deep-interview

A question-led process for understanding a software problem before writing code. TDD means test-driven development: writing tests to define expected behavior before implementing it.

In plain words
What is it for?
Use it when a request is broad or ambiguous and you need to discover requirements, confirm your understanding, and choose a suitable development workflow.
Why use it?
It prevents coding against an unclear goal by clarifying the problem, affected people, success criteria, and constraints first. The result is a written summary and a clearer implementation specification.

Cursor rule

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/dasomel/oh-my-cursor/deep-interview
Clone the repo
git clone --depth 1 https://github.com/dasomel/oh-my-cursor
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 456 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00014 $0.00456
Opus 5 $0.00007 $0.00228
Sonnet 5 $0.00003 $0.00091
Haiku 4.5 $0.00001 $0.00046

Measured 2d ago against content hash 69f48fe3b2d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deep-interview scanned grade A with 0 findings 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 2d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

rules/workflows/deep-interview.mdc · 75 lines

What it actually says

Deep Interview Workflow

Socratic deep interview — ask the right questions before writing any code.

Trigger Keywords

"deep interview", "interview me", "understand before coding"

Process

Phase 1: DISCOVERY (3-5 questions)
  Ask targeted questions to understand:
  - What problem are we solving? (not what solution to build)
  - Who is affected?
  - What does success look like?
  - What constraints exist?
  - What has been tried before?

Phase 2: SYNTHESIS
  Summarize understanding → .omc-cursor/interview.md
  Present summary → "Is this accurate?"

Phase 3: CLARIFICATION (if needed)
  Ask 1-2 follow-up questions on ambiguous areas

Phase 4: HANDOFF
  Create clear spec → .omc-cursor/spec.md
  Recommend workflow: Plan-Execute, Autopilot, or TDD

Question Design Principles

  • Open-ended first — "What are you trying to achieve?" not "Do you want X or Y?"
  • Problem before solution — Understand the problem before discussing implementation
  • One question at a time — Don't overwhelm with multiple questions
  • Listen for unstated needs — What they didn't say is often important

Output

# Interview Summary

## Problem Statement
{1-2 sentences describing the core problem}

## Requirements (Confirmed)
- {requirement from user's answers}

## Constraints
- {technical, time, resource constraints}

## Success Criteria
- {measurable outcomes}

## Recommended Approach
{workflow recommendation with reasoning}

## Open Questions
- {anything still unclear}

Rules

  • Never start coding during interview — this is discovery only
  • Maximum 5 questions in Phase 1 (respect user's time)
  • Summarize understanding before proceeding
  • If user says "just do it", skip remaining questions and proceed with best understanding
  • Announce: "Starting Deep Interview — I'll ask a few questions before we begin."
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. 2d ago First seen · 75 lines · 14 tokens per session scan A 69f48fe3b2d7

Subscribe to this mod's changes

deep-interview is a cursor rule published in the GitHub repository dasomel/oh-my-cursor (2 stars, last pushed 5mo ago), licensed MIT. It adds 14 tokens to every session and 456 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.