computer-use

computer-use is a skill for Claude Code, Codex from AtlasOmnia/hermes-custom-pack. It costs 71 tokens per session (2,987 once invoked), scanned F, a copy of computer-use, MIT.

Instructions for controlling a computer desktop in the background through screenshots and accessibility information, without taking over the user’s cursor or keyboard focus.

In plain words
What is it for?
Opening and using desktop apps, inspecting visible controls, and carrying out interface tasks through computer actions.
Why use it?
They let an agent operate graphical applications while the user continues working elsewhere on the computer.

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/atlasomnia/hermes-custom-pack/computer-use
Any agent
npx skills add AtlasOmnia/hermes-custom-pack --skill computer-use
Clone the repo
git clone --depth 1 https://github.com/AtlasOmnia/hermes-custom-pack

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/atlasomnia/hermes-custom-pack/computer-use.svg)](https://agentmods.dev/skills/atlasomnia/hermes-custom-pack/computer-use)
Your own site
<a href="https://agentmods.dev/skills/atlasomnia/hermes-custom-pack/computer-use"><img src="https://agentmods.dev/badge/skills/atlasomnia/hermes-custom-pack/computer-use.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,987 The whole file, excluding the scripts and references it only reads on demand.
Security scan F 4 findings. Scan, not verified.
Origin 94% copy Near-identical to another mod 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 $0.00071 $0.02987
Opus 5 $0.00036 $0.01494
Sonnet 5 $0.00014 $0.00597
Haiku 4.5 $0.00007 $0.00299

Measured 5d ago against content hash bb792db8128b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade F, and why

computer-use scanned grade F with 4 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 5d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

| `blocked pattern in type text` | You tried to `type` a shell command matching the dangerous-pattern block list (`curl ... \| bash`, `sudo rm -rf`, etc.). Break the command up or reconsider |

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

| `blocked pattern in type text` | You tried to `type` a shell command matching the dangerous-pattern block list (`curl ... \| bash`, `sudo rm -rf`, etc.). Break the command up or reconsider |

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

| `blocked pattern in type text` | You tried to `type` a shell command matching the dangerous-pattern block list (`curl ... \| bash`, `sudo rm -rf`, etc.). Break the command up or reconsider |

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| `blocked pattern in type text` | You tried to `type` a shell command matching the dangerous-pattern block list (`curl ... \| bash`, `sudo rm -rf`, etc.). Break the command up or reconsider |
Origin

This is a copy

94% identical to computer-use — 134 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/computer-use/SKILL.md · 288 lines

How it starts

The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Computer Use (universal, any-model, cross-platform)

You have a computer_use tool that drives the user's desktop in the background — your actions do NOT move the user's cursor, steal keyboard focus, or switch virtual desktops / Spaces. The user can keep typing in their editor while you click around in a browser in another window. This is the opposite of pyautogui-style automation.

Everything here works with any tool-capable model — Claude, GPT, Gemini, or an open model on a local OpenAI-compatible endpoint. There is no Anthropic-native schema to learn.

Hermes drives cua-driver under the hood for the platform plumbing. The Hermes-side computer_use tool exposed in this skill is a higher-level Hermes vocabulary; the raw cua-driver MCP tools (which a different agent harness would see) are NOT what you call — call the computer_use actions documented below.

The canonical workflow

Step 1 — Capture first. Almost every task starts with:

computer_use(action="capture", mode="som", app="<the app you're driving>")

Returns a screenshot with numbered overlays on every interactable element AND an AX-tree index like:

#1 AXButton 'Back' @ (12, 80, 28, 28) [Chrome]
#2 AXTextField 'Address bar' @ (80, 80, 900, 32) [Chrome]
#7 Link 'Sign In' @ (900, 420, 80, 24) [Chrome]
...

The role names match the host platform's accessibility framework (AXButton on macOS, Button on Windows UIA, push button on Linux AT-SPI) — treat them as labels, not as strict types.

Step 2 — Click by element index. This is the single most important habit:

computer_use(action="click", element=7)

Much more reliable than pixel coordinates for every model. Claude was trained on both; other models are often only reliable with indices.

Step 3 — Verify. After any state-changing action, re-capture. You can save a round-trip by asking for the post-action capture inline:

computer_use(action="click", element=7, capture_after=True)

Read the full file on GitHub · 288 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. 5d ago First seen · 288 lines · 71 tokens per session scan F bb792db8128b

Subscribe to this mod's changes

computer-use is a skill published in the GitHub repository AtlasOmnia/hermes-custom-pack (55 stars, last pushed 20d ago), licensed MIT. It adds 71 tokens to every session and 2,987 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it F with 4 findings (asks for root, downloads and executes remote code, recursive force delete). It is 94% identical to computer-use, differing in 134 lines, and is treated as a copy.