Claude Code PR Review Guide: Official Code Review vs. Self-Built Subagents
AI vibe coding has doubled code output speeds, but PR review volumes have exploded along with it — manual review has become the bottleneck. Anthropic officially launched Claude Code Review in March 2026, using multiple subagents to review PRs in parallel. But the official version isn't available to everyone, and not everyone needs it. This guide breaks down both paths: the official Code Review (Team/Enterprise only) and the self-built 9-Subagent approach (any Claude Code account), helping you find the right automated PR review strategy.
TL;DR
- Official Code Review: Team/Enterprise only, 5-step GitHub integration, $15-25/review, multi-agent parallel analysis, false positives < 1%, results in 20 minutes
- Self-built 9-Subagent: Any paid account, drop a slash command in
.claude/commands/, fees are just API tokens, runs locally, ~75% of suggestions actionable - REVIEW.md: Place in repo root for automatic activation, use Always check / Style / Skip format — more focused than CLAUDE.md for review scenarios
- Cost tip: Use Manual trigger mode (avoid "After every push") and set a monthly spending cap
Official vs. Self-Built: Find Your Path First
Before diving into setup, clarify which approach fits your situation:
| Dimension | Official Code Review | Self-Built 9-Subagent |
|---|---|---|
| Account requirement | Team / Enterprise only | Any paid Claude Code account |
| Platform support | GitHub only | Local execution, platform-agnostic |
| Billing | $15-25 / review (extra usage) | API token consumption only |
| Trigger | Automatic (PR open or each push) or manual @claude | Manual /code-review slash command |
| Review location | GitHub PR inline comments | Local terminal |
| Setup complexity | Admin panel 5 steps, no code needed | Requires writing .claude/commands/ prompt |
| Full codebase context | Yes (entire repo) | Yes (Claude Code has local repo) |
| Bug detection rate | 84% (official large-PR internal test) | ~75% (community testing) |
Decision framework:
- Have Team/Enterprise + primarily use GitHub → Official (zero setup, auto-trigger, results directly on PR page)
- Individual developer, Pro account, GitLab/Bitbucket user → Self-built 9-Subagent
- Hybrid: run /code-review locally first, then let the official version catch any remaining issues
Setting Up Official Code Review: 5-Step GitHub Integration
The entire setup happens in the claude.ai admin panel — no CLI required. Two permissions needed: Claude org admin and GitHub org admin.
Step 1: Go to claude.ai/admin-settings/claude-code, find the Code Review section, and click Setup.
Step 2: Follow the prompts to install the Claude GitHub App to your GitHub org. The app requests read/write access to Contents and Pull Requests, which is necessary for analyzing PRs.
Note: Orgs with Zero Data Retention cannot use Code Review, as the analysis process requires temporarily storing code.
Step 3: Select the repositories to enable Code Review for. Once configured, it applies across repos without per-repo installation.
Step 4: Set the Review Behavior (trigger mode) for each repo:
- Once after PR creation: Reviews each PR once, most predictable cost, best for most cases
- After every push: Triggers on every push, highest cost — avoid unless necessary
- Manual: Only triggers when someone comments
@claude review, best for high-traffic repos or testing periods
Step 5: Open a test PR to verify. You should see a "Claude Code Review" check run appear within minutes. The first full review takes about 20 minutes.
Manual Triggering
In any mode, commenting @claude review at the top of a PR comment manually triggers a review. Requires owner / member / collaborator permissions. Doesn't work on draft PRs.
Hidden trap: In Manual mode, once someone comments
@claude review, that PR becomes automatically triggered on every subsequent push — effectively switching to "After every push" mode. Easy to miss on high-traffic repos.
REVIEW.md Template and Best Practices
Place REVIEW.md in the repository root — Claude Code Review reads it automatically, no additional configuration needed. It's additive: it extends Claude's default correctness checks without replacing them.
