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 extract-customer-insightsgit 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/extract-customer-insights)<a href="https://agentmods.dev/skills/emichy/product-judgment/extract-customer-insights"><img src="https://agentmods.dev/badge/skills/emichy/product-judgment/extract-customer-insights/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/extract-customer-insights"><img src="https://agentmods.dev/badge/skills/emichy/product-judgment/extract-customer-insights.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 | $0.00106 | $0.01064 |
| Opus 5 | $0.00053 | $0.00532 |
| Sonnet 5 | $0.00021 | $0.00213 |
| Haiku 4.5 | $0.00011 | $0.00106 |
Grade A, and why
extract-customer-insights 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 12d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extract customer insights
What the call revealed — not a theme deck. Transcript only for quotes — never invent. Search before you label corroborated.
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."
120 words of your own prose is long. 180 is an analysis — cut until it isn't. Quotes don't count.
Search findings live in Triangulate. Never in Proof, never in Other signals.
Output contract
| Step | Deliver |
|---|---|
| 1 | Line 1: Right now they [job] by [workaround] — whichever workaround carries the cost, not the one they came to test. Observed only; a read like "they know it breaks" is Assumption or a quote, not Line 1. Can't say it → say you don't have an insight yet. |
| 2 | Proof: two or three quotes on the lede, the ones with a consequence. Then one sentence of label, max. No paragraph after the quotes. Label anything beyond the tape as inference or read. Vibe is allowed; invented certainty isn't. |
| 3 | One bet card, on the workaround with the cost. If that isn't what they came to test, say both in a line: "They shrugged at alerts; the cost is month-end in finance." Other signals: at most three, one sentence each. No account lists, no filing briefs, no second bet. |
| 4 | Triangulate — search tickets, CRM, issues, analytics, repo. Don't write "Corroborated" without searching. |
| 5 | One sentence read, one sentence flip. Don't restate the bet card. Offer pressure-test-a-bet or make-it-land if useful. |
Anything about how they work keeps its line even when it changes nothing this week.
Bet card
Behavior: one line — outcome → workaround — quote. Not a paragraph, and not the leap. Assumption: [what this implies — the leap goes here] Test: [smallest observable check — show something, grep tickets, a metric. Not another interview if avoidable.]
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.
- 12d ago First seen · 72 lines · 106 tokens per session scan A 480fc211bd88
extract-customer-insights is a skill published in the GitHub repository emichy/product-judgment (4 stars, last pushed 26d ago), licensed MIT. It adds 106 tokens to every session and 1,064 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 2026-08-31.
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…