“Outsource your thinking, not your understanding .”
Sphinx is a Git hook for agent-assisted development. Before your agent’s code ships, it asks you a question about what that code actually does.
Built to run on minimal tokens, from your existing coding agent, OpenRouter, or any OpenAI-compatible endpoint.
Your webhook handler now saves the event ID before calling charge() . Stripe times out and sends the same event again. What happens on the retry?
It runs twice, so the customer is charged twice.
Not quite. The retry finds the saved ID and returns 200 without charging. But that ID is stored before the charge succeeds. If charge() fails, what does the next retry do?
It skips the charge, so the customer is never billed.
An illustrative exchange. Real questions come from your diff.
01 You push. Or your agent does. Git pauses on the branches you protect.
02 Sphinx asks. A reviewer that never saw your chat reads the diff and asks what the change does when things go wrong.
03 You answer. Get it wrong and you learn why, then try a new scenario. Get it right and the push continues.
Works with Codex, Claude Code, Cursor, OpenCode, and Pi , or plain Git. Your answers never reach the coding agent, and .env files and keys are never opened. In a hurry? sphinx yolo lets pushes through, and every skip is logged.
Start in a minute.
# Node 22.19+ · macOS, Linux, or WSL npm install -g sphinx-understand sphinx install # then push as usual git push
sphinx install connects Git and your coding agents and asks which model should review. Read the docs for everything else.