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 lucasheriques/shipmate --skill mom-testgit clone --depth 1 https://github.com/lucasheriques/shipmateWrote 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/lucasheriques/shipmate/mom-test)<a href="https://agentmods.dev/skills/lucasheriques/shipmate/mom-test"><img src="https://agentmods.dev/badge/skills/lucasheriques/shipmate/mom-test/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/lucasheriques/shipmate/mom-test"><img src="https://agentmods.dev/badge/skills/lucasheriques/shipmate/mom-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00072 | $0.02332 |
| Opus 5 | $0.00036 | $0.01166 |
| Sonnet 5 | $0.00014 | $0.00466 |
| Haiku 4.5 | $0.00007 | $0.00233 |
Grade B, and why
mom-test scanned grade B with 1 finding 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 9d 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
- Division of labour: they own the problem, you own the solution. Never let them design the product; never tell them what their problem is. How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Mom Test — customer conversation procedure
When to use
Any time you're validating an idea through conversations: drafting interview questions, prepping a discovery call, analyzing what someone said, or judging whether a meeting was a win. Core mechanism: people lie about opinions and the future, but rarely about specific things that already happened. Note the scope limit: conversations validate market risk (do they want it, will they pay, are there enough of them) — they cannot retire product risk (can you build/grow/retain it). Heavy product risk means building earlier with less certainty; live-product questions are often better answered by usage data.
The procedure
1. Prepare
- Pick a focused, findable segment first. Slice ("Customer Slicing") until you have a who-where pair: who exactly, and where you can reach them. Slice by who wants it most and why (motivations), then by where they already gather or what workarounds they already do. Choose the first segment by: profitable, easy to reach, personally rewarding. If you can't say where to find them, keep slicing.
- Write the list of 3 — with the whole team, the 3 most important things to learn from this type of person. Include at least one question that could destroy the idea; if none of your questions scare you, they're wrong. Prep prompts: "If this failed, why would it have happened?" and "What would have to be true for this to be a huge success?" Minimum viable prep: "What do we want to learn from these guys?" If you can't answer that, skip the conversation.
- Desk-research first. Never spend conversation time on anything the internet can answer. 5 minutes of LinkedIn/company diligence before B2B meetings.
- If asking for a meeting, frame it — Vision / Framing / Weakness / Pedestal / Ask ("Very Few Wizards Properly Ask"): the problem-space vision (not your idea), where you're at and that you have nothing to sell, your specific weakness they can fix, why they specifically can help, the ask. Never "can I interview you" / "can I pick your brain" / "can I get your opinion". Compressible to two sentences.
- Keep it casual when possible. The first learning conversation doesn't need to be a meeting — 5 minutes tells you if a problem exists and matters. Video calls are fine (the 2013 "in person only" advice predates normalized remote work); the surviving principle is that formality kills candor. If it feels like they're doing you a favour, it's too formal.
- Cap prep at about an hour. More is stalling.
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.
- 9d ago First seen · 95 lines · 72 tokens per session scan B a18879e85d23
mom-test is a skill published in the GitHub repository lucasheriques/shipmate (4 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 2,332 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
solo-failures
Understand why startups fail — the most common failure modes, anti-patterns, and how to avoid them, backed by data from 101 founder interviews.
solo-analyze
Evaluate a startup idea against real patterns from 101 founder interviews.
solo-growth
Get data-backed growth and marketing recommendations for your business.
solo-roast
Get your startup plan roasted with data — Garry Tan style.
solo-patterns
Browse and search the startup pattern database (11 categories, 80+ patterns).
solo-playbook
Get a data-backed step-by-step playbook for any startup goal.