How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
CloudflareAGENTS.mdcloudflare/kumo/packages/kumo-figma/AGENTS.md
Generates production-quality Figma components from component-registry.json. Destructive sync: purges and recreates all components per run. Parent: See root AGENTS.md for monorepo context.
CloudflareAGENTS.mdcloudflare/kumo/packages/kumo-figma/src/generators/AGENTS.md
37 component generators creating Figma components from component-registry.json. Registry is source of truth. Parent: See packages/kumo-figma/AGENTS.md for plugin context. Every generator follows this structure: ALL magic numbers and constants MUST live here: Key utilities:
CloudflareAGENTS.mdcloudflare/kumo/packages/kumo-screenshot-worker/AGENTS.md
Cloudflare Worker that uses Puppeteer + Browser Rendering to capture screenshots of Kumo docs pages. Used for visual regression testing. Parent: See root AGENTS.md for monorepo context. Never commit secret values. .dev.vars is gitignored at the root level. All requests require X-API-Key: <API_KEY> header. Returns { results: ScreenshotResult[] } where each result has a base64-encoded image or an error string. Limits: max 50 pages per batch, max 64 KB per css action payload. When captureSections: true, the worker looks for…
CloudflareAGENTS.mdcloudflare/kumo/packages/kumo/src/components/AGENTS.md
39 UI components. Base UI primitives + Tailwind v4 styling. Compound component pattern throughout. Parent: See packages/kumo/AGENTS.md for library context. Each component follows: {name}/{name}.tsx + optional {name}.test.tsx, {name}.browser.test.tsx Every component file MUST export (lint-enforced by enforce-variant-standard): 13 components use this pattern: Input, Select, Combobox auto-wrap with Field when label prop provided:
MicrosoftAGENTS.mdmicrosoft/apm/templates/hello-world/AGENTS.md
You are a helpful AI assistant focused on clean, maintainable code and best practices. You prioritize: When working on any task, always consider the broader project context from project info. This is a demonstration project showcasing APM (Agent Primitives Manager) primitives compilation into AGENTS.md format. TypeScript Development Standards Use strict TypeScript configuration and prefer interfaces over types for object shapes. Implement proper generic constraints and avoid any type. Code Structure - Use barrel exports for clean imports - Implement proper…
MongoDBAGENTS.mdmongodb/mongoid/AGENTS.md
Mongoid is a Ruby Object-Document Mapper (ODM) framework for MongoDB. Mongoid allows developers to define their data models using Ruby classes, and it handles the mapping between these classes and the underlying MongoDB collections. It is built on top of the MongoDB Ruby driver, and is intended to be a (mostly) drop-in replacement for ActiveRecord in Ruby on Rails applications. The project targets Ruby 2.7+. Do not use syntax or stdlib features unavailable in Ruby 2.7. Tests require a running…
NVIDIAAGENTS.mdNVIDIA/k8s-device-plugin/AGENTS.md
Guidance for AI coding agents working in this repository. Human contributors should also read CONTRIBUTING.md. The NVIDIA device plugin for Kubernetes is a DaemonSet that advertises NVIDIA GPUs to the kubelet through the Kubernetes device plugin framework, so that the kubelet can allocate those GPUs to containers. It also tracks GPU health. As of v0.15.0 this repository additionally holds the implementation of GPU Feature Discovery (GFD), which labels nodes with GPU properties. The repository builds four binaries, each with its…
