I really don't get why people think Opus 5 is bad. In my testing it's been fine, but every other model is converging on also being fine. I have ADHD mode installed in my main Claude Code instance though, so that may be part of why I have a better time with it?
What in the world is ADHD mode? Searching it up I see this thing called an “ADHD” skill? Does that work well?
It seems like the skill has some more specific scaffolding for problem solving, so (if that’s true, i didn’t read very in depth) in that case that alone might significantly reduce perfeived performance variability between models
https://github.com/ayghri/i-have-adhd