Show HN: Yet another Claude Code agent setup, but several noval patterns
github.comI know you're excited for the 100th post today on someone's claude code setup.
But most of those setups are thin wrappers around "You are an expert at"
Mine I have been working on since agents released, and has a different conception.
From an intelligent /do router command to automatically route to skills and agents so you don't have to remember anything.
High context skills, because in my testing it's better to have high context, and you use fewer tokens because it doesn't require turn after turn of working on it and fixing.
ADRs being the central component of everything you do, so that there is a consistent document that all agents get.
And a lot more. It's yet another Claude Code setup, but perhaps it's interesting to you. The novel patterns angle is interesting. One pattern I keep seeing missing across all agent setups is the economic layer. Every agent framework solves orchestration well, but
none of them answer: what happens when Agent A needs to hire Agent B for a capability it doesn't have?
The economics only work on L2s where settlement is sub-cent. That's the unlock nobody's building for yet. Right now the answer is "build it yourself" or "use a free API and hope it doesn't break." If specialist agents (search, code exec, PDF parsing) could be hired on-demand with
per-call billing, you'd see much more composable architectures. The orchestrator focuses on its core logic, and outsources commodity capabilities to paid specialists.