AGENTS.md examples from real projects

How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Worked for most · soon

HK-hub

HK-hubReads credentialsAGENTS.md

AgentSkills / redis-development

HK-hub/AgentSkills/redis-development/AGENTS.md

Version 1.0.0 Redis, Inc. January 2026 Note: This document is mainly for agents and LLMs to follow when maintaining, generating, or refactoring Redis applications. Humans may also find it useful, but guidance here is optimized for automation and consistency by AI-assisted workflows. Best practices for Redis including data structures, memory management, Redis Query Engine (RQE), vector search with RedisVL, semantic caching with LangCache, and performance optimization. Optimized for AI agents and LLMs.

68mo agoReviewMount

HK-hubAGENTS.md

AgentSkills / video-podcast-maker

HK-hub/AgentSkills/video-podcast-maker/AGENTS.md

Cross-agent portability layer. Read natively by Codex, Copilot, Cursor, Windsurf, Aider, Zed, Amp, JetBrains Junie, and others. Claude Code reads this too alongside SKILL.md. This is a coding-agent skill for automated video podcast creation via Remotion. The primary instruction file is SKILL.md.

68mo agoReviewMount

HK-hubReads credentialsAGENTS.md

OpenCoding

HK-hub/OpenCoding/AGENTS.md

OpenCoding 是企业级多模态 Coding Agent（Server + headless CLI）。后端为 Java 21 / Spring Boot 3.4 多模块 Maven 工程：PostgreSQL + MyBatis-Plus + Flyway + Redisson，MapStruct + Lombok，四协议模型适配（Anthropic / OpenAI / Gemini / Ollama 原生）；前端 open-coding-client 为 React 19 + Vite + TS 独立工程。 docs/design/ 是冻结契约，实现必须与其一致：先改设计文档、再改代码：与设计不符的实现视为缺陷；偏离须先在决策日志追加条目。M1 契约冻结前不写任何适配器代码。当前处于 M0 迁移阶段，仓库可能暂不可编译——现状以 §12 清单为准。运行时依赖 PostgreSQL 14+ 与 Redis 7+；单元测试离线可跑（见 README）。写任何 Java 代码前必须遵守以下 5 条规范，全文与反例清单见 .qoder/rules/：

141d agoReviewMount

CLAUDE.md vs AGENTS.md

About AGENTS.md

What is AGENTS.md?

An open format for instructions to coding agents, read by Codex, Cursor and others. Think of it as a README written for agents.

Where does it go?

At the repository root, with more specific files in subdirectories. Agents read the one closest to the file they're editing.

What should it contain?

Setup and test commands, code style, and the rules a new contributor would need to know.

Does Claude Code read it?

Claude Code reads CLAUDE.md. A one-line CLAUDE.md that points at AGENTS.md covers both.