Review agent-written code in layers the way the Claude Code team does
by PaperChaseWebb
The Claude Code team described how they moved most code reading to automated reviewers, kept humans for risky and directional calls, and still cut the share of reverted pull requests by more than 40% while merges doubled.
- Price
- Free
- Difficulty
- Intermediate
- Setup
- 30 min
- Format
- .md file
review-agent-written-code-in-layers-the-way-the-claude-code-team-does.md · 2 KB · direct download, no signup
What you end up with
Review has to converge: one PR went through more than fifty agent rounds overnight, so they now cap rounds at three, re-review only new diffs, and suppress repeat findings.
What you get
- A plain-language summary of the workflow
- A fill-in prompt template
- What to watch out for
- A link to the original source
Who it is for
Builders who already use AI agents and want a proven workflow they can copy into their own project.
Works with
Solid chips: the agent is named in this listing's own tools list. Dashed chip: Plain Markdown, so it also pastes into other agents such as Grok Bot, Hermes, OpenClaw or Muse. We list those as compatible by format only, not as tested.
Tools needed
Cost to run: Free with the agent plan you already use.
Time to result: One working session
How it works
Read what they did
Skim the source post linked below, then the summary on this page.
Expected: You know the setup and the one rule that made it work.
Fill in the template
Copy the prompt and replace every [bracketed] value with your own project details.
Expected: A prompt that fits your project.
Run it once and check
Run it on a small task first and confirm the result yourself before you trust it on real work.
Expected: One verified run.
Sample prompt from the pack
Adoption steps the post lists, in our words: keep a short CLAUDE.md with checks the agent can run; run /code-review and /security-review locally before a PR; add a REVIEW.md and move repeated review comments into it; require CI and add Testing, Risk and How to revert to the PR template; turn on an AI reviewer for one repo first; require every review thread resolved before merge; write risk tiers based on the change, not the author; cap review rounds; turn incidents and reverts into an eval set.
Adapted by PaperChaseWebb. Not the original author's prompt.
Free preview of the file
# Review agent-written code in layers the way the Claude Code team does PaperChase agent use case (free feed entry), version 1.0. Source: [Addy Osmani, Morgan Westlee Lunt and Qing Wang (Claude Code team, Anthropic)](https://claude.dev/blog/solving-code-review-at-anthropic/), 2026-10-15. ## What they did Addy Osmani, Morgan Westlee Lunt and Qing Wang laid out a stack of checks: the agent must show test or build output before a PR, a fresh-context subagent reviews the diff, several review agents look for bugs and a second group votes before a finding is posted, security findings block merge until fixed or dismissed with a reason, and a classifier sets a risk tier that decides whether zero, one or two humans approve. Merge queue, flags, staged release and fast rollback sit underneath. Past incidents became a daily eval for the reviewer. ## Worth knowing Review has to converge: one PR went through more than fifty agent rounds overnight, so they now cap rounds at three, re-review only new diffs, and suppress repeat findings. An agent's approval never fills a required human slot, and whoever prompted a change owns it. Internal numbers are Anthropic's own. The post is dated Oct 15 with no time; the earliest share we found on X was Oct 16 at 01:49 UTC.
Worth knowing
- Review has to converge: one PR went through more than fifty agent rounds overnight, so they now cap rounds at three, re-review only new diffs, and suppress repeat findings. An agent's approval never fills a required human slot, and whoever prompted a change owns it. Internal numbers are Anthropic's own. The post is dated Oct 15 with no time; the earliest share we found on X was Oct 16 at 01:49 UTC.
- Figures are as reported by the original author and were not re-measured by us.
Questions
Where does this come from?
A public post credited to Addy Osmani, Morgan Westlee Lunt and Qing Wang (Claude Code team, Anthropic). Source: https://claude.dev/blog/solving-code-review-at-anthropic/
Is it free?
Yes. Feed entries are free to read and download.
Details
Version 1.0 · Updated Oct 25, 2026 · Markdown version of this page
License: Personal and commercial use. Credit the original source when you share the workflow. Download terms
Related
AGENTS.md, CLAUDE.md and Cursor rules starter files
Six fill-in instruction files for coding agents (base, Next.js plus Supabase, FastAPI, browser game, CLAUDE.md pointer, scoped Cursor rules) and 8 prompts to write, trim and test your own.
Ask-first rules for AI agents: hard nos, approval cards and a test set
Paste-in rules that make an agent ask before it sends, spends, posts or deletes, define what a real yes is, and stop retries after a no, plus 12 test scenarios to check it.