Use --continue to Resume Your Most Recent Claude Code Conversation
You're deep in a refactoring session, you close the terminal by accident — or intentionally step away — and now you need to pick up where you left off. Instead of starting fresh, just resume.
# Resume the most recent conversation
claude --continue
# Short form
claude -c
Claude Code reloads the full conversation history from your last session — every prompt, every file change, every decision. You're back in context instantly, as if you never left.
You can also resume and immediately give a new instruction in one shot:
# Resume and continue with a new task
claude -c "now add tests for the changes we just made"
# Resume in print mode for a quick follow-up
claude -c -p "summarize what we changed in the last session"
This pairs especially well with --resume if you want to pick a specific older conversation instead of just the most recent one:
# List recent conversations and pick one to resume
claude --resume
A few scenarios where --continue shines:
- Accidental closes — terminal crashed, laptop restarted, you hit Ctrl+D too fast
- Planned breaks — step away for lunch, come back and keep going
- Follow-up tasks — finished a feature, closed the session, then realized you forgot the tests
- Review and iterate — re-enter a session to ask Claude about decisions it made earlier
The conversation persists locally, so this works even after reboots. Just keep in mind that very old sessions may have been cleaned up automatically.
claude -c is your undo button for closing a session too early.
via Claude Code
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.
The -p (print) flag runs Claude Code as a one-shot command — ask a question, get an answer, and return to your shell. Perfect for quick lookups, scripting, piping output, and integrating Claude into shell workflows without starting a full interactive session.