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-scenariosgit 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 | $0.00720 | $0.00720 |
| Opus 5 | $0.00360 | $0.00360 |
| Sonnet 5 | $0.00144 | $0.00144 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
ai-dev-gallery adding-scenarios.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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scenario and Prompt Template Instructions
When reviewing or modifying scenarios.json or promptTemplates.json:
IMPORTANT: Source Generator Embedded Files
Both scenarios.json and promptTemplates.json are embedded at build time by Roslyn source generators. Changes to these files require a full rebuild to take effect - they are NOT loaded dynamically at runtime.
scenarios.json Structure
{
"CategoryName": {
"Name": "Category Display Name",
"Icon": "\uE8BD",
"Description": "Category description for the UI",
"Scenarios": {
"ScenarioName": {
"Name": "Scenario Display Name",
"Description": "What this scenario does",
"Instructions": "User-facing instructions for using this sample",
"Id": "kebab-case-unique-id",
"Icon": "\uE8D4"
}
}
}
}
Required Scenario Fields
Name: Display name shown in UIId: Unique kebab-case identifier (e.g.,"summarize-text")
Optional Fields
Description: Brief description of the scenarioInstructions: User instructions for the sample UIIcon: Segoe MDL2 glyph code (e.g.,"\uE8BD")
Usage in Samples
The ScenarioType enum is auto-generated from scenarios.json. Reference in [GallerySample]:
[GallerySample(
Scenario = ScenarioType.TextSummarizeText, // CategoryScenarioName format
...
)]
The naming pattern is {Category}{ScenarioName} in PascalCase.
promptTemplates.json Structure
{
"TemplateName": {
"system": "<|system|>\n{{CONTENT}}<|end|>\n",
"user": "<|user|>\n{{CONTENT}}<|end|>\n",
"assistant": "<|assistant|>\n{{CONTENT}}<|end|>\n",
"stop": ["<|end|>", "<|user|>"]
}
}
Required Prompt Template Fields
user: Template for user messages with{{CONTENT}}placeholderstop: Array of stop sequences
Optional Prompt Template Fields
system: Template for system prompt with{{CONTENT}}placeholderassistant: Template for assistant responses with{{CONTENT}}placeholder
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 · 103 lines · 720 tokens per session scan A 4d921837ee1b
ai-dev-gallery adding-scenarios.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 720 tokens to every session, about $0.0036 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 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.
mcp-dotnet-samples AGENTS.md
Instructions for microsoft/mcp-dotnet-samples, covering agents.md - mcp .net samples, project overview, project structure and architecture, repository organization and sample components.
DevoxxGenieIDEAPlugin GEMINI.md
Instructions for devoxx/DevoxxGenieIDEAPlugin, a project described as: DevoxxGenie is an agentic plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code. Latest version now also supports Spec Driven Development…
moorestech AGENTS.md
AGENTS.md instructions for moorestech/moorestech, covering コーディングの指針, qa（必須）, 互換性とパフォーマンス, 既知の制約（設計上の割り切り） and regionの活用.
easy-vibe AGENTS.md
AGENTS.md instructions for datawhalechina/easy-vibe, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.