Get quizzed on your agent's code before you are allowed to push it
Sphinx is a free open-source Git hook for agent-assisted development. When you or your agent push to a protected branch, it asks you a question about what the diff actually does, generated by your existing coding agent, OpenRouter or any OpenAI-compatible endpoint.
Source
critiquebrowser on Hacker News · 2026-10-18 · Project link
Written in our own words. Credit to the original author. Link checked 2026-10-18.
What they did
Sphinx is a free open-source Git hook for agent-assisted development. When you or your agent push to a protected branch, it asks you a question about what the diff actually does, generated by your existing coding agent, OpenRouter or any OpenAI-compatible endpoint.
Result (as claimed)
Install with npm; 165 points on Show HN.
Tools they used
Cost: Pricing depends on the tools you pick; check each official pricing page.
Set it up
Pick a contained repo or task
Start on a branch or side project where mistakes are cheap.
Install and configure
Set up OpenRouter, Git. Read what it can run on your machine and limit permissions where possible.
Run it on a real task
Give it a well-scoped issue and let it work. Review the diff like any pull request.
Add guardrails
Keep tests and CI in the loop, and never let an agent push to main or touch production secrets unattended.
Copy the full setup prompt
Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.
You are helping me set up this AI use case end to end in Claude Code. Goal: Get quizzed on your agent's code before you are allowed to push it What the original author did: Sphinx is a free open-source Git hook for agent-assisted development. When you or your agent push to a protected branch, it asks you a question about what the diff actually does, generated by your existing coding agent, OpenRouter or any OpenAI-compatible endpoint. Reported result (as claimed by the author): Install with npm; 165 points on Show HN. Source: https://news.ycombinator.com/item?id=50137950 Tools they used: OpenRouter, Git Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Codex. Goal: Get quizzed on your agent's code before you are allowed to push it What the original author did: Sphinx is a free open-source Git hook for agent-assisted development. When you or your agent push to a protected branch, it asks you a question about what the diff actually does, generated by your existing coding agent, OpenRouter or any OpenAI-compatible endpoint. Reported result (as claimed by the author): Install with npm; 165 points on Show HN. Source: https://news.ycombinator.com/item?id=50137950 Tools they used: OpenRouter, Git Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Grok Bot. Goal: Get quizzed on your agent's code before you are allowed to push it What the original author did: Sphinx is a free open-source Git hook for agent-assisted development. When you or your agent push to a protected branch, it asks you a question about what the diff actually does, generated by your existing coding agent, OpenRouter or any OpenAI-compatible endpoint. Reported result (as claimed by the author): Install with npm; 165 points on Show HN. Source: https://news.ycombinator.com/item?id=50137950 Tools they used: OpenRouter, Git Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
The Daily 5
Get five new use cases tomorrow morning
Free. Real sources. Unsubscribe any time.
Related use cases
Run Claude Code and VS Code on an iPad with a Linux layer
LinPad OS brings Linux to the iPad with git, Python, Node.js, VS Code and a terminal, and Claude Code is listed in its store.
Run your own always-on agent team on your PC with Claude Code
Unable to use Dots, Muse or Grok Bot, the author built Crew, a free open-source team of AI agents that lives on a PC, runs on Claude Code and keeps working after you walk away.
Make your coding agent show evidence before it says done
vstack is a small workflow for Claude Code and Codex based on pstack: the agent follows a state machine and must provide evidence before it can claim a task is done.
Review code at agent volume the way the Claude Code team does
The Claude Code team describes how they review code when agents write most of it: high test coverage and deep automated reviews first, then optimizing for the least human review time that does not raise reverts or incidents, with clear rules on where humans stay in the loop.