four-steps

four-steps is a skill for Claude Code, Codex from getagentseal/founder-playbook. It costs 148 tokens per session (6,781 once invoked), scanned A, original, MIT.

A customer-development method for startups that are still looking for customers and a workable business model. Its four stages are Customer Discovery, Customer Validation, Customer Creation, and Company Building.

In plain words
What is it for?
Use it to interview and learn from potential customers, test whether they will pay, build a repeatable sales process, and decide when the business is ready to grow.
Why use it?
It addresses the situation where a team has built a product but has not shown that people will buy it. It helps test customer needs and sales assumptions before scaling the company.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it to interview and learn from potential customers, test whether they will pay, build a repeatable sales process, and decide when the business is ready to grow.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/getagentseal/founder-playbook/four-steps
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 getagentseal/founder-playbook --skill four-steps
Clone the repo
git clone --depth 1 https://github.com/getagentseal/founder-playbook

Made for: Claude Code, Codex.

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 four-steps

README.md
[![agentmods](https://agentmods.dev/badge/skills/getagentseal/founder-playbook/four-steps.svg)](https://agentmods.dev/skills/getagentseal/founder-playbook/four-steps)
Your own site
<a href="https://agentmods.dev/skills/getagentseal/founder-playbook/four-steps"><img src="https://agentmods.dev/badge/skills/getagentseal/founder-playbook/four-steps.svg" alt="Measured on agentmods" height="20"></a>
Per session 148 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,781 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. Third-party audits
  • Socket pass 26 Apr 2026
  • Snyk pass 26 Apr 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00148 $0.06781
Opus 5 $0.00074 $0.03390
Sonnet 5 $0.00030 $0.01356
Haiku 4.5 $0.00015 $0.00678

Measured 8d ago against content hash afa0e5aea118, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

four-steps 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 8d 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.

four-steps/SKILL.md · 569 lines

How it starts

The opening of the file, as written. The whole thing — 569 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Note: This skill is independent analysis and commentary, not a reproduction of the original text. It synthesizes the book's core ideas with modern startup practice, surfaces where frameworks are outdated or incomplete, and integrates perspectives from adjacent disciplines. For the full argument and context, read the original book.

The Four Steps to the Epiphany

"Startups that survive the first few tough years do not follow the traditional product-centric launch model. Through trial and error, hiring and firing, successful startups all invent a parallel process to product development. I call this process 'Customer Development.'" - Steve Blank

Should You Use This Skill?

Are you searching for customers and a business model (not executing a known one)?
├─ YES → This skill is for you
└─ NO  → You have paying customers and a repeatable sales process?
         ├─ YES, but stuck before mainstream → Use Crossing the Chasm
         ├─ YES, scaling fine → You're past this. Use Company Building concepts only
         └─ NO, still pre-product → Start here at Customer Discovery

Have you validated that people will pay for your product?
├─ NO  → Start at Customer Discovery (Step 1)
└─ YES → Can you describe a repeatable sales process?
         ├─ NO  → You're in Customer Validation (Step 2)
         └─ YES → Have you matched your launch to your Market Type?
                  ├─ NO  → You're in Customer Creation (Step 3)
                  └─ YES → Company Building (Step 4)

The Core Insight

9 out of 10 new product introductions fail. Not because the products don't work - because the companies never found customers.

The Product Development model (Concept → Build → Test → Launch) was designed for manufacturing in the early 1900s and adopted by consumer packaged goods in the 1950s. It works when you're launching a new product into an existing market with known customers. Most startups have neither.

PRODUCT DEVELOPMENT (what everyone does):
  Concept/Seed ──→ Product Dev ──→ Alpha/Beta ──→ Launch
                                                    ↑
                                              "Where are the
                                               customers?"

CUSTOMER DEVELOPMENT (what winners do - in parallel):
  ┌──────────┐    ┌──────────┐    ┌──────────┐    ┌──────────┐
  │ Customer │←──→│ Customer │←──→│ Customer │───→│ Company  │
  │ Discovery│    │Validation│    │ Creation │    │ Building │
  └──────────┘    └──────────┘    └──────────┘    └──────────┘
       ↻               ↻               ↻
    iterate          iterate         iterate

Read the full file on GitHub · 569 lines

Files

What ships with it

4 files 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.

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. 8d ago First seen · 569 lines · 148 tokens per session scan A afa0e5aea118

Subscribe to this mod's changes

four-steps is a skill published in the GitHub repository getagentseal/founder-playbook (550 stars, last pushed 1mo ago), licensed MIT. It adds 148 tokens to every session and 6,781 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens