Leon

Packaging agent workflows into reusable skills is the right abstraction. The hard part isn't building one-off agents — it's making them reliable enough to share. How do you handle versioning when the underlying site changes? That's where most agent skills break down in production.

This is a smart pattern for production agent systems. I've been running Sonnet as the main loop for tool-heavy workflows and the cost adds up fast when you need Opus-level reasoning on edge cases. Having the advisor as a on-demand escalation path instead of running Opus on every turn is exactly the right trade-off. Curious how the handoff latency feels in practice — does the shared context...