agentmods.dev

talon-computer-use

talon-computer-use is a plugin for Claude Code from gettalon/talon-plugins. Its manifest loads nothing; the 1 skill it bundles cost 61 tokens per session together, scanned A, original, MIT.

A macOS desktop control add-on for using the mouse, keyboard, screenshots, windows, displays, and clipboard.

In plain words
What is it for?
Use it to automate desktop tasks such as clicking, typing, taking screenshots, managing windows, and copying or pasting text.
Why use it?
It lets an agent carry out computer actions that would otherwise require manual interaction with the Mac desktop.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest.

not rated 6repo 6mo ago A scan tokens not measured original MIT

Good fit Use it to automate desktop tasks such as clicking, typing, taking screenshots, managing windows, and copying or pasting text.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add gettalon/talon-plugins
/plugin install talon-computer-use
View source ↗ gettalon/talon-plugins
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.

Clone the repo
git clone --depth 1 https://github.com/gettalon/talon-plugins

Made for: Claude Code.

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 talon-computer-use

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

Your own site · 80×15
<a href="https://agentmods.dev/plugins/gettalon/talon-plugins/computer-use"><img src="https://agentmods.dev/badge/plugins/gettalon/talon-plugins/computer-use.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 1 skill cost 61 tokens a session between them.
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.
Security

Grade A, and why

talon-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 1mo 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.

plugins/computer-use/.claude-plugin/plugin.json · 20 lines

What it actually says

{
  "name": "talon-computer-use",
  "description": "Control the macOS desktop \u2014 mouse, keyboard, screenshots, windows, displays, clipboard. Native Quartz event automation via usecomputer CLI.",
  "version": "1.0.0",
  "author": {
    "name": "Talon"
  },
  "homepage": "https://github.com/gettalon/talon-plugins",
  "repository": "https://github.com/gettalon/talon-plugins",
  "license": "MIT",
  "keywords": [
    "computer-use",
    "desktop",
    "automation",
    "macos",
    "mouse",
    "keyboard",
    "screenshot"
  ]
}
Contents

What it installs

The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 61 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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. 1mo ago First seen · 20 lines scan A 9dea9e437bc7

Subscribe to this mod's changes

talon-computer-use is a plugin published in the GitHub repository gettalon/talon-plugins (6 stars, last pushed 6mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Claude Codeai-toolsbrowser-automationchrome-devtoolschrome-extensionclaude
Related

Other plugins, from other repositories

mochi

A browser companion for AI assistants. Bundled MCP tools for Chrome automation, persistent project memory (Continuum chain), and an in-page hint modal — pair with the Mochi Chrome extension.

DevZonayed/Mochi · not measured

browser-relay

Let agents use the Chrome you already have open and logged in through a Skill + CLI, locally or across machines.

reliefeai/browser-relay · not measured

devharness

Run and debug a live app from inside Claude Code: breakpoints and variable inspection in Chrome and Node.js, managed dev servers, and replayable call history so setup is never re-driven by hand.

InDate/devharness · not measured

chrome-bridge

Borrow a tab from your own logged-in Chrome and hand it back: navigate, read, fill, audit, diff and record in the browser you already use; logins, 2FA and CAPTCHAs stay with you (handoff). ChromeOS included; the debugger only on request (trusted input, traces, video). Ships the chrome-bridge skill (recipes) and the…

frsorrentino/chrome-bridge · not measured

architect

Multidisciplinary idea and project evaluator — dispatches parallel specialist agents, synthesizes unified assessment with scores.

JuanMarchetto/agent-skills · not measured

architecture-reviewer

Audit code against architecture documentation — detects drift between design and implementation.

JuanMarchetto/agent-skills · not measured