# Claude Code Review: why I enable it on every PR

> Source: https://extradev.fr/en/blog/claude-code-review-why-i-enable-it-on-every-pr
> Published: 2026-06-19
> Author: Vincent Roye
> Site: Extra Dev (https://extradev.fr)
> Lang: en-US
> Tags: claude code, code review, agents ia, pull request, qualité code, anthropic, dev senior

Claude Code Review runs 4 AI agents in parallel on every pull request. Under 1% false positives, 20 minutes per review, $15 to $25 per pass. A field report from a senior dev who uses it daily.

At Anthropic, productivity per engineer jumped **200% in one year**. The bottleneck is no longer writing code: it is reviewing it. Claude Code Review, launched in March 2026, attacks this problem by sending a fleet of 4 AI agents on every pull request. I started using it on my day-rate engagements from day one, and I am not going back.

- 🎯 **4 agents in parallel**: each PR is analyzed from four distinct angles in ~20 minutes.
- 📊 **Under 1% false positives**: the system checks its own findings before publishing.
- ⚠️ **$15 to $25 per review**: a real cost, worthwhile only on code heading to production.
- ⚡ **Complement, not replacement**: Claude does not approve the PR, it comments. The human dev has the final say.

When you deliver code on a day-rate engagement at €180/day, quality is not a bonus: it is the contract. A critical bug that slips into production costs days of debugging, client trust, and sometimes the contract renewal. Claude Code Review does not replace the human reviewer, but it catches what the end-of-day skim lets through. Here is how the system works, what it costs, and why it changes my workflow as an AI-augmented senior dev.

## What Claude Code Review actually does

Most code analysis tools (ESLint, SonarQube, various linters) work through static pattern matching. They flag rule violations, not logical bugs. Claude Code Review works differently: it **reads code the way a developer would**, taking the project context into account.

### How do the 4 agents split the work?

According to documentation published on [GitHub by Anthropic](https://github.com/anthropics/claude-code/blob/main/plugins/code-review/README.md), the system launches 4 agents in parallel on each PR:

- **Agents 1 and 2**: check conformance with the repository's CLAUDE.md and REVIEW.md files. These files serve as project memory, exactly as I recommend on every engagement. A well-written CLAUDE.md is the difference between an agent that understands the project's conventions and one shooting in the dark.
- **Agent 3**: scans the changes for obvious bugs (null references, inverted conditions, off-by-one errors).
- **Agent 4**: analyzes git blame and history to spot contextual regressions, patterns that have already caused problems.

Each finding gets a confidence score from 0 to 100. Only those above 80 are published. This cross-verification step explains the under-1% false-positive rate, a number I struggle to hit with any standard linter.

### Why does the CLAUDE.md file change everything?

My experience confirms what the official docs suggest: **a repository without CLAUDE.md receives generic comments**. A repository with a detailed CLAUDE.md (naming conventions, architectural patterns, critical business rules) receives comments that read like those from a lead dev who actually knows the project. It makes sense: two of the four agents are dedicated to reading that file. If you do not invest 30 minutes in it, you waste half the system's power.

I have been using project context files (CLAUDE.md, ARCHITECTURE.md, CONVENTIONS.md) on every engagement for over a year. Claude Code Review validates this approach: structured project memory is no longer just a good practice, it is a measurable performance multiplier for agents.

## Anthropic's internal numbers

Anthropic uses Code Review internally on almost all of its PRs. The metrics published on the [official blog](https://claude.com/fr/blog/code-review) paint a clear picture of what the system catches.

