desktop-act

desktop-act is a skill for Claude Code from Lifecycle-Innovations-Limited/claude-ops. It costs 41 tokens per session (583 once invoked), scanned A, original, MIT.

A cross-platform computer-use skill for controlling desktop applications through an MCP interface, with isolated desktop sessions for concurrent agents.

In plain words
What is it for?
Use it to reserve a desktop, take screenshots, perform GUI actions, monitor long-running sessions, and release the session when finished.
Why use it?
It manages desktop access across Linux, macOS, and Windows so agents can interact with graphical software without sharing the same session.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

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

Good fit Use it to reserve a desktop, take screenshots, perform GUI actions, monitor long-running sessions, and release the session when finished.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lifecycle-innovations-limited/claude-ops/desktop-act
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 Lifecycle-Innovations-Limited/claude-ops --skill desktop-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 desktop-act

README.md
[![agentmods](https://agentmods.dev/badge/skills/lifecycle-innovations-limited/claude-ops/desktop-act/github.svg)](https://agentmods.dev/skills/lifecycle-innovations-limited/claude-ops/desktop-act)
Your own site
<a href="https://agentmods.dev/skills/lifecycle-innovations-limited/claude-ops/desktop-act"><img src="https://agentmods.dev/badge/skills/lifecycle-innovations-limited/claude-ops/desktop-act/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 desktop-act

Your own site · 80×15
<a href="https://agentmods.dev/skills/lifecycle-innovations-limited/claude-ops/desktop-act"><img src="https://agentmods.dev/badge/skills/lifecycle-innovations-limited/claude-ops/desktop-act.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 583 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Prompt Injection · line 36
    Subtle instructions detected that may alter agent decision-making or introduce hidden biases.
    Fix: Review content for implicit steering or bias. Ensure instructions are explicit and align with the skill's stated purpose.
How audits are shown
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 $0.00041 $0.00583
Opus 5 $0.00020 $0.00292
Sonnet 5 $0.00008 $0.00117
Haiku 4.5 $0.00004 $0.00058

Measured 6d ago against content hash baf28c3da96b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

desktop-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 6d 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.

desktop-act/skills/desktop-act/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

desktop-act

Computer-use primitives via mcp__desktop-act__* plus act(goal) (OAuth via claude-agent-sdk — no Anthropic API key).

Multi-agent (required pattern)

ensure_desktop(owner_id="<agent-id>", geometry="2560x1440")  # exclusive seat
# … primitives with session_id …
heartbeat_desktop(session_id)   # long runs
release_desktop(session_id)     # on stop / idle done

If another agent holds every free seat, Linux auto-spawns a new Xvnc on the next free display/port. Leases expire (DESKTOP_ACT_LEASE_TTL); reaper frees the lock and stops pool VNC so idle seats do not thrash the host.

Architecture

  • Parent agent is the brain — primitives + screenshots, or hands-off act(goal).
  • Linux: X11 + Xvnc/websockify pool (:50:99), file-locked leases.
  • macOS: single interactive session (Screen Sharing → noVNC optional).
  • Windows: full WinBackend (ImageGrab + pyautogui/SendInput); single interactive desktop only (no multi-seat pool). Needs a logged-in session.

Watching the desktop

Pool session returns novnc_url (port base DESKTOP_ACT_NOVNC_PORT_BASE, default 6082). Host default display (often :1) is separate and is never reaped by the idle reaper. Always prefer the returned URL over hardcoding ports.

Install

  • With claude-ops: desktop-act@ops-marketplace (co-installed by /ops:setup and /ops:update via plugin-dependencies.json).
  • Standalone: marketplace add Lifecycle-Innovations-Limited/desktop-act, then desktop-act@desktop-act.

When to use

Task Approach
Local app you need to click/type into desktop-act primitives
Concurrent agents needing isolated seats Linux pool + ensure_desktop(owner_id=…)
Hands-off goal mcp__desktop-act__act(goal, max_iterations=…)
Browser-only automation Prefer browser MCP tools when no OS UI is required

Defaults

  • act model: claude-sonnet-5
  • act max_iterations: 20 (not max_steps)
  • Python: >=3.11

Read the full file on GitHub · 59 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. 6d ago First seen · 59 lines · 41 tokens per session scan A baf28c3da96b

Subscribe to this mod's changes

desktop-act is a skill published in the GitHub repository Lifecycle-Innovations-Limited/claude-ops (187 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 583 once invoked, about $0.0002 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

telegram-userbot

Use when full MTProto control of Telegram account via Telethon. DM, Voice Note, Call, Video Call, Group/Channel management, member scraping, bot cloning, outreach automation, broadcast, CRM tracking, content reposting, scheduled messaging, webhook triggers. Use for all Telegram automation as a real user (not bot API).

oyi77/1ai-skills · 70 tokens

meeting-agenda-optimizer

Designs effective meeting agendas, reduces meeting waste, and creates structured formats for recurring meetings. Analyzes meeting patterns to recommend which meetings to keep, combine, or eliminate.

Adri3l-R3nan/cognify-skills · 41 tokens

add-teams

Adds Microsoft Teams connector to a Power Apps code app. Use when sending Teams messages, posting to channels, or integrating with Teams chat.

microsoft/power-platform-skills · 31 tokens

sys-configure

Configure Claude Octopus — redirects to /octo:setup interactive wizard.

nyldn/claude-octopus · 18 tokens

context-engineering

Dynamic context injection, mode switching (dev/review/research), selective loading, and strategic compaction for token optimization.

a5c-ai/babysitter · 28 tokens

bookmarks-management

Manages X/Twitter bookmarks — organize by category with auto-tagging, clear all bookmarks in bulk, and export/scrape bookmarks with full metadata. Supports keyword-based categorization, CSV and JSON export, keep-filters, and folder creation (Premium). Use when users want to export, organize, or clear their X bookmarks.

nirholas/XActions · 71 tokens