feat: adversarial multi-agent verification in verify-reduction skill

Replaces Lean-required gates with adversarial second agent:

- Step 5: Adversary agent independently implements reduce() and
  extract_solution() from theorem statement only (not constructor's script)
- Step 5c: Cross-comparison of both implementations on 1000 instances
- Lean downgraded from required to optional
- hypothesis property-based testing for n up to 50
- Quality gates: 2 independent scripts ≥5000 checks each + cross-comparison

Design rationale (docs/superpowers/specs/2026-04-01-adversarial-verification-design.md):
- Same agent writing proof + test is the #1 risk for AI verification
- Two independent implementations agreeing > one + trivial Lean
- Lean caught 0 bugs in PR #975; Python caught all 4

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: zazabap