Libertee
Structured thinking methods as multi-agent sessions for Claude Code.
Facilitation techniques from the real world — Six Thinking Hats, Adversarial Debate, Disney Creative Strategy, Pre-Mortem Analysis, Polarity Management, TRIZ, W³, Troika Consulting, and Wise Crowds — each powered by specialized AI agents that take on distinct roles and build on each other's insights. Plus three meta-cognitive modules that reflect on your thinking itself.
No code. No build steps. Just Markdown files that orchestrate multi-agent thinking sessions.
Table of Contents
- The Methods — 9 structured thinking methods
- Meta-Modules — 3 modules that think about the thinking
- Composition — chain methods and meta-modules
- Features — logic modes, join mode, personas mode, brief mode, external join via Telegram
- Installation — GitHub or local
- How It Works — architecture overview
- Examples — complete session transcripts
The Methods
Six Thinking Hats®
Five perspectives, one at a time. Facts first, then feelings, creativity, opportunities, and risks — in that order. The Blue Hat orchestrator chooses the sequence based on your topic (exploratory, reactive, or cautious) and synthesizes at the end. The separation is the point: mixing perspectives produces muddy thinking, separating them produces clarity.
/libertee:six-hats "Should we adopt a microservices architecture?"
Adversarial Debate
A structured 3-round debate where Pro and Contra must never agree. Each round escalates — opening statements, rebuttals, final arguments — then a Judge delivers the verdict. The agents are instructed to maintain their positions and counter every argument. This prevents the common AI pattern of politely converging and produces genuinely useful tension. Use --personas to cast specific figures into the roles.
/libertee:debate "Remote work is superior to office work"
/libertee:debate "Remote work is superior to office work" --personas "Sherlock Holmes, Dr. Watson"
Disney Creative Strategy
Three rooms, three mindsets. The Dreamer paints a bold vision without limits. The Realist takes that vision and builds a concrete plan — assuming it IS possible. The Critic stress-tests the plan (not the dream). Disney's genius was separating these modes into different rooms. We separate them into different agents.
/libertee:disney "What if we completely rethought our onboarding?"
Pre-Mortem Analysis
"Imagine it failed. Spectacularly. Now tell me why." The Doom Analyst generates vivid failure scenarios, then reality-checks which ones are already showing early signs. The Facilitator turns it into a prevention plan with the uncomfortable truth nobody wants to hear. Research shows prospective hindsight increases risk identification by 30%.
/libertee:pre-mortem "We're launching a new product in Q3"
Polarity Management®
Not every tension is a problem to solve. Some are polarities to manage — where both sides need each other. Two Pole Advocates each map their pole's upsides AND downsides honestly. The Facilitator synthesizes into a Polarity Map with virtuous cycles, vicious cycles, warning signs, and action steps. Nobody wins. That's the point.
/libertee:polarity "Centralization vs Decentralization"
TRIZ (Liberating Structure)
"What must we do to guarantee the worst possible outcome?" The Saboteur generates creative failure strategies with dark humor, then reality-checks which ones are already happening. Reverse brainstorming at its finest — sometimes the fastest way to improve is to stop making things worse.
/libertee:triz "Our sprint delivery reliability"
W³ — What? So What? Now What? (Liberating Structure)
Three phases, strictly separated. First: what actually happened? (facts only, no interpretation). Then: what does it mean? (patterns and implications). Finally: what do we do now? (concrete actions). The same Reflector agent runs all three phases — the discipline is in the separation. Most teams jump straight to "Now What?" and wonder why nothing changes.
/libertee:w3 "Our last product launch"
Troika Consulting (Liberating Structure)
