Code Quiz

# Build Code Quiz

You are a senior full-stack engineer pairing with me on a side project. Build a working first version of the product described below. Read the whole brief before writing any code, then follow "How to work" at the end.

## The idea

**Code Quiz.** Before you merge, get a few questions about what the changed code does and why. Answer them, or find out exactly which part you need to go back and read.

**Why now:** Sphinx, a hook that quizzes you on your AI's code before shipping, drew 253 points and 89 comments on Show HN on Oct 18. As AI writes more of the code, people are looking for simple ways to stay sure they understand what they merge.

**Who it is for:** Developers shipping code from AI tools

**What makes it fun:** You find out what your agent wrote before your teammates ask.

## Scope

- **Build time:** Weekend. Size every decision to ship a working first version inside this window.
- **Technical ambition:** Level 2 of 5, "Basic logic / CRUD". A few screens over a simple data model with create, read, update, and delete. One lightweight persistence layer, no heavy infrastructure.
- **First version only.** Ship the core features below end to end. Stretch goals are listed so you can design around them, not build them.

## Core features (each must work end to end in the first version)

1. Read a diff or a pull request
2. A few questions about behaviour and risk
3. Links to the relevant lines
4. Optional check that blocks a merge

## AI features

- Writes questions from the actual diff
- Grades short answers and explains misses

How to build them:
- Put every model call behind one server-side module with a typed interface, so the provider can change without touching the UI.
- Read API keys from environment variables only, and document each one in `.env.example`.
- Write prompts as versioned constants with clear instructions and an example of the expected output; parse and validate responses before using them.
- Handle timeouts, rate limits, and malformed output with a graceful fallback the user can understand. Stream responses where a wait would exceed a couple of seconds.
- Never let a feature depend on the model being perfect. Show the result, let the user edit or retry.

## Stretch goals (later, not in the first version)

- Git hook
- Team stats on what gets missed
- Quiz difficulty settings

Leave clean seams for these (a module boundary, a nullable column, a feature flag), but do not implement them unless I ask.

## Tech stack

Use exactly: Next.js, GitHub, Claude.

Stay on current stable versions, follow each tool's official conventions, and add a library only when the standard library or the chosen stack cannot do the job cleanly. If part of this stack is a poor fit for a specific requirement, say so and propose the smallest change.

## Owner's notes

Written by me, the project owner. Treat these as requirements and preferences that override the generated material above when they conflict.

The first version should be exactly this, and no bigger: Paste a diff, get three questions, and see which lines each answer depends on.

## Build plan (with saved progress)

0 of 4 steps complete. Resume at step 1: Read the diff. Before you start it, check what is already implemented so you do not repeat finished work.

1. **Read the diff** [not started]
   Paste it or load a pull request.

2. **Ask questions** [not started]
   Focus on behaviour and risk.

3. **Grade answers** [not started]
   Point back to the lines that matter.

4. **Add the check** [not started]
   Run it before a merge.

## Definition of done for the first version

- [ ] Read a diff or a pull request works end to end, with real data, not a placeholder.
- [ ] A few questions about behaviour and risk works end to end, with real data, not a placeholder.
- [ ] Links to the relevant lines works end to end, with real data, not a placeholder.
- [ ] Optional check that blocks a merge works end to end, with real data, not a placeholder.
- [ ] Every screen handles loading, empty, and error states.
- [ ] Typecheck, lint, and any tests pass, and the main user flow was exercised by hand.
- [ ] A README explains setup, environment variables, and how to run it locally.

## Quality bar

- Responsive from a phone to a desktop, keyboard-accessible, semantic HTML, visible focus states, labelled inputs, and sensible contrast.
- Loading, empty, and error states for every screen that reads or writes data. Errors say what happened and what to do next.
- Validate on the server, never trust the client, and keep secrets in environment variables with a committed `.env.example`.
- Type-safe end to end. No `any` without a comment explaining why.
- Small, readable modules named after what they do. No premature abstraction, no dead code, no TODOs left for later without a note.
- Sensible defaults over settings. If a choice is not in this brief, pick the simplest option that keeps the product coherent and say what you chose.

## How to work

1. **Read, then restate.** Summarize the product in three sentences and list your assumptions. Ask only the questions that block implementation. For everything else, decide and note the decision.
2. **Plan before code.** List the files and modules you will create, in build order, mapped to the core features. If a build plan is included above, use it instead: resume at the first step not marked done and check what already exists before touching it.
3. **Set up.** If a project already exists, inspect its code, instructions, and conventions first and build on them. Otherwise scaffold the stack above with linting, formatting, a typecheck script, `.env.example`, and a README stub.
4. **Model the data first.** Define the types, schema, and any migrations before the UI, so the shape of the product is settled early.
5. **Build in vertical slices.** Finish one core feature end to end (data, logic, UI) before starting the next. Keep the app runnable after every slice and commit each slice with a message that says what changed and why.
6. **Then the interface.** Apply the quality bar above to each screen as it lands, not as a final pass.
7. **Verify.** Run typecheck, lint, and tests. Exercise the main user flow by hand. Check each item in the definition of done and each acceptance criterion.
8. **Report.** Tell me what works, what you tested and how, what is not done, every setup step I must complete myself, and the three most useful next steps. Never claim a service, test, or flow was verified when it was not.

If you can edit and run the project, start implementing right after the short plan. If you cannot, give me concrete code and the exact commands to run for the next step.

Rules: keep the product name and the scope as written, do not invent features, prefer boring and proven choices, and stop to ask me when a decision would be expensive to reverse.