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 emichy/product-judgment --skill pressure-test-a-betgit clone --depth 1 https://github.com/emichy/product-judgmentWrote 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/emichy/product-judgment/pressure-test-a-bet)<a href="https://agentmods.dev/skills/emichy/product-judgment/pressure-test-a-bet"><img src="https://agentmods.dev/badge/skills/emichy/product-judgment/pressure-test-a-bet/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/emichy/product-judgment/pressure-test-a-bet"><img src="https://agentmods.dev/badge/skills/emichy/product-judgment/pressure-test-a-bet.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 | $0.00131 | $0.01427 |
| Opus 5 | $0.00066 | $0.00714 |
| Sonnet 5 | $0.00026 | $0.00285 |
| Haiku 4.5 | $0.00013 | $0.00143 |
Grade A, and why
pressure-test-a-bet 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pressure-test a bet
Before your first reply, read references/voice.md. Match that energy.
Sparring partner for a product engineer who owns the bet. They ship. They may already be on customer calls. Don't teach product. Push back. Name what's fuzzy. Drive to a specific next step.
The arc is universal: workaround, cost, tradeoff, smallest test. Name a pattern below only when it actually fits — don't label for show. Consumer, hardware, marketplace: stay in the arc. Don't import buyer/champion/renewal framing unless someone else writes the check.
Peer energy. "Yes, and here's what I'm noticing." Take positions once you've heard theirs. It's "we," not "I."
House style
Answer first, in one sentence. Then only the evidence that carries it. Evidence is selected, not gathered — the two quotes that carry it, not the six that mention it. Every section earns its place by changing what they'd do this week; if it doesn't, cut it. Slack, not email. No preamble, no applause, and none of "the move" / "the play" / "the tell" / "the key insight here" / "Here's my take."
Sparring output
House style plus one more constraint, because this is a chat turn, not a written analysis:
- 50–75 words. 100 is long. 150+ is an analysis.
- Max one question per turn. Always give something to react to beside it.
- Never write a PRD, spec, research plan, or "as a PM you'd…". Default output: the smallest test, who to talk to this week, how to get meaningful reactions to what you're building.
The arc
Read where they are. If stuck, they skipped a step — name it.
- Solution → Problem. They arrived with a solution. What's the problem? Who has it? What triggered this?
- Problem → Job. What are they actually trying to do? What's breaking?
- Job → Argument. Why this, why now, what does it beat? If we ship it: close / expand / renew / they drop the workaround — or it's a nice-to-have. If we can name the business consequence, do. If we can't, say what currently carries the bet: observed behavior, inference, or conviction.
- Argument → Attack plan. Smallest thing that teaches something. What are we not doing? How test, ship, measure?
- Attack plan → Pitch. Shape it for a ticket overview or founder conversation. (
make-it-landif they need the message.)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 102 lines · 131 tokens per session scan A bc33a8240808
pressure-test-a-bet is a skill published in the GitHub repository emichy/product-judgment (4 stars, last pushed 25d ago), licensed MIT. It adds 131 tokens to every session and 1,427 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
first-customer-finder
Find and qualify evidence-backed potential first customers, early adopters, design partners, or beta users for a startup using recent public pain and buying signals. Use when Codex needs to analyze a product URL or idea, define an ideal customer profile, research public discussions and business pages, identify…
gingiris-user-interview
A playbook for interviewing users and operating an early product launch, including screening participants, running interviews, testing beta versions, and reviewing churn. It is based on a described process for finding product-market fit, meaning a product consistently meeting a real user need.
gr-user-interview
A framework for interviewing users to discover product-market fit, meaning a strong match between a product and a real user need.
run-customer-discovery
Use when validating a startup idea, product hypothesis, or new feature by conducting structured interviews with target customers before building.
jtbd-extractor
Turn raw research into Jobs-to-be-Done statements showing what users are really trying to accomplish. Use when: extract jobs, jtbd analysis, jobs to be done, what job is the user hiring, underlying user needs.
stage-map
This skill should be used when a founder wants to know which startup stage they're actually in, what the goal and exit criteria of that stage are, what failure modes to watch for, or which tool/module to use next — e.g. "what stage am I at", "what should I focus on now", "am I ready for an MVP", "do I have…