Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Code Review for Claude Code

claude.com

Post reply on HN
Print view View original

11–20 of 52 posts

Re: Code Review for Claude Code

#11

Post by sixothree »

NoahZuniga wrote: post #6
simianwords wrote: post #3

nice but why is this not a system prompt? what's the value add here?

You're paying the same token rate for this as you would if it was just a system prompt. Clearly the scaffolding adds something. (They mention their github action which seems more like a system prompt)

Does this only work with github actions? What about Devops and gitlab?

Re: Code Review for Claude Code

#12

Post by atonse »

CharlesW wrote: post #2

Interesting: "Reviews are billed on token usage and generally average $15–25, scaling with PR size and complexity."

Wait, what? So if I'm a paying Max user, i'd still have to pay more? Don't see the value. Would rather have a repo skill to do the code review with existing Claude Max tokens.

Re: Code Review for Claude Code

#15

Post by xlii »

> We've been running Code Review internally for months: on large PRs (over 1,000 lines changed), 84% get findings, averaging 7.5 issues. On small PRs under 50 lines, that drops to 31%, averaging 0.5 issues. Engineers largely agree with what it surfaces: less than 1% of findings are marked incorrect.

So the take would be that 84% heavily Claude driven PRs are riddled with ~7.5 issues worthy bugs.

Not a great ad of agent based development quality.

Re: Code Review for Claude Code

#16

Post by lowsong »

> Reviews are billed on token usage and generally average $15–25, scaling with PR size and complexity.

You've got to be completely insane to use AI coding tools at this point.

This is the subsidised cost to get users to use it, it could trivially end up ten times this amount. Plus, you've got the ultimate perverse incentive where the company that is selling you the model time to create the PRs is also selling you the review of the same PR.

Re: Code Review for Claude Code

#17

Post by Bnjoroge »

satvikpendem wrote: post #8
Bnjoroge wrote: post #5

what are the implications for the tens of code review platforms that have recently raised on sky high valuations?

Same as all the other companies that built on top of the API and then were obsoleted after the API provider made it a built-in feature. https://finance.yahoo.com/news/claude-just-killed-startup-sf...

bitter lesson applied to platforms

Re: Code Review for Claude Code

#18

Post by remus »

Twixes wrote: post #13
CharlesW wrote: post #2

Interesting: "Reviews are billed on token usage and generally average $15–25, scaling with PR size and complexity."

Average _per review_? Insane costs, that's potentially thousands per developer. Am I missing something?

I haven't used it so just spit balling, but surely it depends on the quality of the review? If it picks up lots of issues and prevents downtime then it could work out as worthwhile. What would it cost an engineer with deep knowledge of the codebase to do a similar job? You could spend an hour really digging into a PR, poking around, testing stuff out etc. Im guessing most engineers are paid more than $15-25/hr, not to mention the opportunity cost.

Re: Code Review for Claude Code

#19

Post by 8cvor6j844qw_d6 »

cbovis wrote: post #9
CharlesW wrote: post #2

Interesting: "Reviews are billed on token usage and generally average $15–25, scaling with PR size and complexity."

This cost seems wild. For comparison GitHub Copilot Code Review is four cents per review once you're outside of the credits included with your subscription.

Same thoughts.

For comparison, Greptile charges $30 per month for 50 reviews, with $1 per additional review.

At average of $15~25 per review, this is way more expensive.

Re: Code Review for Claude Code

#20

Post by lbreakjai »

Bnjoroge wrote: post #5

what are the implications for the tens of code review platforms that have recently raised on sky high valuations?

There might still be plenty of room to compete, especially at $15-$25 per review. I'm starting to feel like the right harness makes more difference than the right model.

The real competition for both claude and the platforms is a skill running locally against the very same code.

Post reply on HN