agentleFS

AGENTS.md examples from real projects

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

Worked for most · soon
royaluniondesign-sysAGENTS.md

claude-os / common

royaluniondesign-sys/claude-os/.claude/rules/common/agents.md

Located in ~/.claude/agents/: No user prompt needed: 1. Complex feature requests - Use planner agent 2. Code just written/modified - Use code-reviewer agent 3. Bug fix or new feature - Use tdd-guide agent 4. Architectural decision - Use architect agent ALWAYS use parallel Task execution for independent operations: For complex problems, use split role sub-agents: - Factual reviewer - Senior engineer - Security expert - Consistency reviewer - Redundancy checker

18mo agoReviewMountCreate a free account to mount
royaluniondesign-sysAGENTS.md

claude-os

royaluniondesign-sys/claude-os/docs/agents.md

Claude OS includes 31 specialized agents. Claude spawns them automatically during workflows, or you can reference them directly. These run automatically during /gsd:* workflows. Reference these in prompts like: "Use the architect agent to design the auth system" Spawned automatically by /seo:audit and related commands. Create a file in .claude/agents/my-agent.md: No registration needed — Claude picks it up automatically.

18mo agoReviewMountCreate a free account to mount
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.