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.

install copies · 90 days. Times the install command was copied on this site in the last 90 days, bots filtered.: 10
skills.sh installs: 1.2K
GitHub stars: 1K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add am-will/codex-skills --skill llm-council --agent claude-code

Installs into .claude/skills of the current project.

Files

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).