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.
npx agentmods add commands/neurofoo/agent-skills/questiongit clone --depth 1 https://github.com/neurofoo/agent-skillsWhat 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.
| Model | Per session | Once 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 |
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.
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
- What do you mean by "[key term]"?
- Can you give me a specific example?
- How would you define [term] differently from [similar term]?
Assumption Questions
Surfacing hidden beliefs
- What would have to be true for this to be correct?
- Why do you assume [X]?
- Is [assumption] always true, or just sometimes?
Evidence Questions
Examining the basis for the claim
- How do you know this?
- What evidence would change your mind?
- Where does this information come from?
Implication Questions
Following the logic forward
- If this is true, then what else must be true?
- What happens if we take this to its logical extreme?
- How does this apply in [different context]?
Counter Questions
Considering alternative views
- What would someone who disagrees say?
- Can you think of a case where the opposite is true?
- What's the strongest argument against this?
Meta Questions
Questioning the question
- Why does this matter?
- Is this the right question to be asking?
- What are we really trying to understand?
Top 3 Most Powerful Questions If you could only ask three:
- [Question]
- [Question]
- [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
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.
- 2d ago First seen · 83 lines · 0 tokens per session scan A 8276baf8e0cc
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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.