A concrete example
I create /review, which kicks off a full code review. I type /review and Claude applies my process without me describing it again.
Why it matters
Slash commands turn a manual workflow into a button. You save hours on routine work.
You run into it in Claude Code, Codex CLI, the /memory, /agents, /review commands, and reusable workflows.
Don't mix it up with
Claude Code: Claude Code is Claude's agent: it reads a project, edits files, and runs commands with your approval.
CLAUDE.md: CLAUDE.md is the file where you write down a project's rules so Claude doesn't start from scratch.
Common mistakes
- Creating a command for something you'll only do once.
- Piling up 50 commands without deleting any.
- Forgetting to version the commands in the repo.
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 create /review, which kicks off a full code review. I type /review and Claude applies my process without me describing it again.
- I keep the main trap in mind: Creating a command for something you'll only do once.
Quick questions
What is Slash command in AI?
A slash command is a short command that fires off a prepared instruction inside an AI tool.
Where will I run into Slash command?
You run into it in Claude Code, Codex CLI, the /memory, /agents, /review commands, and reusable workflows.
Which word should I read next?
Start with Claude Code, CLAUDE.md, Hook.