llm-council - Multi-Planner Council for Robust Implementation Planning
Run a council of planners and judges to synthesize robust implementation plans from multiple candidate plans
Tags
Updated: 2026-03-09Capabilities
Typical Inputs
Typical Outputs
What this skill does
- create run directory
- save task brief
- spawn planner subagents
- run judge subagent
- anonymize planner outputs
- randomize plan ordering
- generate implementation plan
- store council artifacts
Inputs
- repository files
- .autolab context
- user intake answers
- council configuration
Outputs
- task brief file
- planner outputs
- judge output
- final plan file
- run summary file
Requirements
- explicit user invocation
- run directory creation permission
- parallel subagent execution capability