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 jeffreytse/grimoire-core --skill run-customer-discoverygit clone --depth 1 https://github.com/jeffreytse/grimoire-coreWrote 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/jeffreytse/grimoire-core/run-customer-discovery)<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.
<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>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 | $0.00028 | $0.01084 |
| Opus 5 | $0.00014 | $0.00542 |
| Sonnet 5 | $0.00006 | $0.00217 |
| Haiku 4.5 | $0.00003 | $0.00108 |
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.
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
-
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.
-
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.
-
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.
-
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…"
-
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.
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.
- 6d ago First seen · 64 lines · 28 tokens per session scan A f0ed944741c2
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.
Other skills, from other repositories
semantic-model-disambiguation
Analyze Power BI semantic models for column-level overlaps that confuse Copilot and Fabric data agents. Detect ambiguity, review with domain expert, apply fixes via MCP.
infrastructure-as-code
Domain: DevOps & Cloud Engineering.
prompt-2-data
Generate comprehensive synthetic relational data for any specified subject with multiple normalized CSV files maintaining referential integrity.
academic-paper-drafting
End-to-end academic paper drafting for CHI, HBR, journals, and conferences with venue-specific templates, drafting workflows, and revision strategies.
research-first-development
Build knowledge bases that build software — research before code, teach before execute.
agent-governance
Patterns for adding safety, trust, and policy enforcement to AI agent systems -- control which tools agents can call, what content they process, and maintain accountability through audit trails.