llm-council

SKILL.md

Multi-agent planning council that orchestrates independent implementation plans, anonymizes them, then merges into one final plan.

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

LLM Council Skill

Quick start

Always check for an existing agents config file first ($XDG_CONFIG_HOME/llm-council/agents.json or ~/.config/llm-council/agents.json). If none exists, tell the user to run ./setup.sh to configure or update agents.

The orchestrator must always ask thorough intake questions first, then generates prompts so planners do not ask questions.

Even if the initial prompt is strong, ask at least a few clarifying questions about ambiguities, constraints, and success criteria.

Tell the user that answering intake questions is optional, but more detail improves the quality of the final plan.

Use python3 scripts/llm_council.py run --spec /path/to/spec.json to run the council.

Plans are produced as Markdown files for auditability.

Run artifacts are saved under ./llm-council/runs/<timestamp> relative to the current working directory.

Configure defaults interactively with python3 scripts/llm_council.py configure (writes $XDG_CONFIG_HOME/llm-council/agents.json or ~/.config/llm-council/agents.json).