Sphinx
A hook that quizzes you on your AI's code before shipping
Are you the maker of Sphinx? Claim this listing
What is Sphinx?
Sphinx is A hook that quizzes you on your AI's code before shipping It's designed for developers and teams who want a habit check that they understand agent-written changes.
About Sphinx
Key Strengths
- Pauses pushes to protected branches and quizzes you on what the diff does when things go wrong before letting it through
- Questions come from a separate reviewer model that never saw the chat that wrote the code
- Free and MIT-licensed; works with Claude Code, Codex, Cursor, OpenCode, Pi or plain Git
Limitations to Consider
- Your changed code goes to the reviewer provider, and there's no default cap on model calls (about 5 to 8 requests per check)
- Easy to bypass by design: the README calls it practice, not a security gate, and 'sphinx yolo' skips checks
- Installs a global Git hook for every repo on the machine and can hold a push for up to 25 minutes; HN commenters doubted the approach and noted the name clash with the Sphinx docs tool
Best For
Developers and teams who want a habit check that they understand agent-written changes.
Skip it if: You need an enforced review gate, or you can't send code to a model provider.
Pricing
flexible pricing options
Free and open source (MIT). Reviews run on your Claude Code or Codex plan, or a separately billed OpenRouter or OpenAI-compatible API. (checked Oct 19, 2026)
Sources
- https://sphinx-six-theta.vercel.app/
- https://github.com/parthh01/sphinx
- https://news.ycombinator.com/item?id=50137950
Pros, cons and pricing compiled from public sources (official pricing/docs pages, published reviews, user reports), not hands-on testing.
Compare Sphinx
Similar Tools in AI Coding Assistants
Plimsoll, a self-hosted sandbox for code your AI agent writes
A sandbox service for running untrusted, agent-authored code that reports the isolation boundary each run executed behind. Lessons, no clone needed: https://plimsollmark.github.io/plimsoll/trainers/ - plimsollmark/plimsoll
Try Plimsoll, a self-hosted sandbox for code your AI agent writesSpecification First Agentic Development Plugin and Prove
Spec-first agentic development is specification-driven development for AI coding agents: reviewed specs, isolated worktrees, gated commits.
Try Specification First Agentic Development Plugin and ProveFrequently Asked Questions
What is Sphinx?
Sphinx is A hook that quizzes you on your AI's code before shipping It's designed for developers and teams who want a habit check that they understand agent-written changes.
How much does Sphinx cost?
Sphinx offers flexible pricing options You can check pricing on their official website.
Who should use Sphinx?
Sphinx is best suited to developers and teams who want a habit check that they understand agent-written changes.