### What impact does it have on bug detection?

Before Code Review, **16% of PRs** received substantive comments from human reviewers. After activation, that figure rises to **54%**. The system does not replace reviewers: it gives them a starting point. Bugs are already identified, ranked by severity, with inline comments on the relevant lines.

| Metric | Before Code Review | After Code Review | Trend |
| --- | --- | --- | --- |
| PRs with substantive comments | 16% | 54% | ↑ +238% |
| Findings on large PRs (1,000+ lines) | Not measured | 84%, avg. 7.5 issues | ↑ systematic |
| Findings on small PRs ( "The real advantage is not using AI to code faster, it is building an industrialized software production system around AI, review included."
>
> Vincent Roye, June 2026

### How to integrate Code Review into a day-rate engagement ritual?

On my engagements, the ritual is simple. Every morning I hold a [30-minute check-in](https://extradev.fr/blog/piloter-dev-regie-distance-rituel-30-minutes) with the client. The previous day's PRs have already gone through Code Review. Critical comments are handled before the call. The client sees clean PRs, annotated, with a transparent review history.

For CTOs and founders who delegate development, this is a concrete quality signal. You no longer ask "was the code reviewed?": you see the agents' comments directly on the PR, ranked by severity, with the confidence score.

According to [McKinsey](https://www.mckinsey.com/capabilities/mckinsey-digital/our-insights/the-economic-potential-of-generative-ai-the-next-productivity-frontier), teams that integrate AI into their quality pipeline (tests, review, monitoring) gain 20 to 30% productivity compared to teams that use it only for code generation.

My verdict: enable Code Review on your critical branches. The $15 to $25 per PR cost is negligible compared to the price of a production bug. If you are a solo dev or on a day-rate engagement, combine `/code-review` locally (free) and Code Review on merge PRs to main (paid). The tool is not perfect (research preview, Team/Enterprise plans only), but it already outperforms the majority of end-of-day human reviews.

## Frequently Asked Questions

### Does Claude Code Review replace a human reviewer?

No. The system never approves a PR: it comments and ranks findings by severity. The human developer has the final say on the merge. Anthropic designed the tool as a complement, not a substitute. Existing review workflows (required approvals, CODEOWNERS) remain intact.

### How much does a review with Claude Code Review cost?

Each review costs between $15 and $25, depending on PR size. The price is proportional to the tokens consumed by the agents. Small PRs (under 50 lines) stay close to $15, large ones (1,000+ lines) can reach $25.

### Can Code Review be used on a privately hosted internal repository?

Not with the managed version, which runs on Anthropic's infrastructure. For private repositories with confidentiality requirements, Anthropic offers the open-source GitHub Action, which runs in your own CI/CD. For self-hosted GitHub Enterprise Server instances, dedicated documentation is available on the Claude Code website.

### What is the prerequisite for getting good results?

A detailed CLAUDE.md file in the repository. Two of the four agents are dedicated to checking conformance with this file. Without it, comments remain generic. With a CLAUDE.md that describes conventions, architectural patterns, and business rules, comments become project-specific and much more useful.

### Does Claude Code Review work with models other than Claude?

No. Code Review is a managed service by Anthropic that uses exclusively Claude models (Opus and Sonnet depending on complexity). The open-source GitHub Action, however, can be configured to use different models, but results are optimized for Claude, as the harness was designed around its specific capabilities.

## Sources

- [GLM 5.2 in Claude Code is Blowing My Mind (Nate Herk | AI Automation)](https://www.youtube.com/watch?v=2OD14-0cot4)
- [Code Review (Claude Code Docs)](https://code.claude.com/docs/en/code-review)
- [Code Review Plugin README (GitHub anthropics/claude-code)](https://github.com/anthropics/claude-code/blob/main/plugins/code-review/README.md)
- [Code Review for Claude Code (Anthropic Blog)](https://claude.com/fr/blog/code-review)
- [Claude Code Review: Automated Code Review with AI Agents (SFEIR Institute)](https://institute.sfeir.com/fr/articles/claude-code-review-revue-code-automatisee-agents/)
- [Claude Code Review Uses AI Agents to Detect Bugs (ZDNet)](https://www.zdnet.fr/actualites/ce-nouvel-outil-claude-code-review-utilise-des-agents-ia-pour-detecter-les-bugs-dans-vos-pull-requests-voici-comment-cela-fonctionne-492315.htm)