[HN Gopher] Code Review for Claude Code
___________________________________________________________________
Code Review for Claude Code
Author : adocomplete
Score : 35 points
Date : 2026-03-09 19:03 UTC (3 hours ago)
(HTM) web link (claude.com)
(TXT) w3m dump (claude.com)
| CharlesW wrote:
| Interesting: "Reviews are billed on token usage and generally
| average $15-25, scaling with PR size and complexity."
| karmakaze wrote:
| At those prices I wonder if it also reviews the design for
| ineffectiveness in performance or decomposition into
| maintainable units besides catching the bugs.
|
| Also the examples are weird IMO. Unless it was an edge/corner
| case the authentication bug would be caught in even a smoke
| test. And for the ZFS encryption refactor I'd expect a static-
| typed language to catch type errors unless they're casting from
| `void*` or something. _Seems like they picked examples by how
| important /newsworthy the areas were than the technicality of
| the finds._
| cbovis wrote:
| 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.
| 8cvor6j844qw_d6 wrote:
| 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.
| atonse wrote:
| 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.
| Twixes wrote:
| Average _per review_? Insane costs, that's potentially
| thousands per developer. Am I missing something?
| remus wrote:
| 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.
| simianwords wrote:
| nice but why is this not a system prompt? what's the value add
| here?
| NoahZuniga wrote:
| 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)
| simianwords wrote:
| seems like a very small value add. why is this a blog post -
| i could do this myself.
| sixothree wrote:
| Does this only work with github actions? What about Devops
| and gitlab?
| Bnjoroge wrote:
| what are the implications for the tens of code review platforms
| that have recently raised on sky high valuations?
| satvikpendem wrote:
| 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...
| sixothree wrote:
| I'm guessing people need to quickly realize Claude is a
| platform.
| Bnjoroge wrote:
| bitter lesson applied to platforms
| cpncrunch wrote:
| Does AI review of AI generated code even make sense?
| xlii wrote:
| > 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.
| lowsong wrote:
| > 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.
___________________________________________________________________
(page generated 2026-03-09 23:01 UTC)