Leaked Claude Code setup splits work across models, with Jev routing in about 16ms
A leaked Anthropic Claude Code setup: Sonnet 5.5 runs the main session and builds, Haiku 5.5 scans the repo in parallel, Opus 5.5 stays on call for architecture review, and Jev handles mechanical routing in about 16ms so frontier models wake only when real reasoning is needed.
WHOEVER LEAKED THIS CLAUDE CODE SETUP DESERVES A RAISE I thought the best way to use Claude Code was to just throw Opus at everything. Apparently not. Anthropic’s setup is much more interesting: → Sonnet 5.5 runs the main session and actually builds the thing → Haiku 5.5 swarms the repo for file discovery, AST scans, grep, and docs → Opus 5.5 stays in the background as the architect → Opus gets called in before big plans, after repeated test failures, and before shipping → JEV handles the boring mechanical routing in ~16ms so frontier models only wake up when real reasoning is needed so you get: Opus reviews. Sonnet builds. Haiku swarms. JEV routes. the interesting part isn’t using multiple models. it’s giving each model a different job. Instead of burning Opus context on finding files and running routine commands, you save it for the moments where architectural judgment actually matters. Plan on high.Delegate on medium. Keep Opus on call. https://x.com/beaver_0x/status/2108261141247873319/video/1
This post quotes another post: x.com/beaver_0x/status/2108261141247873319