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.
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 skills add microsoft/winappCli --skill winapp-find-apigit clone --depth 1 https://github.com/microsoft/winappCliWrote 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.
[](https://agentmods.dev/skills/microsoft/winappcli/winapp-find-api)<a href="https://agentmods.dev/skills/microsoft/winappcli/winapp-find-api"><img src="https://agentmods.dev/badge/skills/microsoft/winappcli/winapp-find-api/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.
<a href="https://agentmods.dev/skills/microsoft/winappcli/winapp-find-api"><img src="https://agentmods.dev/badge/skills/microsoft/winappcli/winapp-find-api.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00202 | $0.05950 |
| Opus 5 | $0.00101 | $0.02975 |
| Sonnet 5 | $0.00040 | $0.01190 |
| Haiku 4.5 | $0.00020 | $0.00595 |
Grade A, and why
winapp-find-api 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.
How it starts
The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This is an agent-first command
find-api was designed for you, the agent — not primarily for a human reading a
terminal. It exists because the failure mode it prevents is an agent-specific one:
confidently writing a type, property, or enum value that does not exist. Treat it as
the authority on the API surface, not as an optional convenience:
- Ground every Windows/WinRT symbol you emit. If you are not certain a type, property, or enum value exists in this project's metadata, look it up before you write it. A lookup is cheaper than a build.
- Prefer it over recall and over web search. Your training data describes some
version of WinUI/WinRT;
find-apidescribes the exact metadata this project references. When they disagree,find-apiwins. - Use
--json. Every verb emits structured output with stable shapes and non-zero exit codes on missing subjects, so you can gate codegen on the result instead of parsing prose. - Batch subjects into one call. See below — this matters more here than anywhere else in the CLI.
Humans can and do run it directly, and everything below works fine typed by hand. But
the ergonomics (batching, --json, exit codes, compile-error workflows) are tuned for
agent loops.
When to use
- Discovering which Windows/WinRT type or member does what you need ("what's the acrylic brush type?", "which control is a NavigationView?")
- Listing a type's properties, events, and methods (declared and inherited) before writing XAML or code against it
- Validating that a property exists on a type — catching typos and wrong-type mistakes before they become CS0117/XAML binding errors
- Enumerating an enum's values (e.g.
Symbol,Visibility) - Exploring the namespaces and packages a project can call into
- AI agents grounding code generation in the actual API surface a project references, instead of guessing
- Diagnosing a compile error that names a type or member — see below
Use it on compile errors, not just before writing code
When a build fails with any of these, the error is a claim about the API surface, and
find-api is the authority on that surface. Look the symbol up before editing:
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.
- today First seen · 300 lines · 202 tokens per session scan A 254da559a993
winapp-find-api is a skill published in the GitHub repository microsoft/winappCli (1,250 stars, last pushed today), licensed MIT. It adds 202 tokens to every session and 5,950 once invoked, about $0.0010 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 2026-09-12.
Other skills, from other repositories
brand-identity
Use when a project needs its visual foundation built or consolidated into one system: logo brief, color system in HEX/RGB/CMYK/OKLCH with proven AA contrast, type system, usage rules, and an exported W3C design-tokens.json that later skills consume. NOT the applied UI pixels (that is design), NOT the words or tone…
quicker-authoring-getquicker-user-actions
A workflow for reading public action lists from getquicker.net, including pages beyond the first one, and totaling their likes and count.
quicker-authoring
Routes Quicker headless action editing (P0–P7): pick workflow topic, then schema/step-runner refs. Use when creating or editing Quicker actions, subprograms, steps, or data.json on disk.
quicker-browser-script
End-to-end webpage scripting via the Quicker browser extension: prototype RunScript live (userbrowser / chromecontrol), save as a sys:chromecontrol action, then auto-run it with event triggers (quickertrigger, e.g. BrowserUrlChanged). Use when the user wants scripts to run on pages automatically.
quicker-action-library-search
Search getquicker action library and read shared actions for learning via qkrpc API (library search + shared get, read-only). Use when finding exemplar actions before writing Quicker actions.
quicker-authoring-evalexpression-multi-var
Load when benchmark or user asks for one evalexpression step setting multiple action variables.