A cross-vendor agent loop: Claude Fable 5 as architect, GPT-5.5 Codex as builder
/architect: Reduce Fable tokens by 80%, Fable orchestrates/reviews, Codex builds
Dan McInerney open-sourced a Claude Code skill that chains Claude Fable 5 and GPT-5.5 Codex into a division-of-labor loop. Claude plans and reviews, Codex writes code, and the repo acts as memory. The author claims an 80% reduction in Fable token usage, but the post doesn't include benchmarks or comparison data—just the README and code, so real-world results are unverified.
Why it matters: Dan McInerney open-sourced a Claude Code skill where Claude splits tasks and reviews code, GPT writes it and the repo acts as memory, showing a cross-model split of programming work.