A tool for controlling approved Windows desktop applications through CodeFlowMu Windows Use. A coding agent can inspect windows, click controls, type, scroll, use accessibility controls, and capture screenshots.

Use it to interact with approved native Windows apps, including opening them, completing permitted UI actions, handling login steps with the user when required, and capturing their windows.

It lets an agent operate native Windows applications when browser tools are not suitable. It also requires the application to be approved and follows the application's specified login and verification process.

windows-use — Skill for Claude Code and Codex by joinwell52-AI: A tool for controlling approved Windows desktop applications through…

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.

agentmods

npx agentmods add skills/joinwell52-ai/codeflowmu-open/windows-use

Any agent

npx skills add joinwell52-AI/CodeFlowMu-open --skill windows-use

Clone the repo

git clone --depth 1 https://github.com/joinwell52-AI/CodeFlowMu-open

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/joinwell52-ai/codeflowmu-open/windows-use.svg)](https://agentmods.dev/skills/joinwell52-ai/codeflowmu-open/windows-use)

Your own site

<a href="https://agentmods.dev/skills/joinwell52-ai/codeflowmu-open/windows-use"><img src="https://agentmods.dev/badge/skills/joinwell52-ai/codeflowmu-open/windows-use.svg" alt="Measured on agentmods" height="20"></a>

Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 896 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00060	$0.00896
Opus 5	$0.00030	$0.00448
Sonnet 5	$0.00012	$0.00179
Haiku 4.5	$0.00006	$0.00090

Measured 4d ago against content hash b6dc16ad587e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

windows-use 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 4d 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/windows-use/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Windows Use

Control only applications the user approved in CodeFlowMu Panel. Treat application approval as permission to access that app, not blanket permission for risky side effects.

Workflow

Call windows.capabilities when host readiness is unknown.
Call windows.list_targets before handling login. Follow loginMethod, verificationChannel, loginInstruction, and requiresUser; never infer an authentication flow. A saved password is reported only as a boolean and is never returned.
For qr_code or verification-code methods, stop at the login step and wait for the user. If the method is unspecified, ask the user instead of guessing.
To open an approved target, first reuse any window returned by discovery. Call windows.launch_target only when the target is not already running. Native launch is idempotent and may return already_running=true; never relaunch a minimized, hidden, or initializing application. Web launch only opens the URL—route all page DOM work to a browser-specific capability.
For a native target, call windows.wait_for_app instead of using Shell sleep, then select the returned app_id and window_id. Never invent or reuse a stale window identifier.
Call windows.inspect_ui when labels or standard controls can identify the target. Prefer windows.invoke_ui: UI Automation InvokePattern works without taking foreground focus.
Only when an operation truly needs foreground input, call windows.activate. Never use PowerShell, Alt+Tab, or a terminal to force focus. If activation is blocked, windows.click can deliver a bounded window-message fallback, while text/keyboard input must pause for one user click.
Use windows.screenshot and window-relative coordinates only when UI Automation is insufficient.
Batch a small set of related actions, then inspect again to verify the result. Stop after an error or if the user takes over the foreground window.
Call windows.cancel when the user asks to stop. Claim “paused” only after it returns paused=true. This is an MCP-session pause, not project-level disablement. Call windows.status to verify; call windows.resume only after explicit user instruction.

Read the full file on GitHub · 49 lines

Files

What ships with it

1 file 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.

agents/openai.yaml 203 B

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.

4d ago First seen · 49 lines · 60 tokens per session scan A b6dc16ad587e

Subscribe to this mod's changes

windows-use is a skill published in the GitHub repository joinwell52-AI/CodeFlowMu-open (2 stars, last pushed 10d ago), licensed MIT. It adds 60 tokens to every session and 896 once invoked, about $0.0003 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 2026-08-31.

ai-team cursor desktop-app developer-tools human-ai-collaboration mcp

agentbro-release

Use when releasing AgentBro from this repository: merging dev/main, bumping versions, updating release notes, tagging, pushing, monitoring GitHub Actions, Homebrew cask publication, or fixing a bad release.

shirenchuang/agentbro · 46 tokens

agentbro-pr-merge

Use when reviewing, fixing CI for, approving workflows for, or merging AgentBro pull requests into dev/main, especially external contributor PRs where contributor attribution matters.

shirenchuang/agentbro · 38 tokens

source-command-check

跑全套本地校验(前端 lint/test/build + Rust check)。.

shirenchuang/agentbro · 21 tokens

oculpm-journal

MCP 도구가 보이면 이 스킬 대신 도구를 쓴다 — journalwrite / planstatus / planupdate 가 경로·파일명·frontmatter 규격을 서버에서 보장한다. 아래는 도구가 없을 때 파일을 직접 쓰는 규격이다.

bunhine0452/Ocul-PM · 58 tokens

self-audit

작업을 "완료"라고 보고하기 직전, 스스로 결과를 감사할 때. 커밋/PR 직전 최종 점검에도 사용.

bunhine0452/Ocul-PM · 39 tokens

project-inception

Use when kicking off a new project or feature area in an ocul-pm tracked project (.oculpm/ present) — research the stack landscape via web search, then converse with the user (research-backed choices) to settle the optimal spec, and seed a discussion doc, a detailed 3-depth plan (plancreate), EVALS.md done-criteria…

bunhine0452/Ocul-PM · 85 tokens