run-customer-discovery

run-customer-discovery is a skill for Claude Code from jeffreytse/grimoire-core. It costs 28 tokens per session (1,084 once invoked), scanned A, original, MIT.

A structured process for interviewing potential customers to test whether a startup idea, product assumption, or feature solves a real problem before building it.

In plain words
What is it for?
Planning customer interviews, testing product hypotheses, learning how people handle a problem today, and deciding whether to build or change an idea.
Why use it?
It reduces the risk of spending time and money on something customers do not need or would not pay to solve.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the grimoire-business plugin — 145 skills shipped together

Good fit Planning customer interviews, testing product hypotheses, learning how people handle a problem today, and deciding whether to build or change an idea.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jeffreytse/grimoire-core/run-customer-discovery
Install

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.

Any agent
npx skills add jeffreytse/grimoire-core --skill run-customer-discovery
Clone the repo
git clone --depth 1 https://github.com/jeffreytse/grimoire-core

Made for: Claude Code.

Or install grimoire-business, the plugin that ships this one along with the rest of its 145 skills.

Wrote 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.

agentmods badge for run-customer-discovery

README.md
[![agentmods](https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/run-customer-discovery/github.svg)](https://agentmods.dev/skills/jeffreytse/grimoire-core/run-customer-discovery)
Your own site
<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/run-customer-discovery"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/run-customer-discovery/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.

agentmods 80×15 button for run-customer-discovery

Your own site · 80×15
<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/run-customer-discovery"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/run-customer-discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,084 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00028 $0.01084
Opus 5 $0.00014 $0.00542
Sonnet 5 $0.00006 $0.00217
Haiku 4.5 $0.00003 $0.00108

Measured 6d ago against content hash f0ed944741c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

run-customer-discovery 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 6d 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.

skills/business/entrepreneurship/skills/run-customer-discovery/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run Customer Discovery

Conduct structured customer interviews to validate or invalidate core business assumptions before writing code or spending capital.

Why This Is Best Practice

Adopted by: Y Combinator-advised startups, IDEO design thinking practitioners, Lean Startup methodology adopters, Google Ventures design sprint teams Impact: CB Insights analysis of startup failures found 35% failed due to "no market need" — a problem that customer discovery directly prevents. Steve Blank documented 10+ companies that pivoted from failing to successful after 50+ customer discovery interviews revealed a different problem than assumed. Why best: Building before validating is the most expensive mistake in product development. Customer discovery is the minimum viable test for whether a problem is real, frequent, and worth solving.

Sources: Blank "The Four Steps to the Epiphany" (2005); Ries "The Lean Startup" (2011); IDEO "Design Thinking" field guide; Fitzpatrick "The Mom Test" (2013)

Steps

  1. Document your hypotheses first — before talking to anyone, write down your explicit assumptions: who the customer is, what problem they have, how they currently solve it, and what they would pay for a better solution. This prevents confirmation bias in analysis.

  2. Define your target customer profile — specify 3–5 demographic, behavioral, and situational characteristics of your ideal early adopter. Be specific enough to know who NOT to interview.

  3. Recruit 15–20 interviewees — reach the target profile through: LinkedIn outreach, founder networks, relevant Slack communities, Twitter/X, and warm introductions. Do not interview friends and family who will tell you what you want to hear.

  4. Prepare a question script — write 8–12 open-ended questions focused on past behavior, not hypothetical future behavior. Ask "Tell me about the last time you…" not "Would you use a product that…"

  5. Open with context-setting — explain you are researching a problem space, NOT pitching a product. Tell them you want to learn, not sell. This unlocks honest feedback.

Read the full file on GitHub · 64 lines

Changes

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.

  1. 6d ago First seen · 64 lines · 28 tokens per session scan A f0ed944741c2

Subscribe to this mod's changes

run-customer-discovery is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 21d ago), licensed MIT. It adds 28 tokens to every session and 1,084 once invoked, about $0.0001 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 2026-09-03.