MicrosoftAGENTS.mdmicrosoft/PhiCookBook/AGENTS.md
PhiCookBook is a comprehensive cookbook repository containing hands-on examples, tutorials, and documentation for working with Microsoft's Phi family of Small Language Models (SLMs). The repository demonstrates various use cases including inference, fine-tuning, quantization, RAG implementations, and multimodal applications across different platforms and frameworks. Key Technologies: - Languages: Python, C#/.NET, JavaScript/Node.js - Frameworks: ONNX Runtime, PyTorch, Transformers, MLX, OpenVINO, Semantic Kernel - Platforms: Microsoft Foundry, GitHub Models, Hugging Face, Ollama - Model Types: Phi-3, Phi-3.5, Phi-4 (text, vision, multimodal, reasoning variants)
MicrosoftAGENTS.mdmicrosoft/PhiCookBook/translations/ar/AGENTS.md
PhiCookBook هو مستودع شامل للوصفات يحتوي على أمثلة تطبيقية، ودروس تعليمية، وتوثيقات للعمل مع عائلة Phi من نماذج اللغة الصغيرة (SLMs) التابعة لمايكروسوفت. يعرض المستودع استخدامات متنوعة تشمل الاستدلال، والتخصيص الدقيق، والتكميم، وتنفيذ توليد معزز الاسترجاع (RAG)، والتطبيقات متعددة الوسائط عبر منصات وأطر عمل مختلفة. التقنيات الرئيسية: - اللغات: بايثون، C#/.NET، جافاسكريبت/Node.js - الأُطُر: ONNX Runtime، بايتورش، Transformers، MLX، OpenVINO، Semantic Kernel - المنصات: Microsoft Foundry، نماذج GitHub، Hugging Face، Ollama - أنواع النماذج: Phi-3، Phi-3.5، Phi-4 (نص، رؤية، متعدد…
MicrosoftAGENTS.mdmicrosoft/PhiCookBook/translations/bg/AGENTS.md
PhiCookBook е изчерпателно хранилище с готварски рецепти, съдържащо практически примери, уроци и документация за работа със семейството Phi на Microsoft от Малки Езикови Модели (SLMs). Хранилището демонстрира различни случаи на използване, включително извеждане на изводи, фино настройване, квантуване, реализации на RAG и мултимодални приложения на различни платформи и рамки. Ключови технологии: - Езици: Python, C#/.NET, JavaScript/Node.js - Рамки: ONNX Runtime, PyTorch, Transformers, MLX, OpenVINO, Semantic Kernel - Платформи: Microsoft Foundry, GitHub Models, Hugging Face, Ollama - Видове модели: Phi-3, Phi-3.5,…
MicrosoftAGENTS.mdmicrosoft/PhiCookBook/translations/bn/AGENTS.md
PhiCookBook হলো একটি সমগ্র কুকবুক রেপোজিটরি যা Microsoft এর Phi পরিবারের ছোট ভাষা মডেল (SLM) এর সাথে কাজ করার জন্য হাতে-কলমে উদাহরণ, টিউটোরিয়াল এবং ডকুমেন্টেশন ধারণ করে। রেপোজিটরিটি বিভিন্ন ব্যবহার ক্ষেত্র প্রদর্শন করে যেমন ইনফারেন্স, ফাইন-টিউনিং, কোয়ান্টাইজেশন, RAG ইমপ্লিমেন্টেশন, এবং বিভিন্ন প্ল্যাটফর্ম ও ফ্রেমওয়ার্ক জুড়ে মাল্টিমোডাল অ্যাপ্লিকেশন। মূল প্রযুক্তি: - ভাষা: Python, C#/.NET, JavaScript/Node.js - ফ্রেমওয়ার্ক: ONNX Runtime, PyTorch, Transformers, MLX, OpenVINO, Semantic Kernel - প্ল্যাটফর্ম: Microsoft Foundry, GitHub Models, Hugging Face, Ollama - মডেল টাইপ: Phi-3, Phi-3.5, Phi-4 (টেক্সট,…
MicrosoftAGENTS.mdmicrosoft/PhiCookBook/translations/cs/AGENTS.md
PhiCookBook je komplexní repozitář kuchařek obsahující praktické příklady, návody a dokumentaci pro práci s rodinou malých jazykových modelů (SLM) od Microsoftu Phi. Repozitář demonstruje různé případy použití včetně inferencí, doladění, kvantizace, implementací RAG a multimodálních aplikací na různých platformách a rámcích. Klíčové technologie: - Jazyky: Python, C#/.NET, JavaScript/Node.js - Rámce: ONNX Runtime, PyTorch, Transformers, MLX, OpenVINO, Semantic Kernel - Platformy: Microsoft Foundry, GitHub Models, Hugging Face, Ollama - Typy modelů: Phi-3, Phi-3.5, Phi-4 (textové, vizuální, multimodální, varianty pro uvažování) Struktura…