REVIEW.md vs. CLAUDE.md
- CLAUDE.md: Global instructions, read for all Claude Code work (interactive editing, agentic tasks)
- REVIEW.md: Only read during Code Review execution — ideal for review-specific rules
Both files can coexist. If a PR change makes CLAUDE.md outdated, Claude will flag it as needing updates.
Ready-to-Copy REVIEW.md Template
# Code Review Guidelines
## Always check
- New API endpoints have corresponding integration tests
- Database migrations are backward-compatible
- Error messages don't leak internal details to users
- Sensitive data (tokens, keys, PII) is not logged or hardcoded
## Style
- Prefer `match` statements over chained `isinstance` checks
- Use structured logging, not f-string interpolation in log calls
- Function names should be descriptive verbs, not nouns
## Skip
- Generated files under `src/gen/`
- Formatting-only changes in `*.lock` files
- Auto-generated migration files
Writing tips:
- Be specific in Always check: "New APIs need integration tests" is more useful than "write good code"
- Use Skip to reduce costs: Skipping generated files and lock files measurably reduces token consumption
- Keep Style minimal: Claude already has style preferences — REVIEW.md should only capture your codebase's specific conventions
Review findings use severity levels:
- 🔴 Normal: Bugs that should be fixed before merging
- 🟡 Nit: Minor issues, don't block merging
- 🟣 Pre-existing: Bugs present in the codebase but not introduced by this PR
Self-Built 9-Subagent Approach: The Path for Individual Developers
This approach was designed and open-sourced by engineer HAMY. A slash command in .claude/commands/ simultaneously launches 9 subagents for parallel analysis. According to HAMY's own testing, about 75% of suggestions are actionable (compared to less than 50% with a single agent).
9 Subagent Roles
| Subagent | Analysis Focus |
|---|---|
| Test Runner | Runs tests, reports pass/fail |
| Linter & Static Analysis | Runs linter, type checking |
| Code Reviewer | Up to 5 specific improvement suggestions (ranked by impact/effort) |
| Security Reviewer | Injection risks, auth issues, secrets leakage |
| Quality & Style Reviewer | Complexity, duplication, project conventions |
| Test Quality Reviewer | Test coverage ROI, behavioral vs. implementation tests |
| Performance Reviewer | N+1 queries, blocking ops, memory leaks |
| Dependency & Deployment Safety | Dependencies, breaking changes, migrations |
| Simplification & Maintainability | Conciseness, change atomicity |
Setup Steps
Step 1: Create .claude/commands/ directory in your project root
Step 2: Create .claude/commands/code-review.md defining the 9 subagent roles and parallel execution logic (reference HAMY's open-source template)
Step 3: Run /code-review in Claude Code terminal
Claude auto-determines review scope (priority order):
- Scope you specify (e.g.,
/code-review auth/) - Feature branch vs. main diff
- Staged changes
- Most recent commit
Step 4 (optional): Define coding conventions in CLAUDE.md or your project style guide — all 9 subagents will read them automatically
Final output verdict: Ready to Merge / Needs Attention / Needs Work, with each agent's analysis summary.
Cost Calculation and ROI Evaluation
Official Code Review Costs
Each review costs $15-25 (varies with PR size and codebase complexity), billed as extra usage — doesn't count toward your plan's included usage. Set a monthly spending cap at claude.ai/admin-settings/usage.
