Verify whether an AI agent's decision is well-reasoned before executing. Adversarial multi-model critique (Claude, Grok, DeepSeek) returns ALLOW or HOLD with confidence score. Use before any high-value swap, trade, or autonomous action.
cp -r cryptoskill/skills/payments/moonpay-official-thoughtproof-reasoning-check .claude/skills/clawhub install moonpay-official-thoughtproof-reasoning-check