computer-use

computer-use is a skill for Claude Code, Codex from avibe-bot/avibe. It costs 19 tokens per session (1,907 once invoked), scanned A, original, MIT.

A command-line controller for observing and operating a local computer desktop. It can inspect applications and windows and perform bounded actions such as clicking, typing, scrolling, launching, and copying.

In plain words
What is it for?
Use it to inspect windows, zoom into screenshots, enter text, press keys, move through interfaces, manage the clipboard, and launch or quit local applications.
Why use it?
It lets an agent interact with desktop software when the work cannot be completed through a text-only interface.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to inspect windows, zoom into screenshots, enter text, press keys, move through interfaces, manage the clipboard, and launch or quit local applications.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/avibe-bot/avibe/computer-use
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 avibe-bot/avibe --skill computer-use
Clone the repo
git clone --depth 1 https://github.com/avibe-bot/avibe

Made for: Claude Code, Codex.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/avibe-bot/avibe/computer-use/github.svg)](https://agentmods.dev/skills/avibe-bot/avibe/computer-use)
Your own site
<a href="https://agentmods.dev/skills/avibe-bot/avibe/computer-use"><img src="https://agentmods.dev/badge/skills/avibe-bot/avibe/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.

agentmods 80×15 button for computer-use

Your own site · 80×15
<a href="https://agentmods.dev/skills/avibe-bot/avibe/computer-use"><img src="https://agentmods.dev/badge/skills/avibe-bot/avibe/computer-use.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,907 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 $0.00019 $0.01907
Opus 5.5 $0.00008 $0.00763
Sonnet 5.5 $0.00004 $0.00381
Haiku 4.5 $0.00002 $0.00191

Measured yesterday against content hash 601aca298be5, 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 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/SKILL.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Computer Use

Use the Controller-owned CLI for desktop work:

vibe computer run ./inspect-mail.mjs --arg mailbox=Inbox --arg query=@/tmp/query.txt
vibe computer observe apps
vibe computer observe windows
vibe computer observe window --arg pid=123 --arg window_id=456 --output /tmp/window.png
vibe computer zoom --arg pid=123 --arg window_id=456 --arg x1=0 --arg y1=0 --arg x2=800 --arg y2=600 --output /tmp/zoom.png
vibe computer click --arg pid=123 --arg window_id=456 --arg x=120 --arg y=80
vibe computer type --arg pid=123 --arg window_id=456 --arg text="hello"
vibe computer key --arg key=return --arg pid=123 --arg window_id=456
vibe computer hotkey --arg keys='["cmd","c"]' --arg pid=123 --arg window_id=456
vibe computer scroll --arg direction=down --arg pid=123 --arg window_id=456
vibe computer drag --arg from_x=10 --arg from_y=10 --arg to_x=100 --arg to_y=100 --arg pid=123 --arg window_id=456
vibe computer set-value --arg pid=123 --arg value=enabled --arg element_token=el_1
vibe computer clipboard read --arg include_text=true
vibe computer clipboard write --arg text="copied text"
vibe computer launch --arg bundle_id=com.example.App
vibe computer force-quit --arg pid=123

For multi-step work, write a normal ESM file and import the shipped SDK:

import { computer } from "@avibe/computer";

export default async ({ mailbox, query }) => {
  const mail = await computer.app({ bundleId: "com.apple.mail" });
  const window = await mail.waitFor({ role: "AXWindow", labelContains: mailbox });
  const search = window.element({ role: "textbox", labelContains: "Search" });
  await search.fill(query);
  await window
    .expect({ role: "textbox", labelContains: "Search" })
    .toHaveValue(query);
  return { mailbox, query };
};

Run it with vibe computer run ./inspect-mail.mjs --arg mailbox=Inbox --arg query=@/tmp/query.txt. Ordinary argument values remain strings; @file loads the file as UTF-8 text. The default-exported function receives one argument object. Its return value becomes the JSON result; an omitted return is reported as null, and any other return must be JSON-serializable.

The runner uses Avibe's shipped Node runtime and injects @avibe/computer; never install or resolve another package with that name. The SDK keeps element tokens private, re-observes once when the Controller explicitly reports a stale observation, and stops on ambiguous action outcomes. App and window handles are immutable process descriptors; after an app relaunches, acquire fresh handles with computer.app(...) before continuing.

Scripts that send, submit, pay, delete, or perform another irreversible action must follow verify -> confirm -> re-verify -> act. If the owner-confirmation primitive is unavailable, stop before the irreversible action and use an interactive flow. Save a proven script as a reusable Skill only after the owner explicitly approves saving it.

Every single-operation leaf accepts --args-json OBJECT, --args-json @FILE, repeatable --arg NAME=VALUE, and --json. The two screenshot operations also accept --output PATH; the CLI writes or confirms the caller-selected PNG and prints the resulting path. observe window and zoom are the observation operations that establish the exact window state required before input.

--json keeps the structured driver object at result.structuredContent. The legacy content text block remains available for existing callers.

During one Agent Turn, consecutive vibe computer calls in the same Avibe Session share the driver session. Element tokens from one observation stay valid for following calls until a newer observation replaces that snapshot, so a short script can observe once, click several times, and observe once at the end:

vibe computer observe window --arg pid=123 --arg window_id=456
vibe computer click --arg pid=123 --arg window_id=456 --arg element_token=el_1
vibe computer click --arg pid=123 --arg window_id=456 --arg element_token=el_2
vibe computer observe window --arg pid=123 --arg window_id=456

Read the full file on GitHub · 162 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 · +69 lines 601aca298be5
  2. 4d ago First seen · 93 lines · 19 tokens per session scan A 113e5acbd2cd

Subscribe to this mod's changes

computer-use is a skill published in the GitHub repository avibe-bot/avibe (625 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 1,907 once invoked, about $0.0001 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 2026-10-12.

Related

Other skills, from other repositories

tmux

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output. Use when: (1) monitoring Claude/Codex sessions running in tmux, (2) sending input to interactive terminal applications, (3) scraping output from long-running processes inside tmux, (4) navigating tmux panes/windows…

opensquilla/opensquilla · 113 tokens

agent-initialization

Initialize or extend an Agent from a user requirement - write AGENTS.md, set identity metadata, and create, install or import Skills and hook packages (scripts the harness runs on every prompt, before tool calls, or after a task). For an Agent with an in-app workbench, pair with penguin-plugin; for a standalone…

Prism-Shadow/penguin-harness · 79 tokens

automation

Create and manage scheduled and price-triggered automations.

ginlix-ai/LangAlpha · 13 tokens

co-mail-and-drive

Read and send mail from the user's own Gmail or Outlook account, safely stage Gmail draft attachments, send from the agent's own address, manage Outlook contacts and the Outlook calendar, and work with Google Drive files — with co gmail, co outlook, co email, and co gdrive. Use when the user asks about their inbox, an…

openonion/connectonion · 103 tokens

computer-history

Answer questions about what the user recently did on their computer — who contacted them, what they were working on, where they left off — by reading the local Computer History summaries and raw event streams.

MemTensor/memmy-agent · 42 tokens

cron

Use when the user asks to schedule recurring tasks, one-off reminders, timers, or cron-style jobs through the OpenSquilla cron tool.

opensquilla/opensquilla · 30 tokens