, a third-party plugin's window, a modal that blocks scripting).
When NOT to use
- Anything reachable via the
unrealPython API (actors, assets, levels, most settings, CVars) — userun_ue_pythonor a dedicated tool. It is reliable and does not depend on window focus or pixel positions. - Creating Blueprints — use the Blueprint Forge plugin (Graph API, no clicking).
How
screen_captureto take a screenshot — you read it directly (you are multimodal; no OCR). Locate the target control and read its pixel position.screen_clickwith absolute screenx/yto click it. It asks for confirmation (it changes editor state).
Re-capture after each click to confirm the result before the next action.
What ships with it
2 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.
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.
- 4d ago First seen · 24 lines · 0 tokens per session scan A 0891acea647a
computer-use is a skill published in the GitHub repository ezesubu/VERA (15 stars, last pushed 24d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 257 tokens. 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
dev-in-browser
Use your browser to view https://verso.localhost which is tied to livereload dev server which is already running. You can inspect that page (including taking screenshots!) to validate that your changes fixed the issue.
web-games
Web browser game development principles. Framework selection, WebGPU, optimization, PWA.
webapp-testing
Web application testing principles. E2E, Playwright, deep audit strategies.
pretext
Build creative browser demos with DOM-free text layout.
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
plan-canvas
Open plans and HTML artifacts in a local browser canvas where the human annotates elements, chats, and approves or requests changes without leaving the page. Use when presenting a plan for review, or when feedback like "move this, change that" is easier pointed at than typed.