Windows-MCP: Skill for Claude Code

.claude/skills/windows-mcp-tool-tester/SKILL.md

windows-mcp-tool-tester is a skill for Claude Code from CursorTouch/Windows-MCP. It costs 139 tokens per session (6,451 once invoked), scanned A, original, MIT.

An automated testing skill for Windows-MCP tools, which let an agent control and inspect Windows. It creates tests from a tool’s description and parameter rules, runs them, and reports the results.

In plain words
What is it for?
Testing one Windows-MCP tool at a time, covering normal and unusual inputs, checking errors, measuring response time, and safely cleaning up test processes.
Why use it?
It checks both whether a tool behaves correctly and how quickly it responds, including verification of actions that change the computer.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is CursorTouch/Windows-MCP's own configuration. It tells Claude Code how to work on Windows-MCP itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Windows-MCP configures →

About the project

Windows-MCP is an MCP server that lets AI agents operate Windows computers through actions such as navigating files, opening applications, controlling windows, and interacting with user interfaces. It is used for desktop automation, software testing, and other tasks that require an agent to use Windows.

CursorTouch/Windows-MCP · 6,964 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to CursorTouch/Windows-MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/CursorTouch/Windows-MCP/main/.claude/skills/windows-mcp-tool-tester/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/CursorTouch/Windows-MCP

Made for: Claude Code.

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 windows-mcp-tool-tester

README.md
[![agentmods](https://agentmods.dev/badge/skills/cursortouch/windows-mcp/windows-mcp-tool-tester/github.svg)](https://agentmods.dev/skills/cursortouch/windows-mcp/windows-mcp-tool-tester)
Your own site
<a href="https://agentmods.dev/skills/cursortouch/windows-mcp/windows-mcp-tool-tester"><img src="https://agentmods.dev/badge/skills/cursortouch/windows-mcp/windows-mcp-tool-tester/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 windows-mcp-tool-tester

Your own site · 80×15
<a href="https://agentmods.dev/skills/cursortouch/windows-mcp/windows-mcp-tool-tester"><img src="https://agentmods.dev/badge/skills/cursortouch/windows-mcp/windows-mcp-tool-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 139 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,451 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 87
    Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.
    Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
  • medium Prompt Injection · line 250
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
How audits are shown
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 $0.00139 $0.06451
Opus 5 $0.00069 $0.03225
Sonnet 5 $0.00028 $0.01290
Haiku 4.5 $0.00014 $0.00645

Measured 11d ago against content hash df6dfb97f7b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

windows-mcp-tool-tester 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 11d 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

.claude/skills/windows-mcp-tool-tester/SKILL.md · 586 lines

How it starts

The opening of the file, as written. The whole thing — 586 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Windows-MCP Tool Tester

An automated testing skill that generates comprehensive test cases for a single Windows-MCP tool, executes them, and produces a structured test report with pass/fail results, performance metrics, and actionable recommendations.

Core Principles

  • One tool per invocation. If the user doesn't specify which tool to test, ask them before proceeding.
  • Black-box testing only. Derive test cases exclusively from the MCP tool description and parameter schema — never read source code. Silence in the schema is a documentation gap, not a testing hint.
  • Auto-generate test cases from the tool's MCP description and parameter schema. Cover common scenarios, edge cases, parameter combinations, and error handling paths.
  • Measure two dimensions: correctness (return value matches expectations) and response time (end-to-end, including MCP overhead).
  • Mandatory side-effect verification: every tool call that may modify system state MUST be independently verified — no exceptions, no sampling.
  • Safe cleanup: track process PIDs spawned during testing; only kill those specific PIDs during teardown, never kill by process name alone.
  • Safety first: Windows-MCP has full system access with no sandboxing. Tests involving destructive tools (FileSystem delete, Registry set/delete, Process kill, PowerShell) can modify or destroy data. Running in a VM or Windows Sandbox is strongly recommended. Before executing destructive test cases, confirm the user accepts the risk. See SECURITY.md.
  • Produce a structured report at the end (see Step 4).

Step 0: Identify the Target Tool

If the user hasn't specified a tool, present the full list and ask them to pick one:

App, PowerShell, Screenshot, Snapshot, Click, Type, Scroll, Move, Shortcut, Wait, MultiSelect, MultiEdit, Clipboard, Process, Notification, FileSystem, Registry, Scrape

Once a tool is confirmed, proceed to Step 1. Do NOT test multiple tools in one session.

Read the full file on GitHub · 586 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.

  1. 11d ago First seen · 586 lines · 139 tokens per session scan A df6dfb97f7b3

Subscribe to this mod's changes

windows-mcp-tool-tester is a skill published in the GitHub repository CursorTouch/Windows-MCP (6,964 stars, last pushed 4d ago), licensed MIT. It adds 139 tokens to every session and 6,451 once invoked, about $0.0007 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 2026-08-30.

Related

Other skills, from other repositories

verification-protocol

Mandatory end-to-end verification for .NET MAUI and Comet app tasks. Enforces dependency ownership — broken tools and missing config are YOUR problem to fix, not blockers to report. USE FOR: any task touching UI, pages, navigation, services, or app behavior. Triggers: after code changes, before marking todos done…

dotnet/maui-labs · 105 tokens

maui-unit-testing

Add MAUI app tests around ViewModels, services, platform abstractions, and unit/integration/device boundaries. USE FOR: xUnit, avoiding MauiProgram.CreateMauiApp in unit tests, fakes/mocks, injectable Essentials interfaces, PlatformNotSupportedException, navigation/data services, AppProjectReference, device-test…

dotnet/maui-labs · 84 tokens

host-computer-use

Beta desktop control through the connected A0 CLI host. Use for the user's host/local computer screenshots, screen inspection, menus, native app UI, OS-level clicking, scrolling, typing, or checking computeruseremote status. Use instead of linux-desktop for host/local machine control. Do not use for ordinary browser…

agent0ai/agent-zero · 78 tokens

robotgo-flow

Use when building YAML-driven Windows RPA workflows in Go — step-by-step desktop automation with image template matching, interactive recording mode, hotkey triggers. RobotGo-Flow: YAML-based Windows RPA framework built on RobotGo.

znlgis/opengis-skills · 50 tokens

testing-expert

Expert-level software testing with unit tests, integration tests, E2E tests, TDD/BDD, and testing best practices. Use when the user mentions TDD, BDD, unit tests, integration tests, or end-to-end tests, or when the task involves Testing Fundamentals, Unit Testing, Integration Testing, or End-to-End Testing.

personamanagmentlayer/pcl · 73 tokens

electron-expert

Expert in Electron framework, desktop app development, IPC, and cross-platform packaging. Use when the user mentions desktop, Node.js, cross platform, Windows, macOS, or Linux, or when the task involves Electron Architecture, Process Types, IPC Communication, or App Lifecycle.

personamanagmentlayer/pcl · 59 tokens