Pawel Huryn · 4 min read · Gen AI Tools
Your .claude/ Folder Is a Production Agent
Read the original on productcompass.pm →
Claude Code turns the .claude/ folder into a production-ready agent runtime that can be called from your app. The article outlines the five primitives (CLAUDE.md, skills, MCPs, hooks, sub-agents) and shows how to structure, ship, and host production agents using the same files you edit in development, enabling one function call to replace n8n-style workflows.
Key Takeaways
- Agent as a callable component inside your app; dev and prod share the same CLAUDE.md.
- Five primitives: CLAUDE.md, skills, MCPs, hooks, sub-agents; all are version-controlled and portable.
- Sub-agents live in their own folders; adding a second agent is as simple as creating a new directory.
- A single function call can replace complex workflow orchestration, simplifying production patterns.
- Production choices: SDK vs Managed Agents vs LangGraph vs n8n; for in-app requests, Claude Code’s production stack may suffice—hosted runtimes are optional unless needed.
Excerpt
Last week I ran a spike. Same CLAUDE.md , same skills, same MCPs, same hooks I write every day in Claude Code — pointed at a Next.js app. Shipped a working Knowledge Chatbot in an afternoon. No new framework. No Claude Managed Agents. Zero files I hadn’t written a dozen times before. Everyone's covering agents helping you build or do knowledge work. The pattern nobody's shipping: the same primitives are the production runtime. What you’ll learn: The Claude Code primitives that double as a production runtime When to pick the Agent SDK over Claude Managed Agents or a framework The…