From agent-skills
Creates and maintains AGENTS.md documentation files that guide AI coding agents through a codebase. Use when adding a significant new feature or directory, changing project architecture, setting up a new project or monorepo, noticing a codebase has no AGENTS.md, or after major refactors that change project structure. Also triggers on "document this for agents", "update agents.md", or "create agents.md".
How this skill is triggered — by the user, by Claude, or both
Slash command
/agent-skills:managing-agents-mdThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
**AGENTS.md is a README for AI agents.** It tells any AI coding tool — Claude Code, Copilot, Cursor, Codex — how to navigate and work with your codebase. Keep it updated as the project evolves.
AGENTS.md is a README for AI agents. It tells any AI coding tool — Claude Code, Copilot, Cursor, Codex — how to navigate and work with your codebase. Keep it updated as the project evolves.
Create AGENTS.md when:
Update AGENTS.md when:
Do NOT create for:
For monorepos or large projects, use a hierarchical approach:
Root AGENTS.md → Project overview, tech stack, global conventions
├── app/AGENTS.md → App-specific architecture, commands, patterns
│ └── feature/AGENTS.md → Feature-specific extension points
Each tier adds specificity. Agents read from root down to the most relevant file.
# AGENTS.md — [Project or Directory Name]
Brief one-line description of this part of the codebase.
## Commands
\`\`\`bash
npm run dev # Start development server
npm test # Run tests
npm run build # Production build
\`\`\`
## Project Structure
\`\`\`
src/
├── api/ # REST endpoints (~12 files)
├── services/ # Business logic (~8 files)
├── models/ # Data models (~6 files)
└── utils/ # Shared utilities (~4 files)
\`\`\`
## Key Patterns
[Describe the main architectural patterns, data flow, or conventions]
## Boundaries
### Always
- [Pattern to always follow]
- [Convention to always use]
### Never
- [Anti-pattern to avoid]
- [Dangerous operation]
### Ask First
- [Risky change that needs confirmation]
If the project also uses Claude Code, create a CLAUDE.md that imports the AGENTS.md:
@AGENTS.md
## Claude-Specific
- [Any Claude Code-specific instructions, hooks, or skill references]
This avoids duplicating content while adding Claude-specific configuration.
Stale documentation: An outdated AGENTS.md is worse than none. Update it when the code changes.
Too granular: Don't create AGENTS.md for every directory. Only for significant architectural boundaries.
Duplicating README: AGENTS.md is for AI agents, not humans. Focus on what an agent needs to navigate and modify code correctly — commands, patterns, boundaries.
npx claudepluginhub oryanmoshe/agent-skills --plugin agent-skillsGenerates hierarchical AGENTS.md structures for codebases to optimize AI agent token usage. Use for repo analysis, monorepos, JIT indexing, and token-efficient root/sub-folder docs.
Creates and maintains concise AGENTS.md / CLAUDE.md files for projects. Analyzes toolchain, linters, and conventions to produce minimal agent-facing documentation under 100 lines.
Analyzes a project and generates a root AGENTS.md with operational commands, golden rules, and nested AGENTS.md files for high-context zones. Invoke via "AGENTS.md 만들어줘", "에이전트 규칙 만들어줘", or "/agents-md".