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-agents-for-beginners/agents-mdgit clone --depth 1 https://github.com/microsoft/ai-agents-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/ai-agents-for-beginners/agents-md)<a href="https://agentmods.dev/instructions/microsoft/ai-agents-for-beginners/agents-md"><img src="https://agentmods.dev/badge/instructions/microsoft/ai-agents-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 | $0.02488 | $0.02488 |
| Opus 5 | $0.01244 | $0.01244 |
| Sonnet 5 | $0.00498 | $0.00498 |
| Haiku 4.5 | $0.00249 | $0.00249 |
Grade A, and why
ai-agents-for-beginners AGENTS.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 4d 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 — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Overview
This repository contains "AI Agents for Beginners" - a comprehensive educational course teaching everything needed to build AI Agents. The course consists of 18 lessons (numbered 00-18) covering fundamentals, design patterns, frameworks, production deployment, local/on-device agents, and security of AI agents.
Key Technologies:
- Python 3.12+
- Jupyter Notebooks for interactive learning
- AI Frameworks: Microsoft Agent Framework (MAF)
- Azure AI Services: Microsoft Foundry, Microsoft Foundry Agent Service V2
Architecture:
- Lesson-based structure (00-15+ directories)
- Each lesson contains: README documentation, code samples (Jupyter notebooks), and images
- Multi-language support via automated translation system
- One Python notebook per lesson using Microsoft Agent Framework
Setup Commands
Prerequisites
- Python 3.12 or higher
- Azure subscription (for Microsoft Foundry)
- Azure CLI installed and authenticated (
az login)
Initial Setup
-
Clone or fork the repository:
gh repo fork microsoft/ai-agents-for-beginners --clone # OR git clone https://github.com/microsoft/ai-agents-for-beginners.git cd ai-agents-for-beginners -
Create and activate Python virtual environment:
python3 -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate -
Install dependencies:
pip install -r requirements.txt -
Set up environment variables:
cp .env.example .env # Edit .env with your API keys and endpoints
Required Environment Variables
For Microsoft Foundry (Required):
AZURE_AI_PROJECT_ENDPOINT- Microsoft Foundry project endpointAZURE_AI_MODEL_DEPLOYMENT_NAME- Model deployment name (e.g., gpt-5-mini)
For Azure AI Search (Lesson 05 - RAG):
AZURE_SEARCH_SERVICE_ENDPOINT- Azure AI Search endpointAZURE_SEARCH_API_KEY- Azure AI Search API key
Authentication: Run az login before running notebooks (uses AzureCliCredential).
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.
- 4d ago First seen · 312 lines · 2,488 tokens per session scan A 5ad43a376e15
ai-agents-for-beginners AGENTS.md is an instructions file published in the GitHub repository microsoft/ai-agents-for-beginners (73,847 stars, last pushed 8d ago), licensed MIT. It adds 2,488 tokens to every session, about $0.0124 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
agents AGENTS.md
Instructions for pertamaxxx/agents, covering agents.md, project overview, repository structure, nested agents.md files and setup.
nexent AGENTS.md
AGENTS.md instructions for ModelEngine-Group/nexent, covering agents, available skills, project overview, developer commands and backend (python 3.11).
turbo-flow CLAUDE.md
Claude Code instructions for marcuspat/turbo-flow, covering claude.md — turbo flow, what this repo is, key files and conventions.
typedai AGENTS.md
Instructions for TrafficGuard/typedai, covering general code standards, clean code style guidelines, example, original code and analysis.
claude-code-safety-net CLAUDE.md
Instructions for waleedkhanbaloch/claude-code-safety-net, covering claude.md, project overview, commands, architecture and code style (typescript).
claude-code-safety-net AGENTS.md
Instructions for waleedkhanbaloch/claude-code-safety-net, covering agent guidelines, commands, pre-commit hooks, commit conventions and code style (typescript).