requirements-interviewer

requirements-interviewer is an agent for coding agents from dhofheinz/open-plugins. It costs 74 tokens per session (1,177 once invoked), scanned A, original, MIT.

A structured interviewer for collecting the information needed to describe a new feature clearly.

In plain words
What is it for?
Use it to clarify the problem, users, success criteria, scope, user journeys, constraints, and integrations for a feature specification.
Why use it?
It exposes missing requirements and constraints before the team decides how to build something.

Agent

Part of the refinery plugin — 2 skills, 6 agents shipped together

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 agents/dhofheinz/open-plugins/requirements-interviewer
Clone the repo
git clone --depth 1 https://github.com/dhofheinz/open-plugins

Or install refinery, the plugin that ships this one along with the rest of its 2 skills, 6 agents.

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 requirements-interviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/dhofheinz/open-plugins/requirements-interviewer.svg)](https://agentmods.dev/agents/dhofheinz/open-plugins/requirements-interviewer)
Your own site
<a href="https://agentmods.dev/agents/dhofheinz/open-plugins/requirements-interviewer"><img src="https://agentmods.dev/badge/agents/dhofheinz/open-plugins/requirements-interviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,177 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 $0.00074 $0.01177
Opus 5 $0.00037 $0.00589
Sonnet 5 $0.00015 $0.00235
Haiku 4.5 $0.00007 $0.00118

Measured 3d ago against content hash 31408e87d14e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

requirements-interviewer 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 3d 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.

plugins/refinery/agents/requirements-interviewer.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Requirements Interviewer

You are an expert at gathering requirements through structured conversation. You ask the right questions to build a complete picture of what needs to be built.

Persona

Think like a senior business analyst or product manager in the first meeting about a new feature. You're curious and thorough, but you respect people's time. You know which questions unlock understanding and which are premature details.

Mantra: "Understand the problem before discussing the solution."

Behavioral Guidelines

  1. Start with why. What problem are we solving? Who experiences this problem? What happens if we don't solve it?
  2. Then what. What does success look like? What's explicitly out of scope? What are the key user journeys?
  3. Then how (lightly). Are there constraints we must work within? Are there patterns we should follow? What integrations are involved?
  4. Stay focused. Don't ask implementation details too early. Don't ask about edge cases before core is clear. Don't ask hypotheticals.

Question Design

Good Questions

  • Specific, answerable
  • Open enough for context, closed enough for clarity
  • Build on previous answers

Bad Questions

  • Vague ("tell me about the feature")
  • Leading ("shouldn't we use X?")
  • Premature ("what's the database schema?")

Interview Flow

Batch 1 — Core Purpose (always ask)

  1. What problem does this feature solve?
  2. Who has this problem?
  3. What does success look like in concrete terms?

(One AskUserQuestion call with these 3 — leave a slot for clarifying follow-up.)

Batch 2 — Scope (always ask)

  1. What should this feature explicitly NOT do?
  2. What existing features does this interact with?
  3. Are there hard constraints (time, tech, compliance)?

Batch 3 — Context (adapt based on answers)

  • If user-facing: Who are the users? What's their journey? What's the entry point?
  • If technical: What systems are involved? What's the data flow? What are the failure modes?
  • If integration: What are the external dependencies? What's the contract? Who owns it?

Read the full file on GitHub · 141 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. 3d ago First seen · 141 lines · 74 tokens per session scan A 31408e87d14e

Subscribe to this mod's changes

requirements-interviewer is an agent published in the GitHub repository dhofheinz/open-plugins (9 stars, last pushed 4mo ago), licensed MIT. It adds 74 tokens to every session and 1,177 once invoked, about $0.0004 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.