shipkit-engineering-definition

A technical planning guide that defines how a product should be built, including its mechanisms, important design decisions, technology direction, and component structure.

In plain words
What is it for?
Use it to choose a stack for a new project, design how features work internally, define components, and capture architecture decisions.
Why use it?
It turns a product description into an engineering blueprint that later planning and specification work can rely on.

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

Made for: Claude Code, Codex.

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,323 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 $0.00044 $0.05323
Opus 5 $0.00022 $0.02661
Sonnet 5 $0.00009 $0.01065
Haiku 4.5 $0.00004 $0.00532

Measured 2d ago against content hash e15a467734b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shipkit-engineering-definition 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 2d 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-engineering-definition/SKILL.md · 494 lines

How it starts

The opening of the file, as written. The whole thing — 494 lines — stays where its author put it; the contents beside it link to each section on GitHub.

shipkit-engineering-definition — Technical Approach

Defines