Pass a quiz on agent-written code before you push it
by PaperChaseWebb
Sphinx is a free Git hook that pauses pushes to protected branches and asks you a scenario question about the diff your agent wrote, so you only release code you actually understand.
- Price
- Free
- Difficulty
- Beginner
- Setup
- 15 min
- Format
- .md file
pass-a-quiz-on-agent-written-code-before-you-push-it.md · 2 KB · direct download, no signup
What you end up with
MIT licensed and reached the Hacker News front page with about 200 points.
What you get
- A plain-language summary of the workflow
- A fill-in prompt template
- What to watch out for
- A link to the original source
Who it is for
Builders who already use AI agents and want a proven workflow they can copy into their own project.
Works with
Solid chips: the agent is named in this listing's own tools list. Dashed chip: Plain Markdown, so it also pastes into other agents such as Grok Bot, Hermes, OpenClaw or Muse. We list those as compatible by format only, not as tested.
Tools needed
Cost to run: Free with the agent plan you already use.
Time to result: One working session
How it works
Read what they did
Skim the source post linked below, then the summary on this page.
Expected: You know the setup and the one rule that made it work.
Fill in the template
Copy the prompt and replace every [bracketed] value with your own project details.
Expected: A prompt that fits your project.
Run it once and check
Run it on a small task first and confirm the result yourself before you trust it on real work.
Expected: One verified run.
Sample prompt from the pack
From the project page: install with npm install -g sphinx-understand, run sphinx install to connect Git and your agents and choose a reviewing model, then push as usual.
Adapted by PaperChaseWebb. Not the original author's prompt.
Free preview of the file
# Pass a quiz on agent-written code before you push it PaperChase agent use case (free feed entry), version 1.0. Source: [critiquebrowser on Hacker News](https://news.ycombinator.com/item?id=50137950), 2026-10-18. ## What they did The maker built a hook where a reviewer that never saw your chat reads the diff and asks what happens when things go wrong, such as a retry or a failed payment call. A wrong answer explains why and gives a new scenario; a right answer lets the push continue. ## Worth knowing MIT licensed and reached the Hacker News front page with about 200 points. Needs Node 22.19 or newer on macOS, Linux or WSL. The project says your answers never reach the coding agent and it does not open .env files or keys. There is a skip command for emergencies, and every skip is logged.
Worth knowing
- MIT licensed and reached the Hacker News front page with about 200 points. Needs Node 22.19 or newer on macOS, Linux or WSL. The project says your answers never reach the coding agent and it does not open .env files or keys. There is a skip command for emergencies, and every skip is logged.
- Figures are as reported by the original author and were not re-measured by us.
Questions
Where does this come from?
A public post credited to critiquebrowser on Hacker News. Source: https://news.ycombinator.com/item?id=50137950
Is it free?
Yes. Feed entries are free to read and download.
Details
Version 1.0 · Updated Oct 25, 2026 · Markdown version of this page
License: Personal and commercial use. Credit the original source when you share the workflow. Download terms
Related
AGENTS.md, CLAUDE.md and Cursor rules starter files
Six fill-in instruction files for coding agents (base, Next.js plus Supabase, FastAPI, browser game, CLAUDE.md pointer, scoped Cursor rules) and 8 prompts to write, trim and test your own.
Ask-first rules for AI agents: hard nos, approval cards and a test set
Paste-in rules that make an agent ask before it sends, spends, posts or deletes, define what a real yes is, and stop retries after a no, plus 12 test scenarios to check it.