Name Your Sessions at Launch with --name
Descriptive session names make it easy to find and resume specific threads later. The --name flag (short: -n) sets a display name at launch, so you do not have to rename it afterward with /rename.
claude -n "auth-refactor"
claude -n "api-design-v2"
claude --name "onboarding-flow-debug"
The name shows in the terminal title bar and in the session picker when you run /resume or claude --resume with no arguments. Unlike session IDs (which are UUIDs), names are human-readable, so claude --resume auth-refactor is far easier to type from memory.
Once named, resuming that specific session is a single command:
# Start a named session
claude -n "payment-stripe"
# Come back to it later, from any directory
claude --resume payment-stripe
Combine --name with --worktree to give each isolated feature branch a clear identity:
claude -w feature-auth -n "auth-jwt-migration"
You can still rename mid-session with /rename [name] if you realize the original name was unclear, but setting it upfront means it is correct from the very first message.
Name every focused work session and your /resume picker stays clean and navigable.
Log in to leave a comment.
When typing feels slow — describing a complex bug, explaining architecture, or thinking through a problem out loud — press Option+V to switch to voice input. Speak naturally and Claude Code transcribes your words into a prompt, so you can describe what you need at the speed of thought.
When Claude is heading down the wrong path — editing the wrong file, writing code you don't want, or giving a long explanation you don't need — press Escape to stop it immediately. You keep everything it did up to that point and can redirect with a new prompt.
Closed a session and realized you weren't done? Pass --continue (or -c) when launching Claude Code to pick up exactly where you left off — same context, same files, same conversation history — without re-explaining what you were working on.