It would be cool if I didn't have to worry about whether I was "in" or "out" of the AI TUI. Right now, I need at least two terminals open: One running my shell, that I use to issue shell commands, and one running Claude, where I can't. It would be nice if it could just be my shell, and when I wanted to invoke claude, I'd just type:
Most AI agents have a 'bash mode' and, you can use Warp terminal which is terminal first, but easy to activate the AI from the terminal. For example, if you mangle a jq command, it will use AI to suggest the right way to do it.
Just tested and yes, but it's a little tricky so your `c` script will have to manage session IDs:
1. Start a new session and provide a random UUID:
claude -p "The secret word is potato" --session-id 550e8400-e29b-41d4-a716-446655440000
> I see you've shared a secret word. I'll keep that in mind — the secret word is **potato**.
> Is there something I can help you with today?
2. Use the -r/--resume flag with the same UUID for follow up messages:
claude -p "What is the secret word?" -r 550e8400-e29b-41d4-a716-446655440000
> The secret word is **potato**.
