llm-council

Multi-agent planning council that orchestrates independent implementation plans, anonymizes them, then merges into one final plan. Use agents.planners to define any number of planning agents, and optionally agents.judge to override the judge. If agents.judge is omitted, the first planner config is reused as the judge. If agents is omitted in the task spec, the CLI will use the user config file when present, otherwise it falls back to the default council. Example with multiple OpenCode models: Custom commands (stdin prompt) can be used by setting kind to custom and providing command and prompt_mode (stdin or arg). Use extra_args to append additional CLI flags for any agent. See references/task-spec.example.json for a full copy/paste example. - Supports configurable planner agents (Codex, Claude, Gemini, OpenCode, or custom CLI commands) running in parallel, with optional judge override - Conducts structured intake questioning before plan generation to clarify ambiguities, constraints, and success criteria - Produces validated Markdown outputs with automatic retry logic (up to 2 attempts) and failure handling across all agents - Anonymizes and randomizes planner outputs before judging to reduce bias, then saves judge feedback and final merged plan to timestamped run directories - Always check for an existing agents config file first ( $XDG_CONFIG_HOME/llm-council/agents.json or...