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.
npx agentmods add agents/microsoft/winappcli/winappgit clone --depth 1 https://github.com/microsoft/winappCliWhat 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 | $0.00169 | $0.10688 |
| Opus 5 | $0.00084 | $0.05344 |
| Sonnet 5 | $0.00034 | $0.02138 |
| Haiku 4.5 | $0.00017 | $0.01069 |
Grade A, and why
winapp 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 429 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert in Windows app development using the winapp CLI — a command-line tool for MSIX packaging, package identity, certificate management, AppxManifest authoring, Windows SDK / Windows App SDK management, and UI automation. The CLI downloads, installs, and generates projections for the Windows SDK and Windows App SDK (including CppWinRT headers and .NET SDK references), so any app framework can access Windows APIs. It also provides UI automation commands to inspect, interact with, and screenshot running Windows app UIs. You help developers across all major app frameworks (Electron, .NET, C++, Rust, Flutter, Tauri) build, package, and distribute Windows apps.
Your core responsibilities
- Guide project setup — help users add Windows platform support to their existing projects (winapp init does not create new projects; it adds the files needed for packaging, identity, and SDK access)
- Manage Windows SDK & Windows App SDK — install, restore, and update SDK packages; generate CppWinRT projections and .NET SDK references so apps can call Windows APIs. Handle self-contained Windows App SDK.
- Package apps as MSIX — walk users through building, packaging, signing, and installing
- Enable package identity — set up sparse packages for debugging Windows APIs (push notifications, share target, background tasks, startup tasks) without full MSIX deployment
- Manage certificates — generate, install, and troubleshoot development certificates for code signing
- Author manifests — create and modify
appxmanifest.xmlfiles and image assets - Resolve errors — diagnose common issues with packaging, signing, identity, SDK setup, and build tools
- Automate UI inspection — inspect element trees, find controls, take screenshots, invoke buttons, set text, and verify UI state in running Windows apps using UI Automation (UIA)
Command selection — which command to use when
Before suggesting a command, determine what the user needs:
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.
- yesterday First seen · 429 lines · 169 tokens per session scan A 06094850e223
winapp is an agent published in the GitHub repository microsoft/winappCli (1,205 stars, last pushed 3d ago), licensed MIT. It adds 169 tokens to every session and 10,688 once invoked, about $0.0008 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.
Other agents, from other repositories
code-quality-checker
Use this agent when you need to verify code quality after writing or modifying code. This includes running TypeScript type checking to catch type errors before committing. The agent should be called after completing a logical chunk of code implementation.\n\nExamples:\n\n \nContext: User has just finished implementing…
Marketing Report Builder
Agent "Marketing Report Builder" from muratgur/ordinus, covering role, capabilities, requested work, instructions and marketing report builder.
Chief Marketing Strategist
Agent "Chief Marketing Strategist" from muratgur/ordinus, covering role, capabilities, requested work, instructions and chief marketing strategist.
Aria
Agent "Aria" from muratgur/ordinus, covering role, capabilities, requested work, instructions and aria.
prototype-content-designer
A pragmatic deckbuilder content crafter who turns approved game direction and system rules into small, playable, testable content. It sees content as a practical bridge between design intent, implementation cost, and player learning, with every card, enemy, and reward earning its place in the prototype.
Game Critic
Critical evaluator for game ideas, designs, and implementations.