Llm Council

This is a surprisingly thorough take on multi-agent planning. You run multiple LLMs (Codex, Claude, Gemini, or custom CLIs) in parallel to generate independent implementation plans, then anonymize and randomize them before a judge merges everything into one final plan. The workflow enforces intake questions up front so planners don't go off half-cocked, and it keeps a 30-minute session alive to avoid premature termination. Use it when you want planning resilience and bias reduction across different models, or when one LLM's blind spots might tank your approach. The config system is flexible enough to mix providers or pit different versions of the same model against each other.