What is desktop-ui-control?

A guide for observing and controlling Windows applications through their accessible interface elements and window controls.

Opening and operating Windows apps, working with dialogs and settings, and troubleshooting native desktop interfaces.

It helps desktop actions target known interface elements and verify the result after each change.

desktop-ui-control — Skill for Claude Code and Codex by CodeInfinity1

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 CodeInfinity1/Stram --skill desktop-ui-control

Clone the repo

git clone --depth 1 https://github.com/CodeInfinity1/Stram

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/codeinfinity1/stram/desktop-ui-control/github.svg)](https://agentmods.dev/skills/codeinfinity1/stram/desktop-ui-control)

Your own site

<a href="https://agentmods.dev/skills/codeinfinity1/stram/desktop-ui-control"><img src="https://agentmods.dev/badge/skills/codeinfinity1/stram/desktop-ui-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/codeinfinity1/stram/desktop-ui-control"><img src="https://agentmods.dev/badge/skills/codeinfinity1/stram/desktop-ui-control.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 479 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	$0.00034	$0.00479
Opus 5.5	$0.00014	$0.00192
Sonnet 5.5	$0.00007	$0.00096
Haiku 4.5	$0.00003	$0.00048

Measured 1mo ago against content hash 4c907f2dae5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

desktop-ui-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 1mo 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.

skills/desktop-control/desktop-ui-control/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Desktop UI Control

Purpose

Control Windows applications safely using native Stram OS tools. The assistant should observe windows and UI Automation elements before acting, then verify after each action.

When To Use

Use for Windows app workflows, app dialogs, settings panels, installer prompts, local desktop tasks, and native UI troubleshooting.

Inputs And Evidence

User goal, target app/window, allowed actions, and expected final state.
os_windows output, UIA selector map, element IDs, active window metadata, screenshots.
Approval status for UI observation and state-changing actions.

Tool Map

active_window
os_windows
os_observe_ui
os_click_element
os_type_text
os_send_keys
os_scroll_element
os_switch_window
os_window_state

Workflow

List windows or inspect active window.
Observe UIA tree with approval when element actions are needed.
Choose targets from observed element IDs, not guessed coordinates.
Perform one action at a time.
Observe again and compare against expected state.
Stop for credentials, destructive prompts, ambiguity, or repeated failed actions.

Native Implementation Boundaries

Use Stram os_* tools only.
Do not import Windows-use, Claude computer, OpenAI computer-use, or external reference code as implementation.
Upstream projects are reference evidence for safe loop design only.

Safety And Approval

UI observation and mutating actions are approval-gated because screens may contain private data.
Do not type secrets unless the user provides them for that exact workflow.
Destructive app actions require explicit confirmation.

Verification

Verify active window and UI state after every action.
Prefer element actions over coordinates.
Use screenshots only when needed and store/delete them through native screen tools.

Failure Modes

Clicking stale element IDs.
Typing into the wrong app.
Continuing after a permission or payment dialog appears.

Read the full file on GitHub · 71 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.

1mo ago First seen · 71 lines · 34 tokens per session scan A 4c907f2dae5a

Subscribe to this mod's changes

desktop-ui-control is a skill published in the GitHub repository CodeInfinity1/Stram (11 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 479 once invoked, about $0.0001 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 2026-09-03.

Productivity ai-agent ai-agents ai-tools desktop-automation desktop-automation-software desktop-automation-windows

ask-agents

Send a task or question to Claude Code and/or Gemini as external subagents and report back what they said. Use when the user asks to ask Claude, ask Gemini, ask both, get a second opinion, split reviewer roles, or compare external agents.

chrisblattman/claudeblattman · 55 tokens

review-plan

Review a proposed plan with a single-pass structured critique and a clear verdict. Use when the user asks to review a plan, stress-test a plan, critique a workflow, identify risks, or improve an execution sequence.

chrisblattman/claudeblattman · 46 tokens

alive:settings

The human wants to adjust how the system behaves — not what it contains, but how it feels. Voice, rhythm, preferences, walnut-level config, full permissions toggleable, named squirrel config, action logging toggle. The system adapting to them. Routes to preferences.yaml or walnut config.yaml depending on scope. For…

alivecontext/alive · 84 tokens

desktop-ui-control