computer-use

A skill for reading and controlling native desktop applications through their accessibility information, such as spreadsheets, PDF viewers, and other installed programs. It can inspect a window and operate its visible controls by element or screen position.

In plain words
What is it for?
Use it to list open applications, inspect a window, click controls, type text, set values, scroll, drag items, and run named actions in supported desktop apps.
Why use it?
It gives a coding agent a way to work in desktop software when a web browser is not involved. It also provides a structured way to identify controls before clicking or entering data.

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/kirodotdev/kirocrew/computer-use
Any agent
npx skills add kirodotdev/KiroCrew --skill computer-use
Clone the repo
git clone --depth 1 https://github.com/kirodotdev/KiroCrew

Made for: Claude Code, Codex.

Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,927 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 $0.00105 $0.06927
Opus 5 $0.00053 $0.03463
Sonnet 5 $0.00021 $0.01385
Haiku 4.5 $0.00011 $0.00693

Measured 2d ago against content hash 9db7e0415afe, 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 2d 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.

src/kiro_crew/builtin_skills/computer-use/SKILL.md · 464 lines

How it starts

The opening of the file, as written. The whole thing — 464 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Computer Use — driving native desktop apps

You have MCP tools that read and operate the user's real applications through the operating system's accessibility layer. This is not a browser: use it when the work lives in a desktop app (a spreadsheet, a PDF viewer, a native internal tool, a dialog box), and use playwright-cli (the web-browse skill) for web pages.

Two things to internalise before your first call:

  • Address elements by index, from a snapshot you were just shown. That is the path to prefer for everything: it activates the control directly, it is checked against drift, and the mouse pointer does not move. Coordinates exist as a fallback for canvases, maps and custom-drawn UI that expose no element — see Coordinates and dragging.
  • It is off unless the user turned it on (Settings → Computer Use). The full tool set runs on macOS and Windows alike. They differ in ONE way worth relaying: Windows has no per-process input, so a keystroke takes the user's keyboard focus and a coordinate click moves their real cursor. A "disabled" or "not supported" refusal is a real configuration answer, not a transient error — relay it and stop; do not retry.

The loop

1. Find the app.

computer_list_apps()

Returns the on-screen applications with their bundle ids, pids and window titles. Skip this if the user named an app you can pass straight through — app accepts a display name ("Finder", "Preview") or a bundle id ("com.apple.finder"), matched case-insensitively.

If the app you need is not running, open it:

computer_launch_app(app="Paint")

Give the app's NAME as the OS knows it — the name in the Start menu or the Applications folder. A filesystem path, a command line and a document are all refused, because this opens an application and nothing else; if you find yourself wanting to pass a path, the answer is to launch the app and then use the tools below to open the file from inside it.

Read the full file on GitHub · 464 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. 2d ago First seen · 464 lines · 105 tokens per session scan A 9db7e0415afe

Subscribe to this mod's changes

computer-use is a skill published in the GitHub repository kirodotdev/KiroCrew (3,532 stars, last pushed today), licensed Apache-2.0. It adds 105 tokens to every session and 6,927 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

reskin

Author a NEW skin for the reskinnable-demo app. A skin is a self-contained domain plugin under src/skins/ / that implements the frozen Skin contract (src/shell/skin-contract.ts) to swap the app's entire experience — brand, theme, layout, pages, tools, data, and agent — as a live sales demo. Use when the user says "add…

CopilotKit/CopilotKit · 154 tokens

copilotkit-setup

Use when adding CopilotKit to an existing project or bootstrapping a new CopilotKit project from scratch. Covers framework detection, package installation, runtime wiring (managed Intelligence or self-hosted SSE), provider setup, and first working chat integration.

CopilotKit/CopilotKit · 56 tokens

setup-slack-channel

Use for the PROVIDER half of getting a locally running CopilotKit Channels agent to answer in Slack, when no Slack app exists yet — setting up a Channels bot in Slack for the first time, creating the Slack app and its tokens, attaching it to a managed Intelligence Channel, or when a Channel reports setuprequired, sits…

CopilotKit/CopilotKit · 206 tokens

copilotkit-channels

Use for the CODE half of a managed Intelligence Channel with Slack or Microsoft Teams: customising the Channel a CLI-scaffolded project already ships, or — for a project the CLI did not generate — writing the Channel declaration, the long-running host, and the awaited activation call. Teams provider setup is in scope…

CopilotKit/CopilotKit · 112 tokens

copilotkit-integrations

Use when wiring an external agent framework (LangGraph, CrewAI, PydanticAI, Mastra, ADK, LlamaIndex, Agno, Strands, Microsoft Agent Framework, or others) into a CopilotKit application via the AG-UI protocol.

CopilotKit/CopilotKit · 61 tokens

copilotkit-develop

Use when building AI-powered features with CopilotKit v2 -- adding chat interfaces, registering frontend tools, sharing application context with agents, handling agent interrupts, and working with the CopilotKit runtime.

CopilotKit/CopilotKit · 46 tokens