Claude Code Review
Ranked 16 of 23 agent skills by recommenders
Recommended as a convenient way to get AI code review inside a Claude Code session that finds good issues. Critics say it has blind spots and costs $15-25 per review.
Recommended as a convenient way to get AI code review inside a Claude Code session that finds good issues. Critics say it has blind spots and costs $15-25 per review.
30 people gave an opinion
- recommend it
- 11
- criticize it
- 19
- approval share
- 37%
Recommended in 5 of 13 months
- November 2025: not recommended
- December 2025: recommended
- January 2026: recommended
- February 2026: not recommended
- March 2026: recommended
- April 2026: not recommended
- May 2026: recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 11 people recommend itNeeds 10 or more, met.
- 0.5 recommenders for every criticNeeds 2 to 1 or better, not met.
- Recommended in 5 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Convenient inside a running Claude Code session
“Looks smooth and convenient, especially using the running Claude Code session”
Comment from 30 Mar 2026 in “Inline code review UI for Claude Code (VSCode extension)” “The only one I use right now is code-review. Naturally fitting.”
Comment from 9 Jan 2026 in “MCP Is a Fad” Covers most of what code review needs
“This will cover like 98% of what you want out of code review. It's a good skill.”
Comment from 27 May 2026 in “Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs” “The Claude code review skill is a simple version of exactly this.”
Comment from 29 May 2026 in “Orchestrating AI code review at scale” Finds good issues in code
“Claude's code review skill, in particular, can find some good stuff. But it has some big blind spots around certain types of code.”
Comment from 10 Oct 2026 in “Grieving the loss of details” “AI code review is invaluable.”
Comment from 22 Dec 2025 in “Get an AI code review in 10 seconds”
What people warn about
Each mark is one comment
Expensive per review
“This is the subsidised cost to get users to use it, it could trivially end up ten times this amount.”
Comment from 9 Mar 2026 in “Code Review for Claude Code” “the claude code review product originally mentioned it cost "$15-25 per review" (which is absurd)”
Comment from 16 Oct 2026 in “How the Claude Code team does code review” “It's simpler to just use “review code”. It's also way cheaper.”
Comment from 27 May 2026 in “Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs” - Comment from 9 Mar 2026 in “Code Review for Claude Code”
- Comment from 11 Mar 2026 in “Code Review for Claude Code”
- Comment from 16 Oct 2026 in “How the Claude Code team does code review”
- Comment from 4 Apr 2026 in “How many products does Microsoft have named 'Copilot'? I mapped every one”
Misses issues and blind spots
“Claude's code review skill, in particular, can find some good stuff. But it has some big blind spots around certain types of code.”
Comment from 10 Oct 2026 in “Grieving the loss of details” “the experience had no relation at all with the reliability or thoroughness claims”
Comment from 27 May 2026 in “Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs” “default code-review in Claude code is pretty mid for finding all issues”
Comment from 17 Oct 2026 in “How the Claude Code team does code review” Low value for the price
“The value ceiling is low because it's fundamentally a linting++ problem with better language models.”
Comment from 10 Mar 2026 in “Code Review for Claude Code” “seems like a very small value add”
Comment from 9 Mar 2026 in “Code Review for Claude Code” Noisy, inconsistent results
“When a tool flags 8 issues on clean code and 8 issues on broken code, it's not a reviewer, it's a random number generator with a UI.”
Comment from 13 Mar 2026 in “Code Review for Claude Code” “Honestly I get awful results using this skill.”
Comment from 19 Jun 2026 in “Ask HN: What tools are you using for AI-assisted code review?”
Other agent skills people recommend
The four most recommended other agent skills, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Superpowers | 138 | 72 | 66% | 12 | 4 mo7 owners | — |
| Claude Skills | 59 | 26 | 69% | 11 | — | Approved |
| grill-me skill by Matt Pocock | 39 | 2 | 95% | 8 | — | Approved |
| Get Shit Done | 31 | 32 | 49% | 7 | — | — |
| Claude Code ReviewThis page | 11 | 19 | 37% | 5 | — | — |
What people said
26 of the 32 comments that mention it, newest first. Each links to the original comment.
“default code-review in Claude code is pretty mid for finding all issues”
“it's very easy to rack up $100+ per pr”
“the claude code review product originally mentioned it cost "$15-25 per review" (which is absurd)”
“Claude's code review skill, in particular, can find some good stuff. But it has some big blind spots around certain types of code.”
“this only checks whether the code is in compliance with CLAUDE.md though”
“it was using Opus for simple git diff commands and similarily mechanical tasks”
“Honestly I get awful results using this skill.”
“The Claude code review skill is a simple version of exactly this.”
“It's simpler to just use “review code”. It's also way cheaper.”
“the experience had no relation at all with the reliability or thoroughness claims”
“has a specific prompt that we've found is a good balance of precision, recall, and cost”
“This will cover like 98% of what you want out of code review. It's a good skill.”
“I like the new /code-review skill”
“it was slow and expensive”
“Looks smooth and convenient, especially using the running Claude Code session”
“When a tool flags 8 issues on clean code and 8 issues on broken code, it's not a reviewer, it's a random number generator with a UI.”
“Anthropic is pricing for teams that treat every PR the same”
“The value ceiling is low because it's fundamentally a linting++ problem with better language models.”
“So their business model is to deliver me buggy code and then charge me to fix it?”
“At average of $15~25 per review, this is way more expensive.”
“This is the subsidised cost to get users to use it, it could trivially end up ten times this amount.”
“Not a great ad of agent based development quality.”
“seems like a very small value add”
“One thing that might be effective at limited-interaction recovery-from-ignoring-CLAUDE.md is the code-review plugin”
“The only one I use right now is code-review. Naturally fitting.”
“AI code review is invaluable.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.