MicrosoftAGENTS.mdmicrosoft/PhiCookBook/translations/da/AGENTS.md
PhiCookBook er et omfattende opskriftsbibliotek, der indeholder praktiske eksempler, vejledninger og dokumentation til arbejde med Microsofts Phi-familie af Små Sprogmodeller (SLMs). Repositoriet demonstrerer forskellige brugstilfælde, herunder inferens, finjustering, kvantisering, RAG-implementeringer og multimodale applikationer på tværs af forskellige platforme og frameworks. Nøgleteknologier: - Sprog: Python, C#/.NET, JavaScript/Node.js - Frameworks: ONNX Runtime, PyTorch, Transformers, MLX, OpenVINO, Semantic Kernel - Platforme: Microsoft Foundry, GitHub Models, Hugging Face, Ollama - Modeltyper: Phi-3, Phi-3.5, Phi-4 (tekst, vision, multimodal, ræsonneringsvarianter) Repositoriumsstruktur: - /code/ - Arbejdende kodeeksempler…
MicrosoftAGENTS.mdmicrosoft/PhiCookBook/translations/de/AGENTS.md
PhiCookBook ist ein umfassendes Repository für Kochbücher mit praxisnahen Beispielen, Tutorials und Dokumentationen für die Arbeit mit der Phi-Familie von Small Language Models (SLMs) von Microsoft. Das Repository demonstriert verschiedene Anwendungsfälle, darunter Inferenz, Feinabstimmung, Quantisierung, RAG-Implementierungen und multimodale Anwendungen auf unterschiedlichen Plattformen und Frameworks. Wichtige Technologien: - Programmiersprachen: Python, C#/.NET, JavaScript/Node.js - Frameworks: ONNX Runtime, PyTorch, Transformers, MLX, OpenVINO, Semantic Kernel - Plattformen: Microsoft Foundry, GitHub Models, Hugging Face, Ollama - Modelltypen: Phi-3, Phi-3.5, Phi-4 (Text-, Vision-, multimodale und Reasoning-Varianten)
MicrosoftAGENTS.mdmicrosoft/PhiCookBook/translations/el/AGENTS.md
Το PhiCookBook είναι ένα ολοκληρωμένο αποθετήριο συνταγών που περιέχει πρακτικά παραδείγματα, μαθήματα και τεκμηρίωση για τη δουλειά με την οικογένεια Small Language Models (SLMs) της Microsoft Phi. Το αποθετήριο επιδεικνύει διάφορες περιπτώσεις χρήσης, συμπεριλαμβανομένης της εκτέλεσης συμπερασμάτων, της βελτιστοποίησης, της κβαντοποίησης, των υλοποιήσεων RAG και των πολυτροπικών εφαρμογών σε διαφορετικές πλατφόρμες και πλαίσια εργασίας. Βασικές Τεχνολογίες: - Γλώσσες: Python, C#/.NET, JavaScript/Node.js - Πλαίσια εργασίας: ONNX Runtime, PyTorch, Transformers, MLX, OpenVINO, Semantic Kernel - Πλατφόρμες: Microsoft Foundry, GitHub Models, Hugging Face,…
MicrosoftAGENTS.mdmicrosoft/PhiCookBook/translations/en/AGENTS.md
PhiCookBook is a comprehensive cookbook repository containing hands-on examples, tutorials, and documentation for working with Microsoft's Phi family of Small Language Models (SLMs). The repository demonstrates various use cases including inference, fine-tuning, quantization, RAG implementations, and multimodal applications across different platforms and frameworks. Key Technologies: - Languages: Python, C#/.NET, JavaScript/Node.js - Frameworks: ONNX Runtime, PyTorch, Transformers, MLX, OpenVINO, Semantic Kernel - Platforms: Microsoft Foundry, GitHub Models, Hugging Face, Ollama - Model Types: Phi-3, Phi-3.5, Phi-4 (text, vision, multimodal, reasoning variants)
MicrosoftAGENTS.mdmicrosoft/PhiCookBook/translations/es/AGENTS.md
PhiCookBook es un repositorio completo de libros de cocina que contiene ejemplos prácticos, tutoriales y documentación para trabajar con la familia Phi de Modelos de Lenguaje Pequeños (SLMs) de Microsoft. El repositorio demuestra varios casos de uso incluyendo inferencia, ajuste fino, cuantización, implementaciones RAG y aplicaciones multimodales en diferentes plataformas y marcos. Tecnologías Clave: - Lenguajes: Python, C#/.NET, JavaScript/Node.js - Frameworks: ONNX Runtime, PyTorch, Transformers, MLX, OpenVINO, Semantic Kernel - Plataformas: Microsoft Foundry, GitHub Models, Hugging Face, Ollama - Tipos…
MicrosoftAGENTS.mdmicrosoft/PhiCookBook/translations/et/AGENTS.md
PhiCookBook on põhjalik retseptide hoidla, mis sisaldab praktilisi näiteid, juhendeid ja dokumentatsiooni Microsofti Phi väikeste keelemudelite (SLM-id) kasutamiseks. Hoidla demonstreerib erinevaid kasutusjuhtumeid, sealhulgas järeldamist, peenhäälestamist, kvantiseerimist, RAG-teostusi ja multimodaalseid rakendusi erinevatel platvormidel ja raamistikudel. Peamised tehnoloogiad: - Keeled: Python, C#/.NET, JavaScript/Node.js - Raamistikud: ONNX Runtime, PyTorch, Transformers, MLX, OpenVINO, Semantic Kernel - Platvormid: Microsoft Foundry, GitHub Models, Hugging Face, Ollama - Mudelitüübid: Phi-3, Phi-3.5, Phi-4 (teksti-, nägemis-, multimodaalsed ja järeldusvariandid) Hoidla struktuur: - /code/ - Töökoodinäited ja prooviteostused - /md/…
MicrosoftAGENTS.mdmicrosoft/PhiCookBook/translations/fa/AGENTS.md
PhiCookBook یک مخزن جامع کتاب آشپزی است که شامل نمونههای عملی، آموزشها و مستندات برای کار با خانواده مدلهای زبانی کوچک (SLM) مایکروسافت به نام Phi میباشد. این مخزن موارد استفاده متنوعی از جمله استنتاج، تنظیم دقیق، کمّیسازی، پیادهسازیهای RAG و برنامههای چندرسانهای در پلتفرمها و چارچوبهای مختلف را نشان میدهد. فناوریهای کلیدی: - زبانها: Python, C#/.NET, JavaScript/Node.js - چارچوبها: ONNX Runtime, PyTorch, Transformers, MLX, OpenVINO, Semantic Kernel - پلتفرمها: Microsoft Foundry, GitHub Models, Hugging Face, Ollama - نوع مدلها:…
MicrosoftAGENTS.mdmicrosoft/PhiCookBook/translations/fi/AGENTS.md
PhiCookBook on kattava reseptikirjavarasto, joka sisältää käytännön esimerkkejä, tutoriaaleja ja dokumentaatiota Microsoftin Phi-pienen kielimalliperheen (SLM) käyttöön. Varasto esittelee erilaisia käyttötapauksia, kuten päättelyä, hienosäätöä, kvantisointia, RAG-toteutuksia ja multimodaalisia sovelluksia eri alustoilla ja kehyksissä. Keskeiset teknologiat: - Kielet: Python, C#/.NET, JavaScript/Node.js - Kehykset: ONNX Runtime, PyTorch, Transformers, MLX, OpenVINO, Semantic Kernel - Alustat: Microsoft Foundry, GitHub Models, Hugging Face, Ollama - Mallityypit: Phi-3, Phi-3.5, Phi-4 (teksti-, näkö-, multimodaaliset ja päättelyvariantit) Varaston rakenne: - /code/ - Toimivia koodiesimerkkejä ja näytetoteutuksia - /md/ -…
An open format for instructions to coding agents, read by Codex, Cursor and others. Think of it as a README written for agents.
At the repository root, with more specific files in subdirectories. Agents read the one closest to the file they're editing.
Setup and test commands, code style, and the rules a new contributor would need to know.
Claude Code reads CLAUDE.md. A one-line CLAUDE.md that points at AGENTS.md covers both.
