think-tank-dialectic

name

think-tank-dialectic

description

Hegelian dialectic (Thesis → Antithesis → Synthesis) for irreversible or high-stakes decisions with genuine stalemate — NOT a "better think-tank", a different tool for a different situation. Use when: "this decision is hard to reverse", "both sides have real merit", "genuinely torn between X and Y", "irreversible decision", "real dilemma, not just tradeoffs", "need structured dialectic", "這個決定反悔成本很高", "兩邊都有道理", "在 X 和 Y 之間拉扯", "辯證一下", "不可逆決策", "逃不掉的 tradeoff". Always reach for `think-tank` first; escalate here only when think-tank's Decision Brief shows LOW consensus AND the decision is costly to reverse. Not for: everyday scope decisions (→ think-tank), pure tech selection (→ survey), reversible tasks where you can iterate, or reflexive "let's debate this" requests.

Think Tank Dialectic — Hegelian Deliberation

Dispatch Chains (auto-injected)

!cat .claude/dispatch-config.md 2>/dev/null || true

A DIFFERENT tool than think-tank, not an upgrade: resolves genuine stalemates via Thesis → Antithesis → Synthesis. Cost is high; use is rare by design.

Hard rules (the non-negotiables):

• Never first-resort: reach for autopilot:think-tank first; escalate ONLY when its Decision Brief shows LOW consensus AND the decision is costly to reverse. Do not skip think-tank for a fresh question.
• Max 2 rounds (there is no R3); session re-entry ladder (2nd invocation on the same confirmed problem = Quick Synthesis, 3rd = refuse with the four-option exit).
• HIGH R1 consensus (≥5/6) auto-downgrades — no forced dialectic on an aligned panel.
• Synthesis is NOT a compromise; if no honest higher-order integration exists, the brief says so instead of faking one.

MUST-READ: ../think-tank/references/dialectic-mode.md — the FULL execution protocol (grounding rules 1–5, role composition + drift mitigation, STEP 0–8, brief/scorecard templates). Do not run the dialectic from this summary alone.