computer-use

computer-use is a skill for Claude Code, Codex from NousResearch/hermes-agent. It costs 13 tokens per session (3,856 once invoked), scanned A, original, MIT.

A guide for controlling a computer desktop in the background through actions such as capturing the screen and interacting with apps.

In plain words
What is it for?
Use it for desktop tasks that require viewing and operating graphical applications.
Why use it?
It lets an agent work across desktop applications without taking over the user's cursor, keyboard focus, or virtual desktop.

Skill for Claude CodeCodex

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

Good fit Use it for desktop tasks that require viewing and operating graphical applications.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nousresearch/hermes-agent/computer-use
About the project

Hermes Agent is an AI assistant that learns from its use by creating and improving skills, retaining knowledge, searching past conversations, and adapting to its users. It is for people who want to run an agent through a terminal or messaging platforms while connecting it to different AI models and scheduled tasks.

NousResearch/hermes-agent · 242,093 stars · on GitHub · hermes-agent.nousresearch.com

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 NousResearch/hermes-agent --skill computer-use
Clone the repo
git clone --depth 1 https://github.com/NousResearch/hermes-agent

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/nousresearch/hermes-agent/computer-use.svg)](https://agentmods.dev/skills/nousresearch/hermes-agent/computer-use)
Your own site
<a href="https://agentmods.dev/skills/nousresearch/hermes-agent/computer-use"><img src="https://agentmods.dev/badge/skills/nousresearch/hermes-agent/computer-use.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,856 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. ✓ AI security review Sonnet 5 · 6 Sept 2026
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 $0.00013 $0.03856
Opus 5 $0.00006 $0.01928
Sonnet 5 $0.00003 $0.00771
Haiku 4.5 $0.00001 $0.00386

Measured 3d ago against content hash e3d11184959b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 3d 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

skills/autonomous-ai-agents/computer-use/SKILL.md · 340 lines

How it starts

The opening of the file, as written. The whole thing — 340 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. This wrapper skill teaches the Hermes computer_use workflow and action vocabulary. Call the actions documented below instead of raw cua-driver MCP tools. For driver internals and platform-specific behavior, follow the Cua skill installed by cua-driver skills install. Hermes autodetection is a planned cua-driver follow-up, so currently point Hermes at the resulting ~/.cua-driver/skills/cua-driver directory or symlink it into your skill space.

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:

Read the full file on GitHub · 340 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. 3d ago First seen · 340 lines · 13 tokens per session scan F e3d11184959b

Subscribe to this mod's changes

computer-use is a skill published in the GitHub repository NousResearch/hermes-agent (242,093 stars, last pushed yesterday), licensed MIT. It adds 13 tokens to every session and 3,856 once invoked, about $0.0001 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 2026-09-03.

Related

Other skills, from other repositories

content-hash-cache-pattern

Cache expensive file processing results using SHA-256 content hashes — path-independent, auto-invalidating, with service layer separation.

affaan-m/ECC · 30 tokens

keybindings-help

Use when the user wants to customize keyboard shortcuts, rebind keys, add chord bindings, or modify /.claude/keybindings.json. Examples: "rebind ctrl+s", "add a chord shortcut", "change the submit key", "customize keybindings".

asgeirtj/system_prompts_leaks · 57 tokens

fewer-permission-prompts

Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.

asgeirtj/system_prompts_leaks · 38 tokens

shogun-model-switch

A live-switching tool for changing which command-line AI agent, model, and reasoning mode is running. It updates settings, restarts the agent, and refreshes the displayed session information.

yohey-w/multi-agent-shogun · 83 tokens

14-email-marketing

Dung khi can xay chuoi email hoac Zalo OA gui theo kich ban — welcome series, nurture, promotion, win-back: phan tep, luong automation, subject line, tan suat gui, A/B test va KPI open/click. Kich hoat khi user nhac 'email marketing', 'chuoi email tu dong', 'welcome email', 'email nurture', 'broadcast Zalo OA', 'co…

minhnv0807/ai-business-skills · 189 tokens

notebooklm-manager

Manages NotebookLM notebooks — query, add, list, search, enable/disable, remove. Use when a notebooklm.google.com URL appears or user mentions NotebookLM. Handles URLs through its own Chrome agent — do not navigate directly. Requires: claude-in-chrome MCP.

LeeJuOh/claude-code-zero · 62 tokens