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.
Borrowing it
Nothing to install: this file belongs to microsoft/winappCli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/microsoft/winappCli/main/AGENTS.mdgit 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/instructions/microsoft/winappcli/agents-md)<a href="https://agentmods.dev/instructions/microsoft/winappcli/agents-md"><img src="https://agentmods.dev/badge/instructions/microsoft/winappcli/agents-md/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/instructions/microsoft/winappcli/agents-md"><img src="https://agentmods.dev/badge/instructions/microsoft/winappcli/agents-md.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 | $0.07905 | $0.07905 |
| Opus 5.5 | $0.03162 | $0.03162 |
| Sonnet 5.5 | $0.01581 | $0.01581 |
| Haiku 4.5 | $0.00791 | $0.00791 |
Grade A, and why
winappCli AGENTS.md 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 — 609 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions for winapp
This file provides focused, actionable information to help an AI coding agent be immediately productive in this repo.
Audience contracts
Plain language (everything you write for people)
This covers PRs, issues, review comments, chat replies, commit messages, and docs. Don't assume the reader knows this change, this code, or this conversation.
- Lead with what the user sees, then why. Say the cause after the effect.
- Show, don't describe. Add one concrete example for each claim that isn't obvious: a command and its output, a file tree, or a short code snippet.
- Explain the context, not the basics. Define a project or Windows term the first time in a few words, for example "AUMID (the ID Windows uses for an installed app)". Don't explain git, JSON, or what a CLI flag is.
- Use short sentences and everyday words. Write "use", not "leverage". Name each thing one way and stick to it.
- Don't talk down. Never write "simply", "just", "obviously", "as you know", or "it's easy". Leave out filler, hedging, and praise ("robust", "comprehensive", "seamless").
- When asking someone to choose, assume they know nothing about the feature. First say what decision is needed and why it matters. Then, for each option, say in simple words what the user would see, with an example, and what it costs: extra code, time, or risk. Recommend one and say why.
- Check before posting: could someone who joined this week explain the change back after one read? If not, rewrite it. Don't add more text.
Example of a choice:
- Hard to follow: "Option A: fail fast on ambiguous AUMID. Option B: heuristic frame selection."
- Clear: "Two Calculator windows are minimized, so winapp can't tell which one
you mean. (A) Stop and list both windows so you pick one with
-w. It's always correct, but it costs one extra step. (B) Pick the most recently used window. There's no extra step, but it's sometimes the wrong window. I recommend A, because acting on the wrong window is confusing."
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 Changed · -8 tokens per session bfe5bebc7643
- 12d ago Changed · +16 lines · +229 tokens per session 4f1af9218806
- 13d ago Changed · +6 lines · +158 tokens per session 0656a533c812
- 15d ago Changed · +131 lines · +1,605 tokens per session 1d7523cbb4bd
- 20d ago Changed · +2 lines · +47 tokens per session 46d0880123ff
- 21d ago Changed · +16 lines · +292 tokens per session 8f1cf3b96080
- 22d ago Changed · +2 lines · +57 tokens per session 8723800ebe06
- 23d ago Changed · +17 lines · +300 tokens per session 60f97fe1dd3c
- 1mo ago Changed · +40 lines · +515 tokens per session 170dd7418174
- 1mo ago First seen · 379 lines · 4,710 tokens per session scan A 6b5c54257e70
winappCli AGENTS.md is an instructions file published in the GitHub repository microsoft/winappCli (1,346 stars, last pushed today), licensed MIT. It adds 7,905 tokens to every session, about $0.0316 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.