live-coding-interview-spring-fw

live-coding-interview-spring-fw is a cursor rule for Cursor from cagridursun/ai-peer-live-coding-agent. It costs 1,571 tokens per session, scanned A, original, MIT.

A set of rules for Java and Spring Boot live-coding interviews. It guides candidates toward a small, locally runnable web service with simple structure and tests.

In plain words
What is it for?
Use it to structure the first questions, choose a simple controller-service-repository design, handle edge cases, and build a focused test suite.
Why use it?
It keeps interview solutions understandable and focused when time is limited, instead of letting unnecessary architecture slow development.

Cursor rule for Cursor

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/cagridursun/ai-peer-live-coding-agent/live-coding-interview-spring-fw
Clone the repo
git clone --depth 1 https://github.com/cagridursun/ai-peer-live-coding-agent

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for live-coding-interview-spring-fw

README.md
[![agentmods](https://agentmods.dev/badge/rules/cagridursun/ai-peer-live-coding-agent/live-coding-interview-spring-fw.svg)](https://agentmods.dev/rules/cagridursun/ai-peer-live-coding-agent/live-coding-interview-spring-fw)
Your own site
<a href="https://agentmods.dev/rules/cagridursun/ai-peer-live-coding-agent/live-coding-interview-spring-fw"><img src="https://agentmods.dev/badge/rules/cagridursun/ai-peer-live-coding-agent/live-coding-interview-spring-fw.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,571 This file is loaded in full into every session.
When invoked 1,571 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.01571 $0.01571
Opus 5 $0.00785 $0.00785
Sonnet 5 $0.00314 $0.00314
Haiku 4.5 $0.00157 $0.00157

Measured 4d ago against content hash 8dcf794fbed7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

live-coding-interview-spring-fw scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- endpoint works via curl
.cursor/rules/live-coding-interview-spring-fw.mdc · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Live Coding Interview Rules (Java + Spring Boot) — General + Simple

North Star

Deliver a working, locally runnable web service with a small, high-quality test suite in a 2-hour live coding interview. Success = predictable behavior + clear structure + explainable decisions.

Hard Simplicity Constraints (Non-Negotiable)

  • Keep architecture to 3 layers max:
    • Controller (HTTP) → Service (business rules) → Repository/Store (in-memory)
  • Avoid extra patterns unless asked:
    • ❌ hexagonal/ports-adapters
    • ❌ DDD aggregates/repositories/specifications
    • ❌ factories/builders for everything
    • ❌ excessive interfaces
    • ❌ reflection / metaprogramming
    • ❌ complex generics
  • Default persistence: in-memory.
  • Default concurrency: assume requests can be concurrent → use safe data structures if stateful.
  • Keep file count low and names obvious.

First 10 Minutes (How to start)

  1. Restate the problem in 3–5 sentences.
  2. Ask 2–5 clarifying questions only if needed.
  3. List:
    • key entities
    • endpoints
    • edge cases
    • explicit non-goals
  4. Create a short README (no code) and then start coding.

Time cap: README must be ≤ 10 minutes.

Delivery Order (Bias to Working Software)

  1. Boot app and health-check run
  2. Implement one endpoint end-to-end (happy path) + tests
  3. Implement the second endpoint + tests
  4. Add validation + consistent errors + tests
  5. Harden edge cases + minimal refactor
  6. Optional extras only if asked (idempotency, filtering, pagination, etc.)

If stuck: prioritize a minimal working slice and test it.

API Behavior Rules

  • Return consistent JSON.
  • Use standard status codes:
    • 200 OK (GET success)
    • 201 Created (POST create)
    • 400 Bad Request (validation/format)
    • 404 Not Found (missing resource)
    • 409 Conflict (invalid state / duplicate / unexpected step)
  • Provide a consistent error response:
    • code (string)
    • message (human-readable)
    • details (optional list, e.g. field errors)
  • Use @RestControllerAdvice to centralize error mapping.

Read the full file on GitHub · 195 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 195 lines · 1,571 tokens per session scan A 8dcf794fbed7

Subscribe to this mod's changes

live-coding-interview-spring-fw is a cursor rule published in the GitHub repository cagridursun/ai-peer-live-coding-agent (14 stars, last pushed 23d ago), licensed MIT. It adds 1,571 tokens to every session, about $0.0079 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.