How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
MicrosoftAGENTS.mdmicrosoft/vscode/AGENTS.md
This file provides instructions for AI coding agents working with the VS Code codebase. For detailed project overview, architecture, coding guidelines, and validation steps, see the Copilot Instructions.
MicrosoftAGENTS.mdmicrosoft/vscode/extensions/copilot/assets/prompts/skills/agent-customization/references/agents.md
Custom personas with specific tools, instructions, and behaviors. Use for orchestrated workflows with role-based tool restrictions. Use reasoning-effort to set the reasoning level for the custom agent's model: The selected model must support the configured level. If omitted, the runtime resolves the effort from the model configuration and, when applicable, the parent agent. Sources: built-in aliases, specific tools, MCP servers (<server>/*), extension tools. Special: [] = no tools, omit = defaults. Body reference: #tool:<name> To discover available tools, check your…
MicrosoftAGENTS.mdmicrosoft/vscode/extensions/copilot/src/extension/chatSessions/copilotcli/AGENTS.md
This folder contains the Copilot CLI integration for VS Code Chat. It enables users to open a new Chat window and interact with a Copilot CLI agent instance directly within VS Code. VS Code provides the UI, Copilot CLI SDK provides the smarts. Important: The Copilot CLI agent functionality is powered by the @github/copilot/sdk package. See the SDK package for full type definitions. The integration follows VS Code's platform layering pattern with three layers:
MicrosoftAGENTS.mdmicrosoft/vscode/extensions/copilot/src/platform/authentication/common/AGENTS.md
IAuthenticationService manages GitHub and Copilot authentication. It provides GitHub sessions (OAuth tokens) and Copilot tokens (CAPI tokens). getGitHubSession requires a kind parameter. Choose thoughtfully: Returns AuthenticationSession (never undefined). Throws if the user cancels. Requires createIfNone with a StrictAuthenticationPresentationOptions containing a localized detail string explaining why auth is needed: Same as above but forces re-authentication even if a session exists. Use when the current token has lost authorization: Returns AuthenticationSession | undefined. Never shows UI. Use when auth is optional: For…
MicrosoftAGENTS.mdmicrosoft/vscode/src/vs/platform/agentHost/AGENTS.md
Node runtime service construction is documented separately in node/serviceBootstrapping.md. Host startup timings, process-lifetime correlation, and session workload counts are documented in PERFORMANCE.md. Status: COMPLETE (2026-07-01) All waves A–D and gates G-B1, G-C1, G-C2, G-D1 are done. Codex, Claude, and Copilot all use the unified orchestrator path. Codex advertises multipleChats: { fork: true, sideChat: true }. Model-backed peer, fork, and side-chat parity scenarios run in deterministic replay. The operational chat surface (send/abort/model/agent/history) is fully chat-addressed and uniform across harnesses. Session ownership…
MicrosoftAGENTS.mdmicrosoft/vscode/src/vs/platform/agentHost/common/state/AGENTS.md
This directory contains the VS Code-facing wrappers around the Agent Host Protocol (AHP) state model. Read this before modifying protocol types. The generated protocol includes the Changesets model: Optional protocol fields are usually backwards-compatible. Add the field in the source protocol repo, sync protocol/**, and add wrapper exports only when VS Code code needs them. Adding a new server-produced action type is backwards-compatible when old clients can ignore it safely. Old clients at the same protocol version ignore unknown action…
MicrosoftAGENTS.mdmicrosoft/vscode/src/vs/platform/agentHost/node/copilot/prompts/AGENTS.md
This directory customizes the system prompt for Copilot CLI agent host (ahp+cli) sessions. Read this before changing how the system message is built or adding per-model / per-tool guidance. It mirrors the Copilot extension's extensions/copilot/.../prompts/node/agent/ (agentPrompts), but the agent host runs in its own process and cannot use prompt-tsx, so contributors return plain data the SDK accepts directly. Unless the matching chat.agentHost.copilot.modelCapabilityOverrides entry provides a YAML promptOverrideString or promptOverrideFile containing systemPrompt, resolveSystemMessageConfig(model, context) layers, in order: The per-model prompt override…
MicrosoftAGENTS.mdmicrosoft/vscode/src/vs/platform/agentHost/test/node/AGENTS.md
For tests in this area that touch the SessionDatabase, they MUST use an in-memory database, not a real database file on disk. Use SessionDatabase.open(':memory:') and see the examples from existing tests.
