feat: adversarial prompt rewrite + README + example
- Rewrite all review prompts with XML-structured adversarial stance
(role, operating_stance, attack_surface, finding_bar, calibration)
- Rename skill from codex-review to adversarial-review
- Add verbatim output rule for reviewer findings
- Improve resume prompt with adversarial re-review focus
- Add README with installation, usage, architecture, roadmap
- Add synthetic example of review output
- Inspired by openai/codex-plugin-cc (Apache-2.0) prompt structure
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>