Claude Code CLI Command vs Slash Command
People think claude doctor and /doctor are the same command typed two ways. They are not. A CLI command is typed in your shell after claude, runs, prints and stops, with no chat. Scripts and CI jobs can run it. A slash command is typed inside a running session and acts on that chat. So claude doctor only reads your install, even when Claude Code will not start, while /doctor runs inside a chat and offers fixes.
Claude Code CLI Command
A command you type in the shell after claude, outside a chat.
A Claude Code CLI command is a word you type after claude in your shell, such as claude update or claude auth status. It runs, prints its answer and stops, with no chat. That is the difference from a slash command, which you type inside a running session. Most CLI commands install, sign in, check or clean up, or look after background sessions. If you mistype one, Claude Code says the closest match and stops.
Claude Code Slash Command
A word that starts with /, like /clear, that steers Claude Code.
A slash command is a word that starts with / and that you type at the start of a message, such as /clear or /model. It steers Claude Code itself, not the task you are working on. Type / to open the menu, then type letters to filter it. Any text after the name goes to the command. Many commands are built in. Skills and plugins add more of their own.
In one line
- Claude Code CLI Command
- A command you type in the shell after claude, outside a chat.
- Claude Code Slash Command
- A word that starts with /, like /clear, that steers Claude Code.