Ask HN: How are you reviewing code with Claude Code?
2 comments
I'm actually building something like this.
A code review tool that can be ran by Claude Code (and other tools like cursor, kiro, windsurf) where it does the first pass.
You can also define the rules on how code should be reviewed, and we have a free library of prompts for common code review checks.
I didn't see a way to contact you in your bio so please reach out - ilya (at) wispbit.com - and I can give you access.
A code review tool that can be ran by Claude Code (and other tools like cursor, kiro, windsurf) where it does the first pass.
You can also define the rules on how code should be reviewed, and we have a free library of prompts for common code review checks.
I didn't see a way to contact you in your bio so please reach out - ilya (at) wispbit.com - and I can give you access.
The point of code review imo is to have a human-in-the-loop actually read the code and decide if it makes sense, in the broader context of the application. That means the human knows things that a linter, formatter, automated test-suite, or even AI agent doesn't know about.
If a computer is doing code review, then it's not a code review. It's an automated check. Even if it's done by AI
If a computer is doing code review, then it's not a code review. It's an automated check. Even if it's done by AI
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!