Outreach and reference-run update.
- Scored Codex reference audit run.
- JSON scorecard example.
- Public outreach log updates for benchmark-directory PRs.
Promotion and discovery update.
- GitHub Pages landing page.
- Social card artwork.
- Promotion kit with launch copy.
llms.txt,robots.txt, sitemap, and structured metadata.- Security policy and citation metadata.
Initial public benchmark release.
- ShopPay business rules in
SPEC.md. - Intentionally flawed service implementation covering orders, refunds, users, pricing, wallet, and webhooks.
- Baseline tests documenting seeded business-logic defects.
- Benchmark guide and maintainer answer key.
- Scoring rubric for comparing AI audit reports.
- Example audit report format.
- GitHub Actions test workflow.
- Maintainer roadmap and contribution guide.