1. Personal Claude Max $100 tier; Work Claude Team, and ChatGPT Team. I use almost exclusively Claude Opus 5.5 Medium for everything. ChatGPT seems to miss a lot that Claude doesn’t; I’ll occasionally ask it to do an adversarial review where it finds something, but that’s about it.

2. No.

3. Claude CLI and Codex, but I rarely use the latter, and just call its review function from within Claude. If Anthropic didn’t require API usage for external tooling, I’d be interested in trying a lighter harness, but it’s not that big of a deal for me.

4. No.

5. No.