Thanks for sharing this post about Cook CLI. I like how it uses a recipe-based pattern to define workflows declaratively, making orchestration simpler and cleaner. Great approach to handling execution!
IMO the raw Claude CLI is great for one-off interactive sessions, but as soon as you want repeatable multi-step workflows you’re either copy-pasting prompts forever or hacking your own solution manually. That’s exactly the gap these tools fill.
My take on a solution for this is https://ossature.dev — .smd spec markdown files + ossature audit / build that gives you DAG orchestration, SHA-traced increments, and tiny focused contexts.
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.
My take? I like it. It's concise enough for me to try it out. And I love the webpage.
[1] https://github.com/rjcorwin/cook/blob/main/no-code/SKILL.md
But in general this is meta to the CLI agent.
So if you were to use the CLI to perform a review of some code. This tool would allow you to loop the output of the code review 5 times onto itself.
My take on a solution for this is https://ossature.dev — .smd spec markdown files + ossature audit / build that gives you DAG orchestration, SHA-traced increments, and tiny focused contexts.
Where are people finding time for these sort of projects.
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.