act

act is a command for Claude Code from Lifecycle-Innovations-Limited/claude-ops. It costs 14 tokens per session (217 once invoked), scanned A, original, MIT.

A command for giving an agent a goal and letting it control a live desktop through screenshots, clicks, typing, keyboard input, and scrolling.

In plain words
What is it for?
Use it to operate desktop applications through an autonomous loop or to inspect the screen and perform specific GUI actions manually.
Why use it?
It handles multi-step desktop tasks without requiring you to issue every computer action yourself, while still allowing direct control of individual actions.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the desktop-act plugin — 1 skill, 1 command shipped together

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 commands/lifecycle-innovations-limited/claude-ops/act
Clone the repo
git clone --depth 1 https://github.com/Lifecycle-Innovations-Limited/claude-ops

Made for: Claude Code.

Or install desktop-act, the plugin that ships this one along with the rest of its 1 skill, 1 command.

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 act

README.md
[![agentmods](https://agentmods.dev/badge/commands/lifecycle-innovations-limited/claude-ops/act.svg)](https://agentmods.dev/commands/lifecycle-innovations-limited/claude-ops/act)
Your own site
<a href="https://agentmods.dev/commands/lifecycle-innovations-limited/claude-ops/act"><img src="https://agentmods.dev/badge/commands/lifecycle-innovations-limited/claude-ops/act.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 217 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 5.1 $0.00014 $0.00217
Opus 5 $0.00007 $0.00109
Sonnet 5 $0.00003 $0.00043
Haiku 4.5 $0.00001 $0.00022

Measured 2d ago against content hash d0e2eb7978bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

act 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • review-ui — 86% identical, 95 lines differ
desktop-act/commands/act.md · 25 lines

What it actually says

/desktop:act — autonomous goal execution

Routes the goal through the desktop-act MCP server. The server uses claude-agent-sdk (bundled CLI + OAuth) so no Anthropic API key is required — costs are covered by a Claude Max subscription.

Usage:

  • /desktop:act <goal> — kick off the loop (act tool, max_iterations)
  • Live view: use the novnc_url returned by ensure_desktop / acquire_desktop (pool noVNC base defaults to port 6082, not a fixed host port)
  • Reasoning streams as normal chat output

For finer control with full reasoning visibility, call the MCP primitives directly: mcp__desktop-act__screenshot(), then Read the path, then mcp__desktop-act__click(x, y), etc.

Goal

$ARGUMENTS

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 · 25 lines · 14 tokens per session scan A d0e2eb7978bf

Subscribe to this mod's changes

act is a command published in the GitHub repository Lifecycle-Innovations-Limited/claude-ops (186 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 217 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.