Generative-AI-for-beginners-dotnet copilot-instructions.md

Generative-AI-for-beginners-dotnet copilot-instructions.md is an instructions file for GitHub Copilot from microsoft/Generative-AI-for-beginners-dotnet. It costs 1,390 tokens per session, scanned A, original, MIT.

Instructions for a hands-on .NET course that teaches generative AI through runnable examples. The course covers lessons, sample applications, translations, and services that keep AI provider calls separate from the rest of the code.

In plain words
What is it for?
Use them when adding or editing course lessons, .NET samples, translations, AI integrations, or developer documentation.
Why use it?
They explain where lessons and examples belong and set conventions that make samples easier to test and adapt to different AI services.

Instructions file for GitHub Copilot

About the project

Generative AI for Beginners .NET is a hands-on course that teaches .NET developers to build applications using generative AI models and related tools. Its lessons use practical samples covering scenarios such as chat, audio transcription, agents, and local AI. The catalogue entries are add-ons associated with the course repository.

microsoft/Generative-AI-for-beginners-dotnet · 3,046 stars · on GitHub

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/generative-ai-for-beginners-dotnet/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/microsoft/Generative-AI-for-beginners-dotnet

Made for: GitHub Copilot.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for Generative-AI-for-beginners-dotnet copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/microsoft/generative-ai-for-beginners-dotnet/copilot-instructions.svg)](https://agentmods.dev/instructions/microsoft/generative-ai-for-beginners-dotnet/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/microsoft/generative-ai-for-beginners-dotnet/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/microsoft/generative-ai-for-beginners-dotnet/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,390 This file is loaded in full into every session.
When invoked 1,390 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 $0.01390 $0.01390
Opus 5 $0.00695 $0.00695
Sonnet 5 $0.00278 $0.00278
Haiku 4.5 $0.00139 $0.00139

Measured 5d ago against content hash ab7f9ef8d02c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Generative-AI-for-beginners-dotnet copilot-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 5d 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/copilot-instructions.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Instructions for Generative-AI-for-beginners-dotnet

Project Purpose & Structure

  • This repo is a hands-on .NET course for Generative AI, focused on real-world, runnable code and live coding.
  • Lessons are organized in numbered folders (01-IntroductionToGenerativeAI/ through 05-ResponsibleAI/), each with a readme.md for documentation.
  • All code samples live in the centralized samples/ directory, organized by category: CoreSamples/, MAF/, AppsWithGenAI/, PracticalSamples/.
  • Key technologies: .NET 10+, Microsoft.Extensions.AI (MEAI), Microsoft Agent Framework, Azure OpenAI, Ollama (local models).
  • Multi-language support: see translations/ for localized docs.

Architecture & Patterns

  • Each lesson folder contains documentation; code samples are in samples/ (e.g., samples/AppsWithGenAI/SpaceAINet/ demonstrates full-stack AI integration).
  • Samples are organized under samples/ by category: CoreSamples/, MAF/, AppsWithGenAI/, PracticalSamples/.
  • AI model calls are always abstracted behind service classes (e.g., SpaceAINet.GameActionProcessor), enabling easy provider swapping and testability.
  • API keys and endpoints are never hardcoded—use user secrets or environment variables (see lesson READMEs for details).
  • For SpaceAINet and similar apps:
    • AI providers (Ollama, Azure OpenAI) are toggled at runtime via key bindings.
    • Game state is sent to the AI model, which returns a JSON action and explanation.
    • Screenshots and FPS toggles are built-in for debugging and demonstration.

Developer Workflows

  • Code Formatting (Required Before Each Commit):
    • Run dotnet format before committing any changes to ensure proper C# code formatting and style
    • Ensure all code builds with dotnet build and passes tests with dotnet test
    • Verify formatting with dotnet format --verify-no-changes if linting is enabled
  • Build & Run:
    • Use standard .NET CLI: dotnet build, dotnet run from the relevant project folder (e.g., cd samples/AppsWithGenAI/SpaceAINet/SpaceAINet.Console).
    • For local AI: ensure Ollama is running and the required model is pulled (e.g., ollama pull phi4-mini).
    • For Azure: set secrets via dotnet user-secrets or Codespaces secrets.
  • Switching AI Providers:
    • Most samples support toggling between local (Ollama) and cloud (Azure OpenAI) models at runtime (see app key bindings and README tables).
  • Codespaces:
    • Dev containers are pre-configured for .NET, Azure, and Ollama workflows. Choose the right container for your use case.
  • Testing:
    • Run sample apps in the samples/ directory to verify model integration and workflow.

Read the full file on GitHub · 88 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. 5d ago First seen · 88 lines · 1,390 tokens per session scan A ab7f9ef8d02c

Subscribe to this mod's changes

Generative-AI-for-beginners-dotnet copilot-instructions.md is an instructions file published in the GitHub repository microsoft/Generative-AI-for-beginners-dotnet (3,046 stars, last pushed 4d ago), licensed MIT. It adds 1,390 tokens to every session, about $0.0069 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.