winapp-sandbox

winapp-sandbox is a skill for Claude Code from microsoft/winappCli. It costs 62 tokens per session (2,004 once invoked), scanned A, original, MIT.

A workflow for running, diagnosing, and automating a Windows application inside Windows Sandbox, a disposable Windows environment. It keeps builds and project evaluation on the host computer and treats the sandbox as a shared guest desktop.

In plain words
What is it for?
Use it to test Windows apps, transfer files, automate their user interface, reconnect to the guest, and collect application or desktop evidence.
Why use it?
It provides a controlled place for disposable app testing and diagnostics while making clear that the sandbox does not automatically isolate builds or set itself up.

Skill for Claude Code ✓ vendor

Written for Claude Code: shipped in a Claude Code plugin.

Part of the winappcli plugin — 12 skills, 1 agent shipped together

Good fit Use it to test Windows apps, transfer files, automate their user interface, reconnect to the guest, and collect application or desktop evidence.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/microsoft/winappcli/winapp-sandbox
About the project

winapp CLI is a command-line tool for Windows application development that manages SDKs, app identity, manifests, certificates, packaging, and build tools. It helps developers using frameworks such as .NET, Win32, CMake, Electron, or Rust access Windows-native development capabilities. The catalogue add-ons provide agent workflows for using the CLI.

microsoft/winappCli · 1,268 stars · on GitHub

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 microsoft/winappCli --skill winapp-sandbox
Clone the repo
git clone --depth 1 https://github.com/microsoft/winappCli

Made for: Claude Code.

Or install winappcli, the plugin that ships this one along with the rest of its 12 skills, 1 agent.

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 winapp-sandbox

README.md
[![agentmods](https://agentmods.dev/badge/skills/microsoft/winappcli/winapp-sandbox/github.svg)](https://agentmods.dev/skills/microsoft/winappcli/winapp-sandbox)
Your own site
<a href="https://agentmods.dev/skills/microsoft/winappcli/winapp-sandbox"><img src="https://agentmods.dev/badge/skills/microsoft/winappcli/winapp-sandbox/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 winapp-sandbox

Your own site · 80×15
<a href="https://agentmods.dev/skills/microsoft/winappcli/winapp-sandbox"><img src="https://agentmods.dev/badge/skills/microsoft/winappcli/winapp-sandbox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,004 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 $0.00062 $0.02004
Opus 5.5 $0.00025 $0.00802
Sonnet 5 $0.00012 $0.00401
Haiku 4.5 $0.00006 $0.00200

Measured today against content hash 88e98ab4e87a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-23, from the pricing page.

Security

Grade A, and why

winapp-sandbox 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/winapp/skills/winapp-sandbox/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Before acting

  • Confirm the user wants Sandbox execution. Do not drop --on sandbox to bypass an error.
  • Builds, project evaluation, and restore still run on the host. Do not build untrusted projects on the assumption that Sandbox isolates them.
  • Windows supports one Sandbox; all apps inside it share a user, desktop, and state. Do not treat separate workflows as mutually isolated.
  • Windows 11 24H2+ on a supported edition and hardware virtualization are required. Guest winapp supports x64/Arm64; x86 apps need guest support and matching dependencies.
  • winapp only checks host prerequisites: it does not enable features, install the client, request elevation, or reboot. --on sandbox selects the target, not setup consent.
  • On sandbox_setup_required, explain the required Windows feature and restart. Decide whether to offer agent-assisted setup or give the user manual steps; obtain explicit approval before running the suggested command in an elevated terminal. Use /NoRestart and let the user choose when to reboot: dism.exe /Online /Enable-Feature /FeatureName:Containers-DisposableClientVM /All /NoRestart.
  • On sandbox_setup_requires_restart, ask the user to save work and restart when ready. Never restart automatically or treat setup approval as reboot approval.
  • On sandbox_setup_incomplete, direct the user to open Windows Sandbox from Start and finish its client setup/update. Do not repeatedly retry an unchanged prerequisite.
  • Connection or reconnect may briefly take focus; do not promise zero desktop interruption.
  • Existing Sandbox instances are reused and changed, not discarded. Never close one or run wsb stop without user consent.

Launch, inspect, act, verify

winapp run . --on sandbox --detach
winapp ui list-windows --on sandbox
winapp ui inspect --on sandbox -a MyApp
winapp ui invoke --on sandbox SubmitButton -a MyApp
winapp ui screenshot --on sandbox -a MyApp -o .\result.png
  1. Use --detach when subsequent commands must inspect the running app; without it, run waits for exit. Use --json when consuming the launch result programmatically.
  2. Replace MyApp with the discovered name or copy the returned UiTargetArgs. Keep --on sandbox on every guest UI command, including commands using a PID/HWND.
  3. Inspect before acting and verify the result. Use winapp-ui-automation for selectors and input methods. Real input and recording need a connected, nonminimized client; read-only inspection can still work when input cannot.
  4. Rebuild by rerunning the same command. Add --clean only when clearing that app's data is intended. --debug-output is supported only for packaged Sandbox apps.
  5. Rediscover targets after the Sandbox is recreated. A detached unpackaged app can also end during guest-agent repair; rerun it if it disappears.

Read the full file on GitHub · 161 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. today Changed · +3 lines 88e98ab4e87a
  2. yesterday Changed · +2 lines 1627fd768a96
  3. 6d ago First seen · 156 lines · 62 tokens per session scan A 31b4ef963f26

Subscribe to this mod's changes

winapp-sandbox is a skill published in the GitHub repository microsoft/winappCli (1,268 stars, last pushed today), licensed MIT. It adds 62 tokens to every session and 2,004 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 2026-09-17.