This is essential reading if you're working with OPC or wondering what it actually is. It cuts through confusion by explaining that OPC isn't a standalone tool but rather an orchestration layer on top of Claude Code using hooks, skills, and a shared database. The key insight is that every "agent" is just another `claude -p` subprocess spawned by hooks intercepting Tool events, coordinating through PostgreSQL and file outputs. If you've been confused about how agents actually spawn or where coordination happens, this maps out the entire flow from your terminal command through hook execution to child process management. Read this before you try to modify anything in the OPC architecture.
npx skills add https://github.com/parcadei/continuous-claude-v3 --skill opc-architecture