rafaamaral

Nice approach to the orchestration problem. The recipe-based pattern is clean — define the workflow declaratively, let the CLI handle the execution.

One thing I've been thinking about with tools like this: as you chain more Claude Code calls, the cost compounds fast. A single "cook" run with 5-6 steps could easily burn through $10-15 in API credits if you're not careful about which model handles which step.

Has anyone experimented with routing different recipe steps to different model tiers? E.g., using Haiku for boilerplate generation and Opus only for the steps that actually need deep reasoning? That's where the real savings are in multi-agent orchestration.