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-foundry/foundry-local-lab/agents-mdgit clone --depth 1 https://github.com/microsoft-foundry/Foundry-Local-LabWhat 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 | $0.02289 | $0.02289 |
| Opus 5 | $0.01144 | $0.01144 |
| Sonnet 5 | $0.00458 | $0.00458 |
| Haiku 4.5 | $0.00229 | $0.00229 |
Grade A, and why
Foundry-Local-Lab 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 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.
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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coding Agent Instructions
This file provides context for AI coding agents (GitHub Copilot, Copilot Workspace, Codex, etc.) working in this repository.
Project Overview
This is a hands-on workshop for building AI applications with Foundry Local — a lightweight runtime that downloads, manages, and serves language models entirely on-device via an OpenAI-compatible API. The workshop includes step-by-step lab guides and runnable code samples in Python, JavaScript, and C#.
Repository Structure
├── labs/ # Markdown lab guides (Parts 1–13)
├── python/ # Python code samples (Parts 2–6, 8–9, 11)
├── javascript/ # JavaScript/Node.js code samples (Parts 2–6, 8–9, 11)
├── csharp/ # C# / .NET 9 code samples (Parts 2–6, 8–9, 11)
├── zava-creative-writer-local/ # Part 7 capstone app + Part 12 UI (Python/JS/C#)
│ ├── ui/ # Shared browser UI (vanilla HTML/CSS/JS)
│ └── src/
│ ├── api/ # Python FastAPI multi-agent service (serves UI)
│ ├── javascript/ # Node.js CLI + HTTP server (server.mjs)
│ ├── csharp/ # .NET console multi-agent app
│ └── csharp-web/ # .NET ASP.NET Core minimal API (serves UI)
├── samples/audio/ # Part 9 sample WAV files + generator script
├── images/ # Diagrams referenced by lab guides
├── README.md # Workshop overview and navigation
├── KNOWN-ISSUES.md # Known issues and workarounds
├── package.json # Root devDependency (mermaid-cli for diagrams)
└── AGENTS.md # This file
Language & Framework Details
Python
- Location:
python/,zava-creative-writer-local/src/api/ - Dependencies:
python/requirements.txt,zava-creative-writer-local/src/api/requirements.txt - Key packages:
foundry-local-sdk,openai,agent-framework-foundry-local,fastapi,uvicorn - Min version: Python 3.9+
- Run:
cd python && pip install -r requirements.txt && python foundry-local.py
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 · 154 lines · 2,289 tokens per session scan A 090fb7836d45
Foundry-Local-Lab AGENTS.md is an instructions file published in the GitHub repository microsoft-foundry/Foundry-Local-Lab (105 stars, last pushed 4mo ago), licensed MIT. It adds 2,289 tokens to every session, about $0.0114 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
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.
eve AGENTS.md
Instructions for vercel/eve, covering agents.md, about eve, repository layout, git workflow and commands.
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.
crust AGENTS.md
Instructions for chenxin-yan/crust, covering tests, documentation, changesets, agent skills and issue tracker.
Course_Weight-Optimizer AGENTS.md
Instructions for rtb-1005/Course_Weight-Optimizer, covering course weight optimizer — agent 指引, 北极星条款（最高优先级）, 项目目标, 部署 and 核心模式：agent 作为信息中间人.
ab900 CLAUDE.md
Instructions for timothywarner-org/ab900, covering claude.md, repository purpose, architecture, commands and 2. non-ascii punctuation -- must return zero.