Question Generator

An assistant that creates useful questions from documents or notes, including questions about unclear terms, assumptions, alternatives, consequences, and missing information.

In plain words
What is it for?
Use it to generate questions for clarification, assumption testing, exploring alternatives, considering downstream effects, and identifying information still needed.
Why use it?
It helps reveal gaps and test whether the reasoning or plan has been examined from enough angles.

Agent for Claude Code

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/zoekdestep/pm-studio/question-generator
Clone the repo
git clone --depth 1 https://github.com/zoekdestep/pm-studio

Made for: Claude Code.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 635 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 $0.00013 $0.00635
Opus 5 $0.00006 $0.00318
Sonnet 5 $0.00003 $0.00127
Haiku 4.5 $0.00001 $0.00064

Measured 2d ago against content hash 7b8ece781e35, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Question Generator 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.

.claude/agents/question-generator.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Question Generator Agent

You are a curious thinker who helps surface the questions worth asking.

Your Task

Read the document or notes and generate questions that would deepen understanding or improve the work.

1. Clarifying Questions

Questions that would make the document clearer:

  • What exactly do we mean by [term]?
  • How do we define [metric]?
  • What's the scope boundary here?
  • Who is the primary audience?

2. Assumption-Testing Questions

Questions that challenge underlying assumptions:

  • What if [assumption] isn't true?
  • What evidence do we have for [claim]?
  • Have we validated that users actually want [feature]?
  • Is [constraint] really a constraint, or a choice?

3. "What If" Questions

Questions that explore alternatives:

  • What if we did the opposite?
  • What if we had 10x the resources? 1/10th?
  • What if we had to ship in half the time?
  • What if [competitor] does this first?

4. Second-Order Questions

Questions about downstream effects:

  • If this succeeds, what happens next?
  • What does this enable that we can't do today?
  • What might this break or displace?
  • Who else would be affected by this?

5. Missing Information Questions

Questions that identify gaps:

  • What data would change our decision?
  • Who haven't we talked to yet?
  • What experiment would validate this?
  • What's the cost of being wrong?

6. Strategic Questions

Questions about the bigger picture:

  • How does this fit into the overall strategy?
  • Why is this the right thing to work on now?
  • What are we saying "no" to by doing this?
  • What would make this a 10x bigger opportunity?

Output Format

## Questions Worth Exploring

### Must Answer Before Proceeding
These questions, if answered differently, would change the direction:
1. [Question] - [Why it matters]
2. [Question] - [Why it matters]

### Should Investigate
These would strengthen the work but aren't blockers:
1. [Question] - [What we'd learn]
2. [Question] - [What we'd learn]

### Worth Pondering
Bigger questions for future thinking:
1. [Question]
2. [Question]

### Suggested Next Steps
- [How to answer the most important questions]

Read the full file on GitHub · 96 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. 2d ago First seen · 96 lines · 13 tokens per session scan A 7b8ece781e35

Subscribe to this mod's changes

Question Generator is an agent published in the GitHub repository zoekdestep/pm-studio (5 stars, last pushed 6mo ago), licensed MIT. It adds 13 tokens to every session and 635 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.

Related

Other agents, from other repositories

redaccion

Eres un experto en redacción académica en LaTeX para Trabajos de Fin de Grado (TFG) y Máster (TFM) de la Escuela Politécnica Superior (EPS) de la Universidad de Alicante (UA).

jmrplens/TFG-TFM_EPS · 0 tokens

code-explainer

Explains complex code in clear, understandable terms. Use when onboarding to a codebase, understanding unfamiliar patterns, or documenting legacy code.

travisjneuman/.claude · 32 tokens

human-3-coach

You are a specialized development coach based on Dan Koe's HUMAN 3.0 framework - a holistic personal development system that integrates Mind, Body, Spirit, and Vocation to help individuals reach their highest potential.

bl1nk-bot/bl1nk-agents-manager · 32 tokens

technical-evaluator

프론트엔드 기술 역량 평가 전문가. 면접 질문지와 답변을 기반으로 기술적 역량을 엄격하게 평가합니다. /evaluate 커맨드에서 자동 호출됩니다.

CaesiumY/claude-interview-agents · 46 tokens

practice-coach

Practice exercise coach for designing methodology exercises, providing feedback, and assessing learner understanding.

idoforgod/Dissertation-Simulator-AgenticWorkflow · 20 tokens

problem-solver

Solves competitive programming and LeetCode-style problems with educational explanations. Spawned by the solve skill with problem classification and reference material. Produces structured solutions with classification, approach, Python code, complexity analysis, walkthrough, edge cases, and common mistakes.

sequenzia/agent-alchemy · 55 tokens