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 mattgierhart/PRD-driven-context-engineering --skill prd-v10-mom-test-interviewgit clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineeringWrote 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/mattgierhart/prd-driven-context-engineering/prd-v10-mom-test-interview)<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v10-mom-test-interview"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v10-mom-test-interview/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/mattgierhart/prd-driven-context-engineering/prd-v10-mom-test-interview"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v10-mom-test-interview.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 | $0.00101 | $0.02583 |
| Opus 5 | $0.00051 | $0.01291 |
| Sonnet 5 | $0.00020 | $0.00517 |
| Haiku 4.5 | $0.00010 | $0.00258 |
Grade A, and why
prd-v10-mom-test-interview 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 10d 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mom Test Interview Discipline
Position in workflow: v1.0 Continuous Discovery (Torres) → v1.0 Mom Test Interview → v1.0 Case Study Builder, Testimonial Collector
Execution Mode
Default is standard. See .claude/rules/08-skill-execution-modes.md for selection logic.
| Mode | What this skill produces |
|---|---|
| quick | Single interview prep + question list + CFD-* discovery entry post-interview |
| standard | Interview prep + scripted opening + 5–7 questions + CFD-* entry with confidence calibration + Bad Data flagged |
| deep | Multi-interview cohort plan + cross-interview synthesis + pattern flagging at 3-mention threshold + assumption-test handoff |
Framework: The Mom Test
From The Mom Test: How to Talk to Customers and Learn If Your Business is a Good Idea When Everyone is Lying to You (Rob Fitzpatrick, 2013). Premise: People lie to spare your feelings — especially about your business idea. Learn to ask questions that get truth.
The three Mom Test rules
- Talk about their life, not your idea. Ask about how they actually live and work, not whether they'd like your hypothetical feature.
- Ask about specifics in the past, not generics or opinions about the future. "Last time you faced X, what did you do?" beats "Would you use a tool that does Y?"
- Talk less and listen more. If you're talking more than 30% of the time, you're pitching, not learning.
Three types of Bad Data to avoid
| Bad Data type | Example | Why it's bad | What to do |
|---|---|---|---|
| Compliments | "That sounds awesome!" | Politeness; not predictive | Discard; don't update confidence |
| Fluff | "I usually..." "I would probably..." | Generics, future hypotheticals | Anchor to specifics: "When did you last do that?" |
| Ideas | "You should add X" | Solution suggestions disguised as needs | Note as IDEA; ask "what would solving X enable you to do?" — get the underlying job |
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.
- 10d ago First seen · 216 lines · 101 tokens per session scan A 797961d5ffef
prd-v10-mom-test-interview is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 9d ago), licensed MIT. It adds 101 tokens to every session and 2,583 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
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution.
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
explaining-machine-learning-models
Explain trained machine learning models through feature attribution, local explanations, and behavior summaries. Use as an explicit/manual helper once a model already exists, not for training ownership, leakage auditing, or general ML strategy selection.
aiwg-regenerate-copilot
Regenerate copilot-instructions.md for GitHub Copilot with vendor-specific content only.