AGENTS.md examples from real projects

MicrosoftAGENTS.md

tgrep

microsoft/tgrep/AGENTS.md

A short guide for AI agents (and the humans who wire them up) that want to use tgrep as a fast search tool inside a repository. It complements the README, which documents every flag; this file covers the few things an agent has to get right. tgrep is ripgrep with a pre-built trigram index and an optional server. A search resolves in this order: 1. Server running for this tree: query it over TCP. Fastest. A file watcher keeps the…

No other project uses it yet

MicrosoftReads credentialsAGENTS.md

Generative-AI-for-beginners-dotnet

microsoft/Generative-AI-for-beginners-dotnet/AGENTS.md

This repository contains Generative AI for Beginners .NET - a hands-on course teaching .NET developers how to build Generative AI applications. The course focuses on practical, runnable code samples and real-world applications.

MicrosoftAGENTS.md

agent-skills

microsoft/agent-skills/Agents.md

A repository of skills, prompts, and MCP configurations for AI coding agents working with Azure SDKs and Microsoft AI Foundry services. Azure SDKs and Foundry APIs change constantly. Never work with stale knowledge. Before implementing anything with Azure/Foundry SDKs: If you skip this step and use outdated patterns, you will produce broken code. These principles reduce common LLM coding mistakes. Apply them to every task. Don't assume. Don't hide confusion. Surface tradeoffs. Minimum code that solves the problem. Nothing speculative.

MicrosoftAGENTS.md

agent-skills / references

microsoft/agent-skills/.github/plugins/azure-sdk-python/skills/azure-ai-projects-py/references/agents.md

For production deployments, use versioned agents:

MicrosoftAGENTS.md

agent-skills / commands

microsoft/agent-skills/.github/plugins/deep-wiki/commands/agents.md

Generate AGENTS.md files for pertinent repository folders — only where missing. Provides coding agents with build commands, testing instructions, code style, project structure, and boundaries.

MicrosoftAGENTS.md

agent-skills / tests

microsoft/agent-skills/tests/AGENTS.md

This folder contains a test harness for evaluating AI-generated code against acceptance criteria for skills. What we're testing: Skills in .github/skills/ that provide domain knowledge for Azure SDKs. How it works: Run pnpm harness --list from the tests/ directory to see all skills with criteria. Location: tests/scenarios/<skill-name>/acceptance-criteria.md Source materials (in order of priority): Critical: Document import distinctions carefully. Many Azure SDKs have models in different locations (e.g., azure.ai.agents.models vs azure.ai.projects.models). Location: tests/scenarios/<skill-name>/scenarios.yaml Scenario design principles: Success criteria:

MicrosoftAGENTS.md

mxc

microsoft/mxc/AGENTS.md

Read and follow .github/copilot-instructions.md before writing or reviewing code. It contains MXC's architecture, compatibility, security, build, and SDK rules. The expectations below apply in addition. - Understand the existing flow before editing: callers, shared helpers, backend ownership, errors, cleanup, and affected SDK entry points. A working happy path is not enough; check how the change composes with existing behavior. - Put behavior where it belongs. Parsers decode contracts and preserve field presence; backend-specific defaults, policy checks, and enforcement belong in…

No other project uses it yet

MicrosoftAGENTS.md

Ontology-Playground

microsoft/Ontology-Playground/AGENTS.md

This document contains guidelines for AI coding assistants working on this project.

MicrosoftAGENTS.md

Microsoft365DSC

microsoft/Microsoft365DSC/AGENTS.md

Purpose: concise, enforceable rules for AI coding agents editing this repository. Generated files (do not edit): Resource definitions (manually authored): Class-specific rules covering $Script: variables, $this.ResourceCache and $this inside nested script blocks live in .github/copilot-instructions.md. Rules for authoring the files under Examples/ live in .github/instructions/m365dsc-examples.instructions.md.

MicrosoftAGENTS.md

Olive

microsoft/Olive/AGENTS.md

Olive is a Python toolkit for AI model optimization on ONNX Runtime. The main package is in olive/, tests are in test/, and the CLI entry point is olive. Olive users should install olive-ai with pip install olive-ai, and follow README.md. Use the smallest relevant check for your change: If you need to run tests, install the appropriate dependencies from test/requirements-test.txt or one of the platform-specific files in test/.

