model-mondays AGENTS.md

Repository-specific instructions for contributors and coding agents working on Microsoft's Model Mondays project, an educational livestream and resource repository about AI models and Microsoft Foundry.

In plain words
What is it for?
Use them when editing episode data, speaker profiles, topics, resources, documentation, or other Model Mondays content.
Why use it?
They explain the repository's purpose, file organization, naming conventions, and project guidance in one place.

Instructions file for CodexOpenCode

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/model-mondays/agents-md
Clone the repo
git clone --depth 1 https://github.com/microsoft/model-mondays

Made for: Codex, OpenCode.

Per session 3,385 This file is loaded in full into every session.
When invoked 3,385 The same file β€” 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 $0.03385 $0.03385
Opus 5 $0.01692 $0.01692
Sonnet 5 $0.00677 $0.00677
Haiku 4.5 $0.00338 $0.00338

Measured 2d ago against content hash ac9954ccae0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

model-mondays AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories β€” prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency β€” 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.

AGENTS.md Β· 403 lines

How it starts

The opening of the file, as written. The whole thing β€” 403 lines β€” stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guidelines for Model Mondays Repository

Last Updated: February 11, 2026
Repository: microsoft/model-mondays
Branch: 2026/s3-schedule-refresh

Custom Agent Available: See .github/copilot-agent.json for the Model Mondays Maintainer agent configuration and .github/skills/ for reusable workflow skills.

Maintainer Guide: See .github/GUIDANCE.md for comprehensive maintainer guidance on using the agent, skills, and validation tools.


πŸ“‹ Repository Overview

This repository hosts the Model Mondays livestream series and Foundry Fridays AMA sessions, providing educational content about AI models, Microsoft Foundry, and related technologies.

Content Structure

model-mondays/
β”œβ”€β”€ data/                           # JSON metadata files
β”‚   β”œβ”€β”€ amas.json                   # AMA session metadata
β”‚   β”œβ”€β”€ livestreams.json            # Episode metadata
β”‚   β”œβ”€β”€ seasons.json                # Season information
β”‚   β”œβ”€β”€ speakers.json               # Speaker profiles
β”‚   β”œβ”€β”€ topics.json                 # Topic taxonomy
β”‚   └── resources.json              # Learning resources
β”œβ”€β”€ docs/
β”‚   β”œβ”€β”€ model-mondays/              # Livestream episode posts (24 files)
β”‚   β”œβ”€β”€ foundry-fridays/            # AMA session posts (34 files + README)
β”‚   β”œβ”€β”€ customer-stories/           # Customer implementations
β”‚   └── assets/                     # All images and banners
β”‚       β”œβ”€β”€ model-mondays/          # Livestream banners (SX-EY.png)
β”‚       β”œβ”€β”€ foundry-fridays/        # AMA banners (SX-EY-AMA.png)
β”‚       β”œβ”€β”€ customer-stories/       # Customer story banners (SX-EY.png)
β”‚       β”œβ”€β”€ people/                 # Speaker headshots
β”‚       └── misc/                   # General assets
β”œβ”€β”€ .2025/                          # Archived historical content
└── README.md                       # Main landing page

🎯 Key Conventions

File Naming Patterns

  1. Episode Posts: yyyy-mm-dd-sXX-eYY.md
    • Example: 2025-12-01-s03-e01.md (Season 3, Episode 1, aired Dec 1, 2025)

Read the full file on GitHub Β· 403 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 Β· 403 lines Β· 3,385 tokens per session scan A ac9954ccae0b

Subscribe to this mod's changes

model-mondays AGENTS.md is an instructions file published in the GitHub repository microsoft/model-mondays (283 stars, last pushed 8d ago), licensed MIT. It adds 3,385 tokens to every session, about $0.0169 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.

Related

Other instructions, from other repositories

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.

microsoft/Generative-AI-for-beginners-dotnet Β· 5,226 tokens

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.

microsoft/Generative-AI-for-beginners-dotnet Β· 1,390 tokens

AppStore CLAUDE.md

Instructions for wangjianqi/AppStore, covering claude.md, project overview, repository structure, working with this repo and content editing.

wangjianqi/AppStore Β· 516 tokens

how2claude CLAUDE.md

Instructions for cresslank/how2claude, covering about this project, about me, what i want claude to do, what i don't want claude to do and project structure.

cresslank/how2claude Β· 437 tokens

vibe-coding-prompt-template backend.instructions.md

Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.

KhazP/vibe-coding-prompt-template Β· 139 tokens

Tutorial_AwesomeModernCPP AGENTS.md

Instructions for Awesome-Embedded-Learning-Studio/Tutorial_AwesomeModernCPP, covering agents.md, θΏ™ζ˜―δ»€δΉˆ, ι€šη”¨ essentials(ζ‰€ζœ‰ agent εΏ…θ―») and δ½ ζ₯εšδ»€δΉˆ?(ζŒ‰εœΊζ™―θ·―η”±).

Awesome-Embedded-Learning-Studio/Tutorial_AwesomeModernCPP Β· 778 tokens