| Scale | Calculation | Monthly estimate |
|---|---|---|
| 10-person team, 3 PRs/day, 20 workdays | $20 × 60 reviews | $1,200-1,500/month |
| 50-person team, 10 PRs/day | $20 × 200 reviews | $4,000/month |
| 100-person team, 1 PR/person/day | $20 × 2,000 reviews | $40,000/month |
Comparison with CodeRabbit
| Claude Code Review | CodeRabbit | |
|---|---|---|
| Billing | $15-25/review (usage-based) | $12-24/person/month (annual plans) |
| Speed | ~20 minutes | ~2 minutes |
| Detection rate | 84% (large PR internal testing) | Not disclosed |
| Platforms | GitHub only | GitHub, GitLab, Bitbucket |
| Codebase context | Entire repo | Changed lines only |
| Personal/Pro plans | Not available | Available (including free tier) |
When Claude Code Review's premium is worth it:
- Large PRs, complex codebases, security reviews requiring cross-file context
- Heavy AI-generated code usage, low tolerance for false positives (Claude < 1%)
- Existing Team/Enterprise subscription — treat Code Review as an add-on
When CodeRabbit is more cost-effective:
- Small to mid-sized engineering teams (< 30 people) — fixed monthly fee is easier to budget
- GitLab or Bitbucket support required
- Faster review turnaround needed (2 minutes vs. 20 minutes)
Limitations and Trade-offs
Official Code Review Limitations
Not suitable for:
- Individual developers and Pro account users (no access)
- GitLab or Bitbucket teams (not supported as of March 2026)
- Fast-merge workflows (20 minutes is too slow — the PR may already be merged)
- Orgs with Zero Data Retention requirements
Suitable for:
- Large teams with high proportions of AI-generated code needing deep security and logic review
- Team/Enterprise subscribers already on GitHub wanting zero-setup automation
- Strict code quality workflows emphasizing low false positive rates (< 1%)
Self-Built 9-Subagent Limitations
- Local execution only — no CI/CD auto-trigger (must manually run
/code-review) - 9 parallel agents take time and consume considerable Claude Code session resources
- Setting up and maintaining prompt templates requires additional investment
Conclusion
Claude Code PR Review marks an important milestone in 2026 — moving "can AI review AI-written code?" from concept to a directly deployable tool. The official version wraps Anthropic's multi-agent capabilities into a native GitHub experience for teams on Team/Enterprise; the self-built version offers individual developers and small teams a path that doesn't require premium subscriptions.
I use Claude Code's subagent functionality in Shareuhack's agent system, and the practical experience is clear: parallel analysis catches significantly more issues than a single agent, especially at the intersection of security and test coverage review. If your codebase already has substantial AI-generated code, automating PR review is a worthwhile investment.
Next steps:
- Team/Enterprise users: Start the 5-step setup at claude.ai/admin-settings/claude-code — use Manual mode for the first week to monitor costs and effectiveness
- Individual/Pro users: Start with HAMY's self-built 9-Subagent tutorial — you can run your first review within 30 minutes
FAQ
Can individual developers use Claude Code PR Review without a Team/Enterprise account?
The official managed Code Review service is limited to Team/Enterprise plans. But individual developers have three alternatives: (1) Self-built 9-Subagent approach — add a slash command to .claude/commands/, run /code-review locally, fees are just API token consumption; (2) GitHub Actions + anthropics/claude-code-action — only requires an Anthropic API key; (3) GitLab users can use the official CI/CD beta integration. For most individual developers, the self-built 9-Subagent approach is the most direct path.
Can choosing the wrong trigger mode really cause bill spikes? What's the most cost-effective setting?
Yes. Selecting 'After every push' means 20 pushes to one PR equals $300-500. The most cost-effective strategy: start with Manual mode (only triggers when someone comments @claude review); be aware that once Manual mode triggers, that PR becomes push-triggered for all subsequent pushes — easy to miss. Also set a monthly spending cap in admin settings to prevent unexpected overages.
Does Claude Code PR Review support GitLab or Bitbucket?
The official managed Code Review service only supports GitHub as of March 2026. GitLab has an official CI/CD beta integration (configure in .gitlab-ci.yml with ANTHROPIC_API_KEY), which doesn't require Team/Enterprise and can perform basic reviews but needs manual prompt setup. Bitbucket has no official support, only community DIY solutions. If your team primarily uses GitLab or Bitbucket, CodeRabbit is a more mature option with native support for all three platforms.
