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 skills add richkuo/rk-skills --skill prd-questionsgit clone --depth 1 https://github.com/richkuo/rk-skillsWrote 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.
[](https://agentmods.dev/skills/richkuo/rk-skills/prd-questions)<a href="https://agentmods.dev/skills/richkuo/rk-skills/prd-questions"><img src="https://agentmods.dev/badge/skills/richkuo/rk-skills/prd-questions/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/richkuo/rk-skills/prd-questions"><img src="https://agentmods.dev/badge/skills/richkuo/rk-skills/prd-questions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00090 | $0.00743 |
| Opus 5 | $0.00045 | $0.00371 |
| Sonnet 5 | $0.00018 | $0.00149 |
| Haiku 4.5 | $0.00009 | $0.00074 |
Grade A, and why
prd-questions 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
prd-questions
Resolve every open decision in the PRD by asking the user directly, then fold the answers into the spec so no reader ever needs the Q&A transcript. The deliverable is a PRD whose Open Questions section is empty because the answers live in the sections they govern.
Input
A repo containing PRD.md (or a named PRD file). No other input needed.
Steps
1. Sweep for questions
Collect, in order:
- Every item in the Open Questions section.
- Inline ambiguities elsewhere ("TBD", "confirm", "assumed", hedged examples).
- Decisions embedded in Post-MVP / roadmap sections that were deferred without being decided.
"All questions" means all three groups — not just the numbered list.
2. Ask in batches
Use the AskUserQuestion tool, max 4 questions per call, sequential calls until done:
- Each question: 2–4 concrete options with real tradeoff descriptions — not "yes/no" but the actual competing designs.
- Put your recommended option first, labeled
(Recommended), and make the recommendation genuinely reasoned (privacy-preserving, simplest-correct, matches the PRD's stated priorities). - One question per decision. Never bundle two decisions into one option.
- Post-MVP questions are fair game but mark them as such in the question text, and offer "Defer to scoping" as a legitimate recommended option when deciding now has no benefit.
3. Fold answers into the spec
For every answer:
- Edit the owning section — pricing answers into the pricing tables/rules, privacy answers into the privacy section, failure-handling into billing/lifecycle. The spec text states the decision plainly; no "per user decision on " hedging inside the rule itself.
- Update worked examples to match (and remove "unverified" hedges once confirmed).
- Cross-reference where a rule spans sections (§-refs).
4. Close out
- Replace the Open Questions list with a one-paragraph note: "None — all prior open questions resolved and folded into the spec:" followed by a decision → section map.
- Commit and push (same PRD PR if still open; footer verb
Updated).
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.
- 11d ago First seen · 60 lines · 90 tokens per session scan A eec0a9ebcc61
prd-questions is a skill published in the GitHub repository richkuo/rk-skills (49 stars, last pushed yesterday), licensed MIT. It adds 90 tokens to every session and 743 once invoked, about $0.0005 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.
Other skills, from other repositories
contradiction-analysis
A structured way to analyze difficult problems by identifying competing forces, finding the main conflict, and deciding which side or issue has the greatest effect.
mass-line
A method for collecting feedback and facts from multiple people or sources, turning them into a plan, and checking the plan with those affected.
practice-cognition
A method for testing ideas in practice, learning from the results, and improving the next attempt through repeated cycles.
protracted-strategy
A long-term planning method for difficult work that cannot be completed quickly, divided into stages with steady progress over time.
concentrate-forces
A decision-making method for situations where several tasks compete for limited time, attention, computing power, or budget.
arming-thought
A Chinese-language routing guide built around checking facts before drawing conclusions. It helps select other methods for tasks such as investigation, decision-making, review, and long-term planning.