agent-desktop

agent-desktop is a skill for Claude Code, Codex from openwong2kim/wmux. It costs 161 tokens per session (1,693 once invoked), scanned A, original, MIT.

A command-line tool for reading and operating desktop applications through their accessibility information. It can inspect screens and perform actions such as clicking, typing, scrolling, and taking screenshots.

In plain words
What is it for?
Automating desktop applications on macOS, Windows, and Linux, including forms, menus, buttons, and other visible controls.
Why use it?
It gives an agent a structured way to see and verify what desktop software is showing instead of relying only on coordinates or guesses.

Skill for Claude CodeCodex

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

Good fit Automating desktop applications on macOS, Windows, and Linux, including forms, menus, buttons, and other visible controls.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/openwong2kim/wmux/agent-desktop
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 openwong2kim/wmux --skill agent-desktop
Clone the repo
git clone --depth 1 https://github.com/openwong2kim/wmux

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 agent-desktop

README.md
[![agentmods](https://agentmods.dev/badge/skills/openwong2kim/wmux/agent-desktop/github.svg)](https://agentmods.dev/skills/openwong2kim/wmux/agent-desktop)
Your own site
<a href="https://agentmods.dev/skills/openwong2kim/wmux/agent-desktop"><img src="https://agentmods.dev/badge/skills/openwong2kim/wmux/agent-desktop/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 agent-desktop

Your own site · 80×15
<a href="https://agentmods.dev/skills/openwong2kim/wmux/agent-desktop"><img src="https://agentmods.dev/badge/skills/openwong2kim/wmux/agent-desktop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 161 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,693 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.
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 $0.00161 $0.01693
Opus 5.5 $0.00064 $0.00677
Sonnet 5.5 $0.00032 $0.00339
Haiku 4.5 $0.00016 $0.00169

Measured yesterday against content hash 941873a93fca, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-desktop 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 yesterday.

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.

native/agent-desktop/skills/agent-desktop/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agent-desktop

agent-desktop is a CLI that reads and operates desktop apps through the OS accessibility tree. Every command prints one JSON envelope (ok, data or error). It is a tool, not an agent: the observe, act and verify loop runs in you.

Shell syntax

Examples use a POSIX shell. In PowerShell, quote every ref ('@s8f3k2p9:e1'), because a bare @token is the splatting operator. Use $env:NAME = 'value' instead of export, and | ConvertFrom-Json instead of $(...) and jq. The Windows skill has the PowerShell forms.

First run

  1. Run agent-desktop status. It reports the platform, permissions and supported_surfaces.
  2. Run agent-desktop skills get platform. It loads the skill for the OS the binary runs on (macOS, Windows or Linux).
  3. For flags and syntax, run agent-desktop <command> --help. This skill does not repeat flag lists.

The loop

Use find when you know the role or exact name. Otherwise map the app first and drill into one region.

agent-desktop snapshot --skeleton --app "Notes" -i --compact   # shallow map, children_count on cut branches
agent-desktop snapshot --root @s8f3k2p9:e3 -i --compact        # drill into one region
agent-desktop click @s8f3k2p9:e12                              # act on a qualified ref
agent-desktop snapshot --root @s8f3k2p9:e3 -i --compact        # verify: re-read the same region
  • A small app needs no skeleton. Take a full snapshot -i.
  • -i keeps interactive nodes only, so a row's static-text label is dropped. To tell which row a repeated button belongs to, drill that row's container with --root and leave out -i. On Windows and Linux that reads the row but does not make its button actionable: a button repeated in other rows is a twin in the window and its ref is refused (see Refs).
  • A --root drill adds its refs to the same snapshot id. Refs outside the drilled subtree, and the drilled root itself, stay valid; refs that were already inside it are replaced, so an old ref there returns STALE_REF.
  • Never skeleton a surface (--surface menu, sheet, alert). A surface is already focused.
  • An action that opens a menu, sheet or alert lists it in data.surfaces. Target that overlay next.
  • After an async step, use wait (see commands-system.md). A fixed sleep is a race.

Read the full file on GitHub · 85 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 85 lines · 161 tokens per session scan A 941873a93fca

Subscribe to this mod's changes

agent-desktop is a skill published in the GitHub repository openwong2kim/wmux (448 stars, last pushed yesterday), licensed MIT. It adds 161 tokens to every session and 1,693 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-11-07.

Related

agent-desktop compared with skills from other repositories

agent-desktop next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
agent-desktopopenwong2kim/wmuxSkill448yesterdayMITA161Claude Code, Codex
melayamelaya-labs/melaya-mcpSkill1yesterdayApache-2.0A206Claude Code
loopWritbase/writbaseSkill117mo agoApache-2.0A35Claude Code, Codex
pinchtab-mcppinchtab/pinchtabSkill11k11d agoMITA52Claude Code, Codex
tmuxTeam-Commonly/commonlySkill1.4ktodayApache-2.0A48Claude Code, Codex
deja-reflectvshulcz/deja-vuSkill1.4kyesterdayMITA49Claude Code
Agent Browser AutomationPramodDutta/qaskillsSkill2455d agoMITA37Claude Code, Codex