Ask HN: What tools are you using for AI-assisted code review? • Hacker News Board

Re: Ask HN: What tools are you using for AI-assisted code review?

#11

Post by tangweigang » Fri, Jun 19, 2026, 2:04 AM UTC

[flagged]

Re: Ask HN: What tools are you using for AI-assisted code review?

#12

Post by felixlu2026 » Fri, Jun 19, 2026, 2:36 AM UTC

[flagged]

Re: Ask HN: What tools are you using for AI-assisted code review?

#13

Post by Supermancho » Fri, Jun 19, 2026, 2:38 AM UTC

Github copilot is a little too opinionated, but we still use it to catch obvious stuff.

Codex on top of that with specific rules and syntax requirements.

Re: Ask HN: What tools are you using for AI-assisted code review?

#14

Post by nxy » Fri, Jun 19, 2026, 2:39 AM UTC

For Claude Code, I think the standard is Codex + Gemini. Why these two? Because it “covers” the blind spots the others would miss by themselves.

Re: Ask HN: What tools are you using for AI-assisted code review?

#15

Post by shsh1312 » Fri, Jun 19, 2026, 4:10 AM UTC

Claude-Code and Codex in combination, combined with an IDE such as Google Antigravity or VisualStudio-Code are very powerful tools, if your company can invest in hardware the new Mac Studio and MacBook Pro allow optimized local inference through open-source tools such as: https://github.com/antirez/ds4

Re: Ask HN: What tools are you using for AI-assisted code review?

#16

Post by stpedgwdgfhgdd » Fri, Jun 19, 2026, 5:46 AM UTC

Built my own using Claude Code; inside a gitlab job we call Claude Code headless. This works well. There is a tiny mcp server exposed to Claude so it can post inline comments. All existing comments are fed into the reviewer to avoid double posting. The quality of feedback is high. Most complexity is in the SHA management. For example after a rebase. Luckily LLMs understand git very well otherwise it would have been impossible for me.

Re: Ask HN: What tools are you using for AI-assisted code review?

#17

Post by kcrwfrd_ » Fri, Jun 19, 2026, 5:55 AM UTC

benoitdest wrote: post #10

/review in claude code - the skill pulls the PR from remote and review it. Can post comments also.

Honestly I get awful results using this skill. The output is way better when I simply ask it to review the changes on my branch compared to origin/main