computer-use

A way to inspect and control desktop application windows through a computer-use driver. It is intended for tasks that require interacting with a graphical application rather than only reading files or running commands.

In plain words
What is it for?
It helps inspect application windows, read their accessibility information, capture the screen, and carry out desktop actions through a named session.
Why use it?
It lets an agent handle visible desktop interfaces when ordinary file and command tools cannot perform the task.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/vironnimo/vbot/computer-use
Any agent
npx skills add Vironnimo/vbot --skill computer-use
Clone the repo
git clone --depth 1 https://github.com/Vironnimo/vbot

Made for: Claude Code, Codex.

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,282 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00059 $0.01282
Opus 5 $0.00030 $0.00641
Sonnet 5 $0.00012 $0.00256
Haiku 4.5 $0.00006 $0.00128

Measured yesterday against content hash c0dd26da9efa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 yesterday.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/computer_use.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

resources/skills/computer-use/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Computer Use

Use the bundled Python script to inspect and operate application windows on the machine running the vBot server. This is a script-backed prototype, not a built-in Tool. On a remote Pi-server plus Windows Desktop Client setup it controls the Pi desktop, not the user's Windows Desktop Client.

The wrapper uses cua-driver's one-shot CLI transport. It requests background delivery by default, but actual behavior and supported applications depend on the host platform and installed driver version.

Script contract

  • Run python {baseDir}/scripts/computer_use.py --session <session> doctor before the first desktop action in a task.
  • Choose a unique lowercase session name containing only letters, digits, hyphens, or underscores. Reuse it for the complete task and call start once before inspection.
  • Treat stdout JSON as data. Exit code zero with "ok": true means the operation completed. A nonzero exit or "ok": false means it did not.
  • The script never installs or upgrades cua-driver. Report a missing or incompatible driver and ask before installing anything.
  • Captures and oversized accessibility data are written below tmp/computer-use/<session>/ in the effective cwd. Load screenshot paths with vBot's read Tool.
  • Element actions (click/scroll with --element) accept an element index or an element_token (e.g. s00000001:12) from a capture. An index resolves against the session's latest capture of the same pid/window_id; capture the target window first, and re-capture when the UI changed since your last capture.
  • Mutating commands require the explicit --apply flag. Without it, the script returns a dry-run description and performs no input action.
  • Applied actions report the driver's delivery, effect, and route metadata. effect: "unverifiable" is normal — it means the driver sent the input but could not confirm the outcome, so verify by re-capturing.
  • The wrapper invokes cua-driver without a shell and removes credential-like environment variables from its child environment.

Read the full file on GitHub · 66 lines

Files

What ships with it

1 file 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.

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 First seen · 66 lines · 59 tokens per session scan A c0dd26da9efa

Subscribe to this mod's changes

computer-use is a skill published in the GitHub repository Vironnimo/vbot (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 59 tokens to every session and 1,282 once invoked, about $0.0003 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.