question

A set of questions for examining a belief, idea, or claim from several angles. The categories cover meaning, assumptions, evidence, consequences, and opposing views.

In plain words
What is it for?
Use it to question a proposal, opinion, explanation, or decision. It generates prompts for clarification, evidence checking, implications, and counterarguments.
Why use it?
It helps expose what a claim depends on and what evidence supports it. This makes it easier to notice weak reasoning or consider alternatives.

Command

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 commands/neurofoo/agent-skills/question
Clone the repo
git clone --depth 1 https://github.com/neurofoo/agent-skills
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 428 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 $0.00000 $0.00428
Opus 5 $0.00000 $0.00214
Sonnet 5 $0.00000 $0.00086
Haiku 4.5 $0.00000 $0.00043

Measured 2d ago against content hash 8276baf8e0cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

question 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.

socratic/commands/question.md · 83 lines

What it actually says

Probing Questions

Generate thought-provoking questions to examine a belief, idea, or claim more deeply.

Instructions

Create questions across multiple categories that would help someone think more deeply about the topic. Focus on uncovering assumptions and exploring implications.

Output Format

Topic: [What we're questioning]


Clarifying Questions

Getting clear on what's being claimed

  1. What do you mean by "[key term]"?
  2. Can you give me a specific example?
  3. How would you define [term] differently from [similar term]?

Assumption Questions

Surfacing hidden beliefs

  1. What would have to be true for this to be correct?
  2. Why do you assume [X]?
  3. Is [assumption] always true, or just sometimes?

Evidence Questions

Examining the basis for the claim

  1. How do you know this?
  2. What evidence would change your mind?
  3. Where does this information come from?

Implication Questions

Following the logic forward

  1. If this is true, then what else must be true?
  2. What happens if we take this to its logical extreme?
  3. How does this apply in [different context]?

Counter Questions

Considering alternative views

  1. What would someone who disagrees say?
  2. Can you think of a case where the opposite is true?
  3. What's the strongest argument against this?

Meta Questions

Questioning the question

  1. Why does this matter?
  2. Is this the right question to be asking?
  3. What are we really trying to understand?

Top 3 Most Powerful Questions If you could only ask three:

  1. [Question]
  2. [Question]
  3. [Question]

Guidelines

  • Good questions create discomfort—that's where learning happens
  • Avoid yes/no questions; ask open-ended ones
  • Follow up on interesting answers with "Why?" and "How do you know?"
  • The best question is often the one you're afraid to ask

$ARGUMENTS

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 · 83 lines · 0 tokens per session scan A 8276baf8e0cc

Subscribe to this mod's changes

question is a command published in the GitHub repository neurofoo/agent-skills (111 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 428 tokens. 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.