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

A set of rules for building samples in Microsoft AI Dev Gallery, an application that demonstrates AI features. It defines the required class structure and loading and cleanup steps for each sample.

In plain words
What is it for?
Use it when reviewing or creating AI Dev Gallery samples, especially examples using language models, Windows ML, or shared model and asset settings.
Why use it?
It prevents sample code from missing the conventions the gallery needs to load, display, and finish examples correctly. It also clarifies how language-model samples should be initialized.

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-samples
Clone the repo
git clone --depth 1 https://github.com/microsoft/ai-dev-gallery

Made for: GitHub Copilot.

Per session 1,034 This file is loaded in full into every session.
When invoked 1,034 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 $0.01034 $0.01034
Opus 5 $0.00517 $0.00517
Sonnet 5 $0.00207 $0.00207
Haiku 4.5 $0.00103 $0.00103

Measured yesterday against content hash f65b80b594be, 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-samples.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 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.

.github/instructions/adding-samples.instructions.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sample Implementation Instructions

When reviewing or creating sample code in AIDevGallery/Samples/:

Required Class Structure

Every sample MUST:

  1. Inherit from BaseSamplePage
  2. Have the [GallerySample] attribute with required properties
  3. Override LoadModelAsync(SampleNavigationParameters) or LoadModelAsync(MultiModelSampleNavigationParameters)
  4. Register cleanup in constructor via this.Unloaded += (s, e) => CleanUp();
  5. Call sampleParams.NotifyCompletion() when model is ready

[GallerySample] Attribute

Required properties:

  • Name: Display name
  • Model1Types: Array of ModelType values
  • Id: Unique GUID string
  • Icon: Segoe MDL2 glyph code

Optional properties:

  • Scenario: Reference a ScenarioType from scenarios.json
  • Model2Types: For dual-model samples
  • NugetPackageReferences: Required packages
  • SharedCode: Array of SharedCodeEnum values
  • AssetFilenames: Asset files needed by the sample

Language Model Samples (IChatClient)

For samples using language models (LLMs):

protected override async Task LoadModelAsync(SampleNavigationParameters sampleParams)
{
    try
    {
        chatClient = await sampleParams.GetIChatClientAsync();
    }
    catch (Exception ex)
    {
        ShowException(ex);
    }

    sampleParams.NotifyCompletion();
}

Windows ML

For samples using ONNX models with Windows ML / ONNX Runtime:

Initialization Flow

  1. Ensure certified EPs - Install/register hardware acceleration packages (DML, QNN, etc.)
  2. Create SessionOptions - Call RegisterOrtExtensions() for additional operators
  3. Honor WinMlSampleOptions - Use Policy for auto-selection or EpName/DeviceType for specific EP
  4. Create InferenceSession - Optionally use compiled model for faster subsequent runs
  5. Call NotifyCompletion - Hide loading spinner when ready

LoadModelAsync Pattern

protected override async Task LoadModelAsync(SampleNavigationParameters sampleParams)
{
    try
    {
        await InitializeModelAsync(sampleParams.ModelPath, sampleParams.WinMlSampleOptions);
    }
    catch (Exception ex)
    {
        ShowException(ex, "Failed to load model.");
    }

    sampleParams.NotifyCompletion();
}

Read the full file on GitHub · 172 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. yesterday First seen · 172 lines · 1,034 tokens per session scan A f65b80b594be

Subscribe to this mod's changes

ai-dev-gallery adding-samples.instructions.md is an instructions file published in the GitHub repository microsoft/ai-dev-gallery (1,498 stars, last pushed 12d ago), licensed MIT. It adds 1,034 tokens to every session, about $0.0052 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.