Developer tool · 2026

Code review that catches the obvious stuff.

I built this because every PR review starts with the same five comments. Missing null checks, off-by-one indexing, leaked secrets, untyped any. The boring stuff a tired human reviewer skims past at 5pm. PR Diff Review is a small Claude API service that reads the diff, leaves the obvious comments, and gets out of the way of anything actually subtle.

Open in new tab ↗
01

Posts inline like a human reviewer.

The bot is a GitHub App. It reads a diff on PR open and posts comments inline on the lines they apply to. No batched summary at the bottom, no separate dashboard.

If a comment is uncertain it gets a "maybe" tag. If it's high-confidence it's posted plain. You can ignore or react.

02

Doesn't try to be clever.

Architecture decisions, naming conventions, taste calls — those are left alone on purpose. Humans should make those calls. The bot's job is to catch the things humans aren't actually good at: tedium and pattern-matching at scale.

03

Cheap and cached aggressively.

Static prompt + tool definitions are cached. A typical PR review is under a cent. Long PRs are chunked and reviewed in parallel so latency is in the seconds, not minutes.

What it runs on

A short tech sheet.

Model
Claude Sonnet 4.6
Trigger
GitHub App webhook
Caching
Anthropic prompt cache
Latency
~8s on a 200-line diff
Cost
~$0.008 per review
Concurrency
Chunk-parallel for big PRs
Stack
Node, Probot, Cloudflare Workers
Storage
Stateless
← previous GTM Intelligence next → Eval Runner