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-samplesgit 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 | $0.01034 | $0.01034 |
| Opus 5 | $0.00517 | $0.00517 |
| Sonnet 5 | $0.00207 | $0.00207 |
| Haiku 4.5 | $0.00103 | $0.00103 |
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.
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:
- Inherit from
BaseSamplePage - Have the
[GallerySample]attribute with required properties - Override
LoadModelAsync(SampleNavigationParameters)orLoadModelAsync(MultiModelSampleNavigationParameters) - Register cleanup in constructor via
this.Unloaded += (s, e) => CleanUp(); - Call
sampleParams.NotifyCompletion()when model is ready
[GallerySample] Attribute
Required properties:
Name: Display nameModel1Types: Array ofModelTypevaluesId: Unique GUID stringIcon: Segoe MDL2 glyph code
Optional properties:
Scenario: Reference aScenarioTypefromscenarios.jsonModel2Types: For dual-model samplesNugetPackageReferences: Required packagesSharedCode: Array ofSharedCodeEnumvaluesAssetFilenames: 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
- Ensure certified EPs - Install/register hardware acceleration packages (DML, QNN, etc.)
- Create SessionOptions - Call
RegisterOrtExtensions()for additional operators - Honor WinMlSampleOptions - Use
Policyfor auto-selection orEpName/DeviceTypefor specific EP - Create InferenceSession - Optionally use compiled model for faster subsequent runs
- 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();
}
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 First seen · 172 lines · 1,034 tokens per session scan A f65b80b594be
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.
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.