Ask HN: How are you reviewing code with Claude Code?

I'm looking for solutions to automatically review code changes made by Claude Code before they're finalized. Currently considering setting up a secondary AI model with my coding guidelines that would:

Review each edit/commit from Claude Code Either reject with feedback (which I'd pass back to Claude Code) or approve for repo push Essentially act as a gatekeeper between Claude Code and my actual codebase Before I build this myself, wanted to check if anyone has already tackled this problem or has a better approach. Any existing tools, workflows, or architectures you'd recommend?

Thanks in advance for any insights!