ai-dev-gallery adding-wcrapis.instructions.md

A set of instructions for working on Windows AI API samples in Microsoft's AI Dev Gallery. These APIs provide features such as text recognition and the Phi Silica model on supported Copilot+ PCs.

In plain words
What is it for?
Use it when reviewing or changing WCRAPIs samples, including readiness checks, limited-access features, model types, and security practices.
Why use it?
It helps developers handle feature availability correctly and avoid exposing restricted-access tokens in source code.

Instructions file for GitHub Copilot

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.

agentmods
npx agentmods add instructions/microsoft/ai-dev-gallery/adding-wcrapis
Clone the repo
git clone --depth 1 https://github.com/microsoft/ai-dev-gallery

Made for: GitHub Copilot.

Per session 738 This file is loaded in full into every session.
When invoked 738 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00738 $0.00738
Opus 5 $0.00369 $0.00369
Sonnet 5 $0.00148 $0.00148
Haiku 4.5 $0.00074 $0.00074

Measured 2d ago against content hash a50fdb9d9f06, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.github/instructions/adding-wcrapis.instructions.md · 93 lines

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 LimitedAccessFeaturesHelper for 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)

Read the full file on GitHub · 93 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. 2d ago First seen · 93 lines · 738 tokens per session scan A a50fdb9d9f06

Subscribe to this mod's changes

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.