No other project uses it yet

MicrosoftAGENTS.md

intelligent-terminal

microsoft/intelligent-terminal/AGENTS.md

Intelligent Terminal is a Windows Terminal fork that adds first-class AI agent workflows. The inherited Windows Terminal build, architecture, and C++ conventions are documented in .github/copilot-instructions.md; this file contains only the fork-specific context. - WTA (tools/wta/) is the Rust orchestrator. - ACP means Agent Client Protocol. wta-master owns a pool of agent CLI processes keyed by agent identity, execution source, and command; helpers using the same key share one process and multiplex sessions through it. Installed, policy-allowed native host agents…

No other project uses it yet

MicrosoftAGENTS.md

intelligent-terminal / TestHostApp

microsoft/intelligent-terminal/src/cascadia/LocalTests_TerminalApp/TestHostApp/AGENTS.md

One packaged Windows app hosts TerminalApp local tests and real production UI for isolated accessibility checks. It does not replace full-app integration tests. The harness surface fre-settings launches the FRE mode, invokes Next through UI Automation, and scans the resulting settings controls. It is not a separate app or launch argument. Agents mode activates the host window before creating the production view model and navigates its Frame with NavigateToPageArgs. This exercises the page's normal OnNavigatedTo initialization, not a TestHost-only Agents…

MicrosoftAGENTS.md

intelligent-terminal / wta

microsoft/intelligent-terminal/tools/wta/AGENTS.md

These rules apply to tools/wta/. The repo-level AGENTS.md is the canonical source for build, deployment, supported providers, runtime paths, and log names. Do not duplicate those facts here. WTA is a Rust binary with three launch modes: - Master (--master <pipe>): owns a pool of agent CLI subprocesses and their ACP stdio connections, accepts helper named-pipe connections, and routes each ACP SessionId to its owning helper. Helpers with the same master-derived agent key share a process. Installed, policy-allowed native host…

No other project uses it yet

MicrosoftAGENTS.md

just

microsoft/just/AGENTS.md

Just is a Microsoft build task organization library for JavaScript/TypeScript projects. It provides a task runner (just-task) and preset build scripts (just-scripts) for common workflows (TypeScript, Webpack, Jest, ESLint, etc.). DO NOT run jest directly. You MUST run yarn test (which wraps jest and takes all the same args) from the specific package to ensure the correct environment is set up. Built on Undertaker (Gulp's task orchestrator). Key modules in packages/just-task/src/: Task functions can: return a Promise, call a done…

MicrosoftAGENTS.md

DiskANN

microsoft/DiskANN/AGENTS.md

Last Updated: 2026-10-29 (based on v0.61.0) DiskANN is a Rust implementation of scalable approximate nearest neighbor (ANN) search algorithms. The project is a rewrite from C++ to Rust. The repository uses a Cargo workspace with crates organized into functional tiers. See Cargo.toml for: - Workspace members and their dependencies - Shared dependency versions - Build profiles (release, test) - Workspace-level lints Tier 1: Foundation - diskann-wide/ - Low-level SIMD, bit manipulation, type width abstractions - diskann-vector/ - Vector primitives and…

MicrosoftAGENTS.md

vscode-eslint

microsoft/vscode-eslint/agents.md

The extension integrates ESLint into VS Code by implementing a ESLint server using the Language Server Protocol (LSP). Key goals: * Defer activation until needed (lazy activation based on opened documents / settings). * Support multiple workspace folders & dynamic working directory inference. * Abstract ESLint version / API differences (CLIEngine vs ESLint class / flat config) transparently. * Provide rich code actions (fix all, rule disable, suggestions) and formatting integration. * Handle notebooks and non-file schemes where possible. Settings…

MicrosoftAGENTS.md

vscode-eslint / client

microsoft/vscode-eslint/client/agents.md

This is the client implementation of the ESLint extension

MicrosoftAGENTS.md

vscode-eslint / server

microsoft/vscode-eslint/server/agents.md

This is the server implementation of the ESLint extension The VS Code API uses URIs to identify resource. ESLint in contrast uses file system paths. The conversion from URIs into file system paths happens in the function getFileSystemPath in the server\src\paths.ts file

MicrosoftAGENTS.md

windows-drivers-rs

microsoft/windows-drivers-rs/AGENTS.md

Rust crates for developing Windows Drivers (WDM, KMDF, UMDF). The workspace only includes the library crates under crates/; examples and tests are excluded from the root workspace because each requires a different WDK configuration (only one WDK config per Cargo build graph is supported). Crate layering (bottom → top): Key design patterns: Requires an eWDK developer prompt and LLVM 17 on PATH for bindgen. cargo-expand v1.0.85 is required for macrotest/trybuild-based tests. Switching between stable/nightly toolchains requires deleting cached test artifacts…

No other project uses it yet

MicrosoftAGENTS.md

vscode-mssql

microsoft/vscode-mssql/AGENTS.md

- Use DEVELOPMENT.md for setup, build, test, localization, and debugging workflows. - Treat package scripts, workspace configuration, and test configuration as the source of truth when documentation disagrees. - Before…