shipkit-product-discovery

shipkit-product-discovery is a skill for Claude Code, Codex from stefan-stepzero/shipkit. It costs 37 tokens per session (3,628 once invoked), scanned A, original, MIT.

A lightweight workflow for defining users, user journeys, and user stories during early product work. A user journey describes how someone reaches a goal, while a user story records a need from that person's viewpoint.

In plain words
What is it for?
It is for creating personas, mapping journeys, and writing user stories for proofs of concept and early products. It also guides when to propose information and when to ask questions.
Why use it?
It helps turn scattered product ideas into a small set of people, needs, journeys, and stories before building a prototype or minimum viable product.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/stefan-stepzero/shipkit/shipkit-product-discovery
Any agent
npx skills add stefan-stepzero/shipkit --skill shipkit-product-discovery
Clone the repo
git clone --depth 1 https://github.com/stefan-stepzero/shipkit

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 shipkit-product-discovery

README.md
[![agentmods](https://agentmods.dev/badge/skills/stefan-stepzero/shipkit/shipkit-product-discovery.svg)](https://agentmods.dev/skills/stefan-stepzero/shipkit/shipkit-product-discovery)
Your own site
<a href="https://agentmods.dev/skills/stefan-stepzero/shipkit/shipkit-product-discovery"><img src="https://agentmods.dev/badge/skills/stefan-stepzero/shipkit/shipkit-product-discovery.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,628 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00037 $0.03628
Opus 5 $0.00018 $0.01814
Sonnet 5 $0.00007 $0.00726
Haiku 4.5 $0.00004 $0.00363

Measured 5d ago against content hash 1614a6ecd1f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

shipkit-product-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 5d 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.

install/skills/shipkit-product-discovery/SKILL.md · 342 lines

How it starts

The opening of the file, as written. The whole thing — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.

shipkit-product-discovery - Lightweight Product Discovery

Purpose: Combines personas, user journey mapping, and user stories into a single lightweight workflow for POC/MVP projects

Protocol: This skill follows the canonical elicitation protocol defined in install/shared/references/elicitation-protocol.md (the mechanics — marker, state files, resume). The steps below are this skill's specific application of that protocol.

Calibration: Apply install/shared/references/ground-or-ask-calibration.md (the intelligence — propose vs ask). Ground first: scan cited signals (the opening prompt, why.json, README.md, package.json, the codebase) before asking anything. Propose every field you can tie to a signal, tagged with its source; flag low-leverage guesses as guessed. High-leverage for this skill: who the PRIMARY personas are and their core journeys / top user needs — these define who the product is FOR and are hard to reverse. If ungrounded, ask. Low-leverage: secondary personas, edge-case journeys, ordering details — propose flagged defaults, don't ask. Target 2–3 questions maximum; if you're about to ask more, your grounding pass was too shallow. Never silently invent an ungrounded primary persona or core need.


When to Invoke

User triggers:

  • "Who are our users?", "Create personas", "User research"
  • "User journey", "Map user needs", "Product discovery"
  • "User stories", "What features?", "Requirements"

Workflow position:

  • Early Pillar 1 (Vision) or Pillar 3 (Co-design) - before specification
  • Replaces separate prod-personas + prod-jobs-to-be-done + prod-user-stories for POC/MVP

Prerequisites

Optional:

  • .shipkit/why.json (Vision helps guide persona creation)
  • .shipkit/stack.json (Technical constraints inform feasibility)

If missing: Generate personas and stories based on user input alone


Process

Step 0: Check for Existing File

Fork context — no user prompts. You are dispatched in a fork and have no user channel. Skip the file-exists menu entirely.

Read the full file on GitHub · 342 lines

Files

What ships with it

2 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. 5d ago First seen · 342 lines · 37 tokens per session scan A 1614a6ecd1f0

Subscribe to this mod's changes

shipkit-product-discovery is a skill published in the GitHub repository stefan-stepzero/shipkit (1 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 3,628 once invoked, about $0.0002 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.