On 2026-10-15 Anthropic moved Claude Code’s Code Review out of research preview to general availability for Team and Enterprise organizations. Most reviews finish about 3x faster (roughly 20 minutes down to 6–10). Admins pick Quick, Standard, or Deep per repository; the Claude GitHub App auto-reviews new PRs, or anyone with write access can comment @claude review. Eligible Enterprise orgs can claim at least $10,000 in Code Review credits by January 15, 2027 (credits expire 30 days after claim).
Key Takeaways
- ✓Scope: Code Review leaves research preview for Claude Team and Enterprise; enable via Claude GitHub App and selected repos (GA announcement)
- ✓Speed: Anthropic says most reviews finish ~3x faster than preview — about 20 minutes down to 6–10 minutes
- ✓Tunable depth: admins set Quick / Standard / Deep per repo (Standard default); triggers: once on PR open, every push, or @claude review only
- ✓Pipeline: multi-agent Find → Verify → Rank → Post; inline comments + check run; never approves or blocks the PR (docs)
- ✓Billing & credits: billed on token usage credits (no flat per-review price); eligible Enterprise orgs can claim ≥$10,000 Code Review credits by Jan 15, 2027 (expire 30 days after claim)
Key Decision Metrics at a Glance
Heavy Claude Code use: compare subscription limits and API bills
Compare 40 dev plans & simulate token costs vs $20/mo subscriptions
Project Links & Resources
Direct AccessIn-Depth Technical Analysis
Why it matters
Coding agents raised write throughput; review became the bottleneck. Anthropic opened its multi-agent Code Review to Claude Code Team/Enterprise as a research preview in early October; on 2026-10-15 it went generally available for those same plans, aiming to make automated review that catches real bugs without too much noise a default gate rather than an experiment.
How it works
Reviews run on Anthropic infrastructure: parallel agents read the diff and surrounding code (Find) → verification filters false positives (Verify) → findings are deduplicated and ranked by severity (Rank) → inline comments plus a Claude Code Review check run are posted (Post). Access inside a review is read-only; it never pushes commits and never approves or blocks the PR. Admins pick Quick / Standard / Deep per repository and choose whether reviews run once on PR open, after every push, or only on @claude review. Repository REVIEW.md on the base/default branch (not the PR branch) can steer what gets flagged.
Metrics (vendor-reported)
The GA post’s hard operational claim: most reviews finish about 3x faster than preview (roughly 20 minutes down to 6–10). Quality numbers Anthropic disclosed at research-preview time—substantive comment rate rising from about 16% to 54%, incorrect findings under about 1%—were not restated as a new public GA leaderboard. Billing has no flat per-review price; spend is token usage credits that scale with review level, change size, and verification work. Treat percentages as vendor-reported; pilot average cost on your own repos before wide rollout.
How to ship it
An Owner enables Code Review in Claude Code settings, installs the Claude GitHub App, and selects repositories; developers then get automatic reviews on new PRs. Use @claude review on a PR, or /code-review in a Claude Code session on any plan for a local-session review. Not available with Zero Data Retention, HIPAA configuration, or CMEK; a Team/Enterprise Claude org is still required even if Claude Code runs via Bedrock, Google Agent Platform, or Foundry. Eligible Enterprise orgs can claim at least $10,000 in Code Review credits by January 15, 2027 (expire 30 days after claim; terms apply). Start with Once after PR creation or Manual mode on a few repos, read average cost in Admin, then expand.
Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.