What problem does it solve? Long sessions quietly turn assumptions into facts, and confident answers are not always correct ones. This Skill forces every non-trivial decision through an adversarial fresh-context review while course-correction is still cheap, catching hidden failure modes before they reach production. ## Core Features & Use Cases - Five-step doubt cycle: CLAIM the decision, EXTRACT the smallest reviewable artifact plus contract, DOUBT it with an adversarial fresh-context reviewer, RECONCILE findings by precedence, and STOP at a bounded condition (trivial findings, 3 cycles, or user override). - Cross-model escalation: In interactive sessions it always offers a second opinion via external CLIs like Gemini or Codex, with read-only sandboxing and stdin piping to avoid shell injection. - Use Case: Before committing a new caching layer claimed to be thread-safe, extract the diff and its contract, hand them to an adversarial reviewer, classify each finding as contract misread, actionable, trade-off, or noise, and iterate until findings are trivial. ## Quick Start Ask the agent to apply doubt-driven development to stress-test the architectural decision or code change you are about to commit.
