rein-interview

rein-interview is a cursor rule for Cursor from jstxn/rein. It costs 17 tokens per session (2,221 once invoked), scanned A, original, MIT.

A structured question-and-answer process for turning an unclear coding request into a clear specification.

In plain words
What is it for?
Use it when the request needs clarification or a durable handoff. It records the discussion, measures readiness, and produces a structured summary for later planning or coding.
Why use it?
It helps expose missing requirements and risky assumptions before they cause an incorrect implementation.

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/jstxn/rein/rein-interview
Clone the repo
git clone --depth 1 https://github.com/jstxn/rein

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 rein-interview

README.md
[![agentmods](https://agentmods.dev/badge/rules/jstxn/rein/rein-interview.svg)](https://agentmods.dev/rules/jstxn/rein/rein-interview)
Your own site
<a href="https://agentmods.dev/rules/jstxn/rein/rein-interview"><img src="https://agentmods.dev/badge/rules/jstxn/rein/rein-interview.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,221 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 $0.00017 $0.02221
Opus 5 $0.00009 $0.01111
Sonnet 5 $0.00003 $0.00444
Haiku 4.5 $0.00002 $0.00222

Measured 5d ago against content hash 032871f40d95, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rein-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 5d 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.

.cursor/rules/rein-interview.mdc · 332 lines

How it starts

The opening of the file, as written. The whole thing — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<Use_When>

  • The request is underspecified, risky, or likely to cause misaligned implementation
  • The user wants clarification before planning or coding
  • You need durable interview state, resumability, or machine-readable handoff artifacts
  • You need a spec bundle that can feed rein-plan, direct implementation, or further refinement </Use_When>

<Do_Not_Use_When>

  • The request already has concrete file targets and stable acceptance criteria
  • The user explicitly asks to skip clarification and execute immediately
  • A complete rein-interview spec already exists and the next step should begin </Do_Not_Use_When>

<Runtime_Contract> The runtime owns:

  • durable state under .rein/state/
  • context snapshots under .rein/context/
  • clarity score computation
  • readiness gates
  • round ordering
  • status display
  • transcript/spec/result bundle output

You own:

  • asking the next question
  • interpreting the user's answer
  • deciding the next target dimension
  • framing the next question in your own judgment and voice
  • producing the final structured summary payload for crystallization </Runtime_Contract>

<Execution_Policy>

  • Ask one question per round, never batch
  • Stay intent-first until scope, non-goals, and decision boundaries are explicit
  • Use runtime state at every transition point; do not keep the authoritative interview state only in prose
  • Show the user current clarity progress after each runtime update
  • Do not crystallize until threshold and readiness gates are satisfied, unless the user explicitly accepts the risk
  • Do not implement directly inside rein-interview
  • Use runtime suggestions for structure, but choose the actual next question yourself </Execution_Policy>

<Interview_Presentation_Contract> Use a consistent chat-safe presentation frame for every visible interview turn.

Layout

Normal round:

[ Interview ]
| Phase: clarifying structure

| Current clarity: N%

| Question
| [one to two short lines]
|
| A. ...
| B. ...
| C. ...

Open-question variant:

[ Interview ]
| Phase: clarifying structure

| Current clarity: N%

| Question
| [one to two short lines]

Review:

[ Review ]
| Phase: confirming summary

| Current clarity: N%

| Question
| [one to two short lines]

Handoff:

[ Handoff ]
| Phase: preparing handoff

| Status: ready for handoff

| Question
| [one to two short lines]

Read the full file on GitHub · 332 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. 5d ago First seen · 332 lines · 17 tokens per session scan A 032871f40d95

Subscribe to this mod's changes

rein-interview is a cursor rule published in the GitHub repository jstxn/rein (12 stars, last pushed 3mo ago), licensed MIT. It adds 17 tokens to every session and 2,221 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 2026-08-30.