MicrosoftAGENTS.mdmicrosoft/vscode/src/vs/workbench/contrib/imageCarousel/AGENTS.md
A generic workbench editor for viewing collections of images in a carousel/slideshow UI. Opens as a modal editor pane with navigation arrows, a caption, and a thumbnail strip. The image carousel is a self-contained workbench contribution that follows the custom editor pattern: Clicking an image attachment pill in chat (when chat.imageCarousel.enabled is true) executes the workbench.action.chat.openImageInCarousel command, which collects request attachment images together with response-derived images for the current chat session and opens them in the carousel. MIME types are…
MicrosoftAGENTS.mdmicrosoft/PowerToys/AGENTS.md
Top-level AI contributor guidance for developing PowerToys - a collection of Windows productivity utilities
MicrosoftAGENTS.mdmicrosoft/generative-ai-for-beginners/AGENTS.md
This repository contains a comprehensive 21-lesson curriculum teaching Generative AI fundamentals and application development. The course is designed for beginners and covers everything from basic concepts to building production-ready applications. Key Technologies: - Python 3.9+ with libraries: openai, python-dotenv, tiktoken, azure-ai-inference, pandas, numpy, matplotlib - TypeScript/JavaScript with Node.js and libraries: openai (Azure OpenAI via the v1 endpoint + Responses API), @azure-rest/ai-inference (Microsoft Foundry Models) - Azure OpenAI Service, OpenAI API, and Microsoft Foundry Models (GitHub Models is retiring end of…
MicrosoftAGENTS.mdmicrosoft/generative-ai-for-beginners/translations/ar/AGENTS.md
يحتوي هذا الريبو على منهج شامل مكون من 21 درسًا يشمل تعليم أساسيات الذكاء الاصطناعي التوليدي وتطوير التطبيقات. الدورة مُصممة للمبتدئين وتغطي كل شيء من المفاهيم الأساسية إلى بناء تطبيقات جاهزة للإنتاج. التقنيات الرئيسية: - بايثون 3.9+ مع المكتبات: openai، python-dotenv، tiktoken، azure-ai-inference، pandas، numpy، matplotlib - تايبسكريبت/جافا سكريبت مع Node.js والمكتبات: openai (Azure OpenAI عبر نقطة النهاية v1 وResponses API)، @azure-rest/ai-inference (نماذج Microsoft Foundry) - خدمة Azure OpenAI، OpenAI API، ونماذج Microsoft Foundry (نماذج GitHub ستتوقف نهاية يوليو 2026)…
MicrosoftAGENTS.mdmicrosoft/generative-ai-for-beginners/translations/bg/AGENTS.md
Това хранилище съдържа обширна учебна програма от 21 урока, която преподава основите на Генеративния AI и разработката на приложения. Курсът е предназначен за начинаещи и обхваща всичко от базови концепции до изграждане на приложения готови за продукция. Ключови технологии: - Python 3.9+ с библиотеки: openai, python-dotenv, tiktoken, azure-ai-inference, pandas, numpy, matplotlib - TypeScript/JavaScript с Node.js и библиотеки: openai (Azure OpenAI чрез v1 endpoint + Responses API), @azure-rest/ai-inference (Microsoft Foundry модели) - Azure OpenAI Service, OpenAI API и Microsoft Foundry модели…
MicrosoftAGENTS.mdmicrosoft/generative-ai-for-beginners/translations/bn/AGENTS.md
এই রেপোজিটরিতে রয়েছে ২১টি পাঠের বিস্তৃত পাঠ্যক্রম যা জেনারেটিভ AI-এর মূল বিষয়বস্তু এবং অ্যাপ্লিকেশন উন্নয়ন শেখায়। কোর্সটি নতুনদের জন্য ডিজাইন করা হয়েছে এবং বেসিক ধারণা থেকে শুরু করে প্রোডাকশন-রেডি অ্যাপ্লিকেশন তৈরি পর্যন্ত সবকিছু আচ্ছাদিত করে। মূল প্রযুক্তি: - Python 3.9+ লাইব্রেরিসহ: openai, python-dotenv, tiktoken, azure-ai-inference, pandas, numpy, matplotlib - TypeScript/JavaScript Node.js এবং লাইব্রেরিসহ: openai (Azure OpenAI v1 endpoint + Responses API), @azure-rest/ai-inference (Microsoft Foundry Models) - Azure OpenAI সার্ভিস, OpenAI API, এবং Microsoft Foundry Models (GitHub Models ২০২৬ সালের জুলাই…
MicrosoftAGENTS.mdmicrosoft/generative-ai-for-beginners/translations/cs/AGENTS.md
