I've used it for a couple of hours. A few observations:

- It's nice to see conversation context alongside the change itself. - I wasn't able to see Claude Code utilise past commit context in understanding code. - It's a tad unclear (and possible unreliable) in what is called 'checkpointing'. - It mucked up my commit messages by replacing the first line with a sort of AI request title or similar.

Sadly, because of the last point (we use semantic release and git-cz) I've had to uninstall it.