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 instructions/microsoft/ai-dev-gallery/adding-wcrapisgit clone --depth 1 https://github.com/microsoft/ai-dev-galleryWhat 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 | $0.00738 | $0.00738 |
| Opus 5 | $0.00369 | $0.00369 |
| Sonnet 5 | $0.00148 | $0.00148 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
ai-dev-gallery adding-wcrapis.instructions.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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Windows AI APIs (WCRAPIs) Sample Instructions
When reviewing or modifying samples in AIDevGallery/Samples/WCRAPIs/:
Overview
Windows AI APIs samples use Windows Copilot Runtime APIs (Phi Silica, Text Recognition, etc.) that are built into Windows on Copilot+ PCs.
Limited Access Features (LAF)
Important Security Note
- NEVER commit production LAF tokens to the repository
- Demo tokens in code are for development only
- Use
LimitedAccessFeaturesHelperfor token management
Feature Availability Checks
Always check if the API is available before use:
var readyState = LanguageModel.GetReadyState();
if (readyState is AIFeatureReadyState.Ready or AIFeatureReadyState.NotReady)
{
if (readyState == AIFeatureReadyState.NotReady)
{
var operation = await LanguageModel.EnsureReadyAsync();
if (operation.Status != AIFeatureReadyResultState.Success)
{
ShowException(null, "Feature not available");
return;
}
}
// Use the API
}
else
{
var msg = readyState == AIFeatureReadyState.DisabledByUser
? "Disabled by user."
: "Not supported on this system.";
ShowException(null, $"Feature not available: {msg}");
}
Model Types for WCRAPIs
Use ModelType.PhiSilica or specific WCRAPI model types:
[GallerySample(
Model1Types = [ModelType.PhiSilica],
...
)]
Code Review Checks
- LAF tokens use
LimitedAccessFeaturesHelper, not hardcoded values - Feature availability checked before use
- Proper error handling for unsupported devices
- User-friendly messages for availability failures
- Graceful fallback when API is not ready
- CancellationToken support for long operations
- Proper disposal of AI resources
Checklist for Adding a New WCR API
When adding a new Windows AI API to the gallery, complete all of the following:
1. API Definition
- Add entry in
AIDevGallery/Samples/Definitions/WcrApis/apis.json
2. Availability Registration (in WcrApiHelpers.cs)
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.
- 2d ago First seen · 93 lines · 738 tokens per session scan A a50fdb9d9f06
ai-dev-gallery adding-wcrapis.instructions.md is an instructions file published in the GitHub repository microsoft/ai-dev-gallery (1,498 stars, last pushed 13d ago), licensed MIT. It adds 738 tokens to every session, about $0.0037 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 instructions, from other repositories
maui uitests.instructions.md
Instructions for dotnet/maui, covering ui testing guidelines for .net maui, ui test structure, two-project requirement, base class and infrastructure and naming conventions.
maui ci-copilot-pipeline-security.instructions.md
Security rules for the Copilot PR-review pipeline. Read before editing.
pydantic-ai AGENTS.md
Instructions for pydantic/pydantic-ai, covering your primary responsibility is to the project and its users, gathering context on the task, ensuring the task is ready for implementation, philosophy and requirements of all contributions.
maui performance-hotpaths.instructions.md
Instructions for dotnet/maui, covering performance-critical path rules, hot paths in maui, allocation avoidance, caching and invalidation and collection iteration.
maui collectionview-windows.instructions.md
Instructions for dotnet/maui, covering collectionview — windows (items/ handler), winui listview/itemsrepeater patterns, data source and change notifications, layout configuration and cross-platform consistency.
codex-provider-sync AGENTS.md
Instructions for Dailin521/codex-provider-sync, covering ai / agent operator guide, vnext architecture baseline, goal, choose the interface and safe operating flow.