apply-lean-startup-methodology

apply-lean-startup-methodology is a skill for Claude Code from jeffreytse/grimoire-core. It costs 62 tokens per session (1,718 once invoked), scanned A, original, MIT.

A planning method for building a small first version of a product, measuring how people use it, and learning whether to continue or change direction. MVP means the smallest version that can test an important product idea.

In plain words
What is it for?
Use it to choose what to build first, define a testable product hypothesis, select measurements, and decide whether to pivot or persevere.
Why use it?
It reduces the risk of spending time and money building a complete product before checking whether the idea solves a real problem.

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 Use it to choose what to build first, define a testable product hypothesis, select measurements, and decide whether to pivot or persevere.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jeffreytse/grimoire-core/apply-lean-startup-methodology
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 apply-lean-startup-methodology
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 apply-lean-startup-methodology

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-lean-startup-methodology"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-lean-startup-methodology.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,718 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 $0.00062 $0.01718
Opus 5 $0.00031 $0.00859
Sonnet 5 $0.00012 $0.00344
Haiku 4.5 $0.00006 $0.00172

Measured 9d ago against content hash 35eccce9157a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

apply-lean-startup-methodology 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 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.

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/apply-lean-startup-methodology/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Apply Lean Startup Methodology

Run the Build-Measure-Learn loop — build the smallest possible product that tests a specific hypothesis, measure whether it produces real validated learning, and decide explicitly whether to pivot or persevere — rather than building a full product on faith before any real usage data exists.

Why This Is Best Practice

Adopted by: Eric Ries developed the methodology from his experience at IMVU; it has since become standard startup-building practice, taught at Y Combinator and Stanford, and credited in the growth of companies including Dropbox (whose MVP was a demo video, not a working product) and Zappos (whose MVP was Nick Swinmurn manually photographing shoes at local stores and fulfilling orders by hand before building any inventory system).

Impact: Ries documented IMVU's own pivot history as the origin case: repeated small, cheap experiments redirected the product away from a doomed initial direction toward one that found real traction, at a fraction of the cost of building the originally planned full feature set. Dropbox's MVP video, rather than a built product, is documented to have grown its beta waitlist from 5,000 to 75,000 signups overnight — validating demand before writing the storage-sync infrastructure.

Why best: This fills a specific gap between two adjacent practices already in use. run-customer-discovery validates that a problem is real and worth solving, then explicitly stops once there are "paying customers and usage data." run-growth-experiment optimizes an existing live product's funnel metrics, assuming real traffic already exists. Neither covers the step in between: what to actually build first, at what scope, and how to measure whether it produced real learning rather than vanity signals — the Build-Measure-Learn loop, with its own vocabulary (MVP types, innovation accounting, the pivot taxonomy) that this bridges.

Sources: Ries, The Lean Startup (2011); Blank, The Four Steps to the Epiphany (2005); documented IMVU, Dropbox, and Zappos case histories.

Read the full file on GitHub · 68 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. 9d ago First seen · 68 lines · 62 tokens per session scan A 35eccce9157a

Subscribe to this mod's changes

apply-lean-startup-methodology is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 21d ago), licensed MIT. It adds 62 tokens to every session and 1,718 once invoked, about $0.0003 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.