An agent is not a magical entity. It is a folder of markdown files plus a prompt. Structure the folder well and the agent works. Structure it badly and it does not.
Agent is the most overused word in AI right now. Most people imagine a black-box autonomous robot. That misunderstanding is expensive. It makes people scared of agents (too magical), disappointed by them (not magical enough), or sold things that are not really agents.
Once you see that an agent is a folder, the fear and mystique go away. You can read it. Edit it. Copy it. Hand one to a teammate. Build a new one in fifteen minutes.
An agent is not a magical entity. It is a folder on your computer that contains three kinds of file. The LLM is the same Claude everyone else uses. The folder is what makes Claude behave like a specialist.
Once you see that an agent is a folder, the fear and the mystique both go away. You can read it. Edit it. Copy it. Hand one to a teammate. Make a new one in fifteen minutes by copying an existing one and changing the role.
The opposite framing, the magic-black-box framing, is what makes people scared of agents, disappointed in them, or sold things that are not really agents at all. If you cannot open the folder, you do not own the agent.
You leave the retreat with eight agents on your Mac Mini. Four on the build team, four on the go-to-market team. All eight are folders you can open, read, and modify.
If you have the IL agent team installed (from the retreat or the template repo), use the writer agent. If not, copy any agent's folder from the template into a new project to follow along.
In your terminal, cd into .claude/agents/writer (or wherever your agent lives). Run ls. You will see a small set of markdown files. Open them in your editor.
Open the file that defines the agent (typically AGENT.md, writer.md, or a file with frontmatter). Notice how short and specific it is. The whole agent is this paragraph plus a few skills.
In Claude Code, ask the writer agent: "Write a 50-word intro for an Infinite Leverage retreat." Save the output.
Change one line in the role file: tone ("be playful, use short sentences") or focus ("always end with a question"). Save.
Ask the same agent the same prompt. The output will be visibly different. Same Claude, different folder, different result.
You have seen, with your own eyes, that the agent is the folder. Same model, different folder, different specialist. The black-box mystique is gone for good.
You open one of the eight agents, change its role definition, run it twice on the same prompt, and watch the same model produce two different outputs because the folder told it to.