A concrete example
I run claude in a folder, describe the change, it proposes a diff, I approve or reject, and it applies it.
Why it matters
It's the tool that let me ship whole projects without knowing how to code. The word comes up in every agent conversation.
You'll run into it in terminal tutorials, agents, GitHub Actions, code reviews, and project automations.
Don't mix it up with
CLAUDE.md: CLAUDE.md is the file where you write down a project's rules so Claude doesn't start from scratch.
Slash command: A slash command is a short command that fires off a prepared instruction inside an AI tool.
Common mistakes
- Thinking it's a ChatGPT-style chat when it's actually an agent that edits your project.
- Giving it access to your whole system without reviewing the commands it proposes.
- Forgetting to write a CLAUDE.md and starting from scratch every session.
Quick checklist
- First I check whether the word names a concept, a tool, a risk, or a metric.
- I tie it to a concrete case: I run claude in a folder, describe the change, it proposes a diff, I approve or reject, and it applies it.
- I keep the main trap in mind: Thinking it's a ChatGPT-style chat when it's actually an agent that edits your project.
Quick questions
What is Claude Code in AI?
Claude Code is Claude's agent: it reads a project, edits files, and runs commands with your approval.
Where will I run into Claude Code?
You'll run into it in terminal tutorials, agents, GitHub Actions, code reviews, and project automations.
Which word should I read next?
Start with CLAUDE.md, Slash command, Hook.