agentmods.dev

desktop

desktop is a skill for Claude Code, Codex from iammrduncan/fxbot. It costs 42 tokens per session (175 once invoked), scanned A, original, Apache-2.0.

Use for a desktop app on your computer, such as a file manager or an editor, and its windows, buttons, menus, and fields, with the agent-desktop command and its accessibility trees.

Skill for Claude CodeCodex

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

not rated 11repo today A scan 42 tokens original Apache-2.0
Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/iammrduncan/fxbot/desktop
View source ↗ iammrduncan/fxbot fxbot.sh
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 iammrduncan/fxbot --skill desktop
Clone the repo
git clone --depth 1 https://github.com/iammrduncan/fxbot

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 desktop

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/iammrduncan/fxbot/desktop"><img src="https://agentmods.dev/badge/skills/iammrduncan/fxbot/desktop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 175 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 $0.00042 $0.00175
Opus 5.5 $0.00017 $0.00070
Sonnet 5.5 $0.00008 $0.00035
Haiku 4.5 $0.00004 $0.00017

Measured today against content hash 5d17db493f95, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 today.

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/skills/desktop/SKILL.md · 16 lines

What it actually says

Desktop apps

Run agent-desktop skills get desktop through computer_shell, and follow what it prints: it matches the agent-desktop on your computer.

On your computer:

  • Start apps with agent-desktop launch, and Chromium only through agent-browser.
  • For a web page, use agent-browser, not agent-desktop: its refs are the page's own.
  • Wait for an app's window before you take a snapshot.
  • For the terminal window, use computer_terminal, not agent-desktop.
  • For what has no tree, such as a canvas, use computer_desktop.
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. today First seen · 16 lines · 42 tokens per session scan A 5d17db493f95

Subscribe to this mod's changes

desktop is a skill published in the GitHub repository iammrduncan/fxbot (11 stars, last pushed today), licensed Apache-2.0. It adds 42 tokens to every session and 175 once invoked, about $0.0002 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 2026-11-06.

Autonomous AgentsDesign and UXagent-harnessagent-toolsai-agentsharnessmcp-tools
Related

desktop compared with skills from other repositories

desktop next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
desktopiammrduncan/fxbotSkill11todayApache-2.0A42Claude Code, Codex
frontend-designyrris/pro-agentSkill233mo agononeA38Claude Code, Codex
prototyperengwu/iudexSkill154mo agononeA90Claude Code, Codex
skin-creatornetease-youdao/LobsterAISkill6.2kyesterdayMITA48Claude Code, Codex
a2uiPrism-Shadow/penguin-harnessSkill3.2kyesterdayApache-2.0A203Claude Code, Codex
canvas-designnetease-youdao/LobsterAISkill6.2kyesterdayMITA59Claude Code, Codex
oma-designfirst-fluke/oh-my-agentSkill1.4kyesterdayMITA32Claude Code