What is windows-desktop-control?

A skill for controlling native Windows desktop applications and browser surfaces through the visible computer interface when a more structured integration is unavailable. It can choose between accessibility controls, display-aware interaction, and coordinate-based fallback.

Use it for native Windows app automation, screen-based browser interaction, display and window placement, screenshots, and actions that require confirmation before changing or deleting data.

It provides a defined way to inspect and operate Windows interfaces when ordinary browser or application integrations cannot reach the needed controls.

windows-desktop-control — Skill for Claude Code and Codex by virtengin

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 virtengine/bosun --skill windows-desktop-control

Clone the repo

git clone --depth 1 https://github.com/virtengine/bosun

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/virtengine/bosun/windows-desktop-control/github.svg)](https://agentmods.dev/skills/virtengine/bosun/windows-desktop-control)

Your own site

<a href="https://agentmods.dev/skills/virtengine/bosun/windows-desktop-control"><img src="https://agentmods.dev/badge/skills/virtengine/bosun/windows-desktop-control/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/virtengine/bosun/windows-desktop-control"><img src="https://agentmods.dev/badge/skills/virtengine/bosun/windows-desktop-control.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 663 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00663
Opus 5	$0.00000	$0.00331
Sonnet 5	$0.00000	$0.00133
Haiku 4.5	$0.00000	$0.00066

Measured 10d ago against content hash 04bd54e5014d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

windows-desktop-control 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 10d 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/windows-desktop-control/skills/windows-desktop-control/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Windows Desktop Control

Use this plugin when the task involves native Windows desktop apps or browser surfaces that do not have a stronger structured integration available.

Operating modes

Pick one of these modes before taking action:

UIA-first mode: preferred for native Windows apps with accessible controls.
Visible-display mode: for quick manual-adjacent automation on the user’s active screen.
Isolated-display mode: for non-interrupting automation on a secondary or virtual display that Windows exposes.
Coordinate-fallback mode: for canvas apps, remote surfaces, or controls that UI Automation cannot reach reliably.

Decision rules

Prefer structured browser automation for websites when a browser tool or MCP server already exists.
Prefer uia_inspect and uia_invoke for native Windows controls before coordinate clicks.
Prefer list_displays and display-aware screenshots before assuming the primary screen is the correct target.
Prefer move_window to place apps on a non-user display before interacting when isolation matters.
Use screenshots to verify state before and after mutating actions.
Ask for human confirmation before destructive actions such as deleting data, closing unsaved work, submitting forms, or sending messages.

Mode patterns

UIA-first mode

Call list_windows and focus_window to target the correct app.
Call uia_inspect to find stable selectors.
Use uia_invoke, type_text, or press_keys.
Capture a screenshot after important mutations.

Isolated-display mode

Call list_displays and choose the non-user display by displayId or displayName.
Launch or find the app with launch_app or list_windows.
Call move_window to place the window on that display. Use fitToDisplay: true when full-display placement is better than a preserved window size.
Use screenshot against that display, then prefer uia_* actions.
If coordinate fallback is required, pass displayRelative: true so coordinates stay local to the isolated display.

Read the full file on GitHub · 57 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.

10d ago First seen · 57 lines · 0 tokens per session scan A 04bd54e5014d

Subscribe to this mod's changes

windows-desktop-control is a skill published in the GitHub repository virtengine/bosun (280 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 663 tokens. 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 2026-08-30.

Browser automation Claude Code agents automation chatgpt claude codex

browser-tools

Security wrapper over the upstream agent-browser skill, adding URL blocklisting, rate limiting, robots.txt enforcement, and scraping guardrails. Use when automating browser workflows that need safety limits.

yonatangross/orchestkit · 40 tokens

web-research-workflow

Unified decision tree for web research and competitive monitoring. Auto-selects WebFetch, Tavily, or agent-browser based on target site characteristics and available API keys. Includes competitor page tracking, snapshot diffing, and change alerting. Use when researching web content, scraping, extracting raw markdown…

yonatangross/orchestkit · 72 tokens

windows-desktop-control