Show HN: Sphinx – A hook that quizzes you on your AI's code before shipping(sphinx-six-theta.vercel.app)
252 points by critiquebrowser 7 days ago | 89 comments
tl;dr: Sphinx is a Git pre-push hook that quizzes developers on AI-generated code before it ships, asking questions about what the diff actually does in failure scenarios. It works with Codex, Claude Code, Cursor, OpenCode, Pi, or plain Git, and runs through your existing coding agent, OpenRouter, or any OpenAI-compatible endpoint. A `sphinx yolo` escape hatch lets pushes through when needed, with skips logged.
HN Discussion:
  • ↑Acknowledges that AI coding leaves developers without understanding, suggesting the tool addresses a real problem
  • ↑Suggests expanding the concept to gate PR submissions to save reviewers' time
  • ↓The real solution is writing code yourself, not building gimmicks around AI practices
  • ~Writing quality PR descriptions achieves the same understanding benefit without a new tool
  • ↓Skeptical it will work in practice due to confirmation fatigue and agents bypassing the quiz