babellisted

# babel — 5-model orchestration Execution runbook for the lead LLM launched via `/babel <task>`. Communication/packet rules: `references/protocol.md`; phase procedures: `references/patterns.md`. babel extends superpowers:brainstorming / superpowers:writing-plans / superpowers:executing-plans / superpowers:subagent-driven-development unchanged, adding only multi-model crew conventions around cdx-sol.mjs / agy_pty_wrapper.py / Workflow tools / superpowers skill set — no new process or execution code. ## Crew table | Model | Role | Invocation | |---|---|---| | Fable5 or Opus | Lead: orchestration, integration, final judgment | The session itself. Ask which one at launch (if the user wants Opus, direct them to the `/model` switch — the skill cannot switch its own model) | | Opus (when not lead) | Hardest verification/judgment | Agent tool model override | | Sonnet | Mechanical implementation, parallel exploration, first-pass screening | Agent tool / Workflow | | GPT-5.6-SOL | Independent design proposal, Build&Debug partner, when-stuck diagnosis, acceptance review | `node "$HOME/.claude/skills/cdx-sol/cdx-sol.mjs"` (tier: checkpoint=quick / design & acceptance=normal / diagnosis & critical acceptance=deep) | | agy (Gemini 3) | Third-opinion review, design-debate participant | `python3 "$HOME/.claude/skills/agy/agy_pty_wrapper.py"` (in environments where `python3` does not point at a real interpreter — e.g. the Windows WindowsApps stub — substitute `python3.13` or `py -3.13`.