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/edgeai-for-beginners/agents-mdgit clone --depth 1 https://github.com/microsoft/edgeai-for-beginnersWrote 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.
[](https://agentmods.dev/instructions/microsoft/edgeai-for-beginners/agents-md)<a href="https://agentmods.dev/instructions/microsoft/edgeai-for-beginners/agents-md"><img src="https://agentmods.dev/badge/instructions/microsoft/edgeai-for-beginners/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.04929 | $0.04929 |
| Opus 5 | $0.02465 | $0.02465 |
| Sonnet 5 | $0.00986 | $0.00986 |
| Haiku 4.5 | $0.00493 | $0.00493 |
Grade C, and why
edgeai-for-beginners AGENTS.md scanned grade C with 2 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 3d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf node_modules package-lock.json Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://localhost:<port>/v1/models How it starts
The opening of the file, as written. The whole thing — 695 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Developer Guide for Contributing to EdgeAI for Beginners
This document provides comprehensive information for developers, AI agents, and contributors working with this repository. It covers setup, development workflows, testing, and best practices.
Last Updated: October 30, 2025 | Document Version: 3.0
Table of Contents
- Project Overview
- Repository Structure
- Prerequisites
- Setup Commands
- Development Workflow
- Testing Instructions
- Code Style Guidelines
- Pull Request Guidelines
- Translation System
- Foundry Local Integration
- Build and Deployment
- Common Issues and Troubleshooting
- Additional Resources
- Project-Specific Notes
- Getting Help
Project Overview
EdgeAI for Beginners is a comprehensive educational repository teaching Edge AI development with Small Language Models (SLMs). The course covers EdgeAI fundamentals, model deployment, optimization techniques, and production-ready implementations using Microsoft Foundry Local and various AI frameworks.
Key Technologies:
- Python 3.8+ (primary language for AI/ML samples)
- .NET C# (AI/ML Samples)
- JavaScript/Node.js with Electron (for desktop applications)
- Microsoft Foundry Local SDK
- Microsoft Windows ML
- VSCode AI Toolkit
- OpenAI SDK
- AI Frameworks: LangChain, Semantic Kernel, Chainlit
- Model Optimization: Llama.cpp, Microsoft Olive, OpenVINO, Apple MLX
Repository Type: Educational content repository with 8 modules and 10 comprehensive sample applications
Architecture: Multi-module learning path with practical samples demonstrating edge AI deployment patterns
Repository Structure
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.
- 3d ago First seen · 695 lines · 4,929 tokens per session scan C 56f518d83480
edgeai-for-beginners AGENTS.md is an instructions file published in the GitHub repository microsoft/edgeai-for-beginners (1,683 stars, last pushed 9d ago), licensed MIT. It adds 4,929 tokens to every session, about $0.0246 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
claude-cookbooks CLAUDE.md
Claude Code instructions for anthropics/claude-cookbooks, covering claude cookbooks, quick start, install dependencies, install pre-commit hooks and set up api key.
Generative-AI-for-beginners-dotnet AGENTS.md
AGENTS.md instructions for microsoft/Generative-AI-for-beginners-dotnet, covering agents.md, project overview, architecture, project structure and setup commands.
Generative-AI-for-beginners-dotnet copilot-instructions.md
Copilot instructions for microsoft/Generative-AI-for-beginners-dotnet, covering copilot instructions for generative-ai-for-beginners-dotnet, project purpose & structure, architecture & patterns, developer workflows and code standards & best practices.
AI-fundamentals AGENTS.md
AGENTS.md instructions for ForceInjection/AI-fundamentals, covering 项目概览与工具使用说明 and 1 核心技术模块.
quarkus-workshop-langchain4j AGENTS.md
Instructions for quarkusio/quarkus-workshop-langchain4j, covering agents.md, project overview, technology stack, project structure and building and running.
LLM-dev-demo AGENTS.md
Instructions for A3RDLab/LLM-dev-demo, covering agents.md, 仓库性质, 环境与密钥约定, 依赖管理 and 常用命令.