Sphinx adds git hook that quizzes developers on AI code before push
Sphinx is a free, open‑source git hook that asks developers a question about the behavior of AI‑generated code before the change is pushed. It works by pausing the push, presenting a scenario—such as a Stripe webhook retry—and requiring the user to explain what the code should do. The answer is not sent to the coding agent, keeping environment variables and secret keys hidden.
Key points
- Sphinx is a free, open‑source git hook that quizzes developers on AI‑generated code before a push.
- It integrates with any OpenAI‑compatible endpoint, such as OpenRouter, and supports models like Codex, Claude, Cursor, OpenCode, and Pi.
- A “yolo” mode lets pushes bypass the quiz, logging each skip while keeping .env files and keys hidden from the agent.
The hook can be installed with npm and connects to any OpenAI‑compatible endpoint, including OpenRouter, as well as models like Codex, Claude, Cursor, OpenCode, and Pi. It supports a “yolo” mode that lets pushes continue while logging each skip, allowing teams to bypass the check when necessary. Sphinx runs on Node 22.19+ on macOS, Linux, or WSL and integrates with existing Git workflows without exposing sensitive data.
Show HN: Sphinx – a hook that quizzes you on your AI's code before shipping
sphinx-six-theta.vercel.app · 18 October 2026Loading the full article…
This text was published by sphinx-six-theta.vercel.app. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
Coverage and discussion
1source- Hacker News discussion · 49 pointsnews.ycombinator.com
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Agents & Tools
All →- Things to Do API launches pay‑as‑you‑go pricing for event queries · 1 src
- Anthropic is reportedly consulting law firms on negotiation tactics for its AI agents · 1 src
- Voxel51 launches 3.0 platform for physical AI data workflows · 2 src
- Claude Code team shares how agents review code with minimal human input · 3 src
- Anomaly Innovations says breach affected about 1.4% of OpenCode Console users · 1 src
Comments
via GitHub Discussions