Opc Architecture

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.

skills.sh installs: 497
GitHub stars: 3.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add parcadei/continuous-claude-v3 --skill opc-architecture --agent claude-code

Installs into .claude/skills of the current project.

Files

OPC Architecture Understanding

OPC (Orchestrated Parallel Claude) extends Claude Code - it does NOT replace it.

Core Concept

Claude Code CLI is the execution engine. OPC adds orchestration via:

Hooks - Intercept Claude Code events (PreToolUse, PostToolUse, SessionStart, etc.)
Skills - Load prompts into Claude Code
Scripts - Called by hooks/skills for coordination
Database - Store state between Claude Code instances

How Agents Work

When you spawn an agent:

Main Claude Code instance (your terminal) runs hook on Task tool
Hook calls subprocess.Popen(["claude", "-p", "prompt"])
A NEW Claude Code instance spawns as child process
Child runs independently, reads/writes to coordination DB
Parent tracks child via PID in DB

$ claude                         ← Main Claude Code (your terminal)
    ↓ Task tool triggers hook
    ↓ subprocess.Popen(["claude", "-p", "..."])
        ├── claude -p "research..."   ← Child agent 1
        ├── claude -p "implement..."  ← Child agent 2
        └── claude -p "test..."       ← Child agent 3