Council Refine — AI skill for Claude Code
/council-refine — Multi-Model Plan Refinement with Opus 4.6 Synthesis.
How to install Council Refine
Installs to ~/.claude/skills/intellegix-intellegix-code-agent-toolkit-council-refine/SKILL.md
mkdir -p ~/.claude/skills/intellegix-intellegix-code-agent-toolkit-council-refine && curl -fsSL https://raw.githubusercontent.com/intellegix/intellegix-code-agent-toolkit/HEAD/commands/council-refine.md -o ~/.claude/skills/intellegix-intellegix-code-agent-toolkit-council-refine/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Council Refine does
/council-refine — Multi-Model Plan Refinement with Opus 4.6 Synthesis
Submit a plan to 3 frontier AI models (GPT-5.2, Claude Sonnet 4.5, Gemini 3 Pro) via Perplexity API for iterative refinement, with Opus 4.6 extended thinking synthesis. Loop until convergence (score >= 8, no critical issues, score gain < 1) or max 3 iterations.
**Prerequisites**: `PERPLEXITY_API_KEY` and `ANTHROPIC_API_KEY` environment variables set. Python packages installed (`pip install perplexityai anthropic`).
Inp
Alternatives in AI
- Oil UI — Push AI UI design to its limits: explore distinct directions, compare them side by side, and refine against re 861 ★
- Flow Next — Plan-first AI workflow plugin for Claude Code, OpenAI Codex, and Factory Droid 569 ★
- Fusion Plan — OMC interview (interactive) → 3-round Opus 4.8 + GPT-5.5 fusion deepening → concise .omc/plans/ output → revie 468 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
LLM Council
A Claude Code skill that pressure-tests any decision through 5 AI advisors with anonymous peer review and a ch
Openprism
Multi-model panel and judge for research synthesis on a hard question
Cisfalcon
A live pre-synthesis specificity gate for AI-designed enhancers: a frozen external measured-activity model plu
Claude Glm Stack
Run Claude Desktop on Z.AI GLM (GLM Coding Plan) via third-party 3P gateway mode + tier-rewriting local proxy:
Vietnam Travel
A tool for AI to visualize plans on a map, a plan table, and an interactive interface with your travel plan. H
Claude GPT Workflow
Claude Code skills for Claude + GPT collaborative workflows. Adversarial plan review + orchestrated code execu
Related Agents
Plan Critic
Use WHEN a chosen direction from brainstorming needs to be pressure-tested before planning. Applies multi-lens
Backlog Grooming
Use when the user needs to groom, refine, or clean up a product backlog. Triggers on: 'groom backlog', 'backlo
Aro:Agent Opus
Generic task execution agent using Claude 4.1 Opus model for premium quality outputs. Reserved for critical de