Toto úložiště obsahuje rozsáhlý 21-lekcí učební plán učící základy generativní AI a vývoje aplikací. Kurz je navržen pro začátečníky a pokrývá vše od základních konceptů až po vytváření aplikací připravených pro produkci. Klíčové technologie: - Python 3.9+ s knihovnami: openai, python-dotenv, tiktoken, azure-ai-inference, pandas, numpy, matplotlib - TypeScript/JavaScript s Node.js a knihovnami: openai (Azure OpenAI přes v1 endpoint + Responses API), @azure-rest/ai-inference (Microsoft Foundry Models) - Azure OpenAI Service, OpenAI API a Microsoft Foundry Models (GitHub Models je na konci…
MicrosoftAGENTS.mdmicrosoft/generative-ai-for-beginners/translations/da/AGENTS.md
Dette repository indeholder et omfattende kursus med 21 lektioner, der underviser i grundlæggende generativ AI og applikationsudvikling. Kurset er designet til begyndere og dækker alt fra grundlæggende koncepter til opbygning af produktionsklare applikationer. Nøgle-teknologier: - Python 3.9+ med biblioteker: openai, python-dotenv, tiktoken, azure-ai-inference, pandas, numpy, matplotlib - TypeScript/JavaScript med Node.js og biblioteker: openai (Azure OpenAI via v1-endpoint + Responses API), @azure-rest/ai-inference (Microsoft Foundry Models) - Azure OpenAI Service, OpenAI API og Microsoft Foundry Models (GitHub Models udfases ved udgangen af…
MicrosoftAGENTS.mdmicrosoft/generative-ai-for-beginners/translations/de/AGENTS.md
Dieses Repository enthält einen umfassenden Lehrplan mit 21 Lektionen, der die Grundlagen der Generativen KI und die Anwendungsentwicklung vermittelt. Der Kurs ist für Anfänger konzipiert und deckt alles von den Grundkonzepten bis hin zum Aufbau produktionsreifer Anwendungen ab. Wichtige Technologien: - Python 3.9+ mit Bibliotheken: openai, python-dotenv, tiktoken, azure-ai-inference, pandas, numpy, matplotlib - TypeScript/JavaScript mit Node.js und Bibliotheken: openai (Azure OpenAI über den v1-Endpunkt + Responses API), @azure-rest/ai-inference (Microsoft Foundry Modelle) - Azure OpenAI Service, OpenAI API und Microsoft Foundry…
MicrosoftAGENTS.mdmicrosoft/generative-ai-for-beginners/translations/el/AGENTS.md
Αυτό το αποθετήριο περιέχει ένα ολοκληρωμένο πρόγραμμα σπουδών 21 μαθημάτων που διδάσκει τα βασικά του Γεννητικού AI και την ανάπτυξη εφαρμογών. Το μάθημα έχει σχεδιαστεί για αρχάριους και καλύπτει από βασικές έννοιες μέχρι την κατασκευή εφαρμογών έτοιμων για παραγωγή. Κύριες Τεχνολογίες: - Python 3.9+ με βιβλιοθήκες: openai, python-dotenv, tiktoken, azure-ai-inference, pandas, numpy, matplotlib - TypeScript/JavaScript με Node.js και βιβλιοθήκες: openai (Azure OpenAI μέσω του v1 endpoint + Responses API), @azure-rest/ai-inference (Microsoft Foundry Models) - Azure OpenAI Service, OpenAI API και…
MicrosoftAGENTS.mdmicrosoft/generative-ai-for-beginners/translations/en/AGENTS.md
This repository contains a comprehensive 21-lesson curriculum teaching Generative AI fundamentals and application development. The course is designed for beginners and covers everything from basic concepts to building production-ready applications. Key Technologies: - Python 3.9+ with libraries: openai, python-dotenv, tiktoken, azure-ai-inference, pandas, numpy, matplotlib - TypeScript/JavaScript with Node.js and libraries: openai (Azure OpenAI via the v1 endpoint + Responses API), @azure-rest/ai-inference (Microsoft Foundry Models) - Azure OpenAI Service, OpenAI API, and Microsoft Foundry Models (GitHub Models is retiring end of…
MicrosoftAGENTS.mdmicrosoft/generative-ai-for-beginners/translations/es/AGENTS.md
Este repositorio contiene un currículo integral de 21 lecciones que enseña los fundamentos de la IA Generativa y el desarrollo de aplicaciones. El curso está diseñado para principiantes y cubre desde conceptos básicos hasta la creación de aplicaciones listas para producción. Tecnologías Clave: - Python 3.9+ con bibliotecas: openai, python-dotenv, tiktoken, azure-ai-inference, pandas, numpy, matplotlib - TypeScript/JavaScript con Node.js y bibliotecas: openai (Azure OpenAI vía el endpoint v1 + Responses API), @azure-rest/ai-inference (Microsoft Foundry Models) - Azure OpenAI Service, OpenAI…
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.
