[eleventen]

I'm surprised that their biggest feature has not been mentioned: The permissions model is much less noisy in Cursor.

Every 30 seconds in claude you get a new, elaborate, contrived bash command that claude wants to run. It's some combination of 10 things you've already granted permission for, but this one is new!

Cursor's auto-review run mode fixes that https://cursor.com/docs/agent/security/run-modes

I know it's a compromise in security, but auto-review+sandboxing provides a much nicer out-of-the-box experience. I'm happily using Cursor + Composer 2.5/Opus for most tasks.

[shevis]

How is that different from claude’s “auto” permission mode?

[eleventen]

I was not aware of auto mode in Claude. In fact, it looks like Claude had it before cursor. Cursor has workspace scoping in a way that Claude does not seem to, but my comment above is mostly moot.