ai-dev-gallery adding-model-definitions.instructions.md

Repository instructions for editing model and API definition files in AIDevGallery, a Microsoft project that showcases AI models and Windows AI APIs. They describe the JSON files, required fields, and review checks.

In plain words
What is it for?
Use them when reviewing or updating model groups, model details, hardware requirements, licenses, prompt templates, or Windows AI API definitions.
Why use it?
They reduce mistakes when adding or changing model entries by making the file structure and required information explicit.

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

Made for: GitHub Copilot.

Per session 544 This file is loaded in full into every session.
When invoked 544 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 $0.00544 $0.00544
Opus 5 $0.00272 $0.00272
Sonnet 5 $0.00109 $0.00109
Haiku 4.5 $0.00054 $0.00054

Measured 2d ago against content hash b370571a6b3a, 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-model-definitions.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-model-definitions.instructions.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Model and API Definition Instructions

When reviewing or modifying definition files in AIDevGallery/Samples/Definitions/:

.modelgroup.json - Model Group Definition

Used for organizing model families with display ordering. Each file contains one or more model groups:

{
  "GroupName": {
    "Id": "guid",
    "Name": "Display Name",
    "Icon": "\uE8BD",
    "Order": 1,
    "Models": {
      "FamilyName": {
        "Id": "slug",
        "Name": "Family Display Name",
        "Description": "...",
        "DocsUrl": "https://...",
        "ReadmeUrl": "https://...",
        "Models": {
          "VariationName": {
            "Id": "guid",
            "Name": "Model Name GPU",
            "Url": "https://huggingface.co/org/model/tree/main/variant",
            "HardwareAccelerator": "GPU",
            "Size": 1234567890,
            "License": "mit",
            "PromptTemplate": "Phi3"
          }
        }
      }
    }
  }
}

Key Fields

  • Individual Model (required): Id (GUID), Url, HardwareAccelerator, License
  • Language Models: have PromptTemplate referencing promptTemplates.json
  • HardwareAccelerator values: "CPU", "GPU", "NPU", or array

apis.json - Windows AI APIs

Located at Definitions/WcrApis/apis.json:

{
  "WCRAPIs": {
    "Id": "guid",
    "Name": "Windows AI APIs",
    "Icon": "\uF4A5",
    "Apis": {
      "ApiName": {
        "Id": "guid",
        "Name": "API Display Name",
        "Description": "...",
        "Icon": "icon.svg",
        "IconGlyph": "\uE8F2",
        "ReadmeUrl": "https://...",
        "License": "ms-pl",
        "Category": "Category Name"
      }
    }
  }
}

Code Review Checks

  • JSON structure matches expected schema
  • All GUIDs are unique across all definition files
  • HardwareAccelerator matches model requirements
  • Language models have valid PromptTemplate
  • JSON is valid (no trailing commas, proper escaping)
  • Icons reference existing files in Assets/ModelIcons/

Read the full file on GitHub · 83 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 · 83 lines · 544 tokens per session scan A b370571a6b3a

Subscribe to this mod's changes

ai-dev-gallery adding-model-definitions.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 544 tokens to every session, about $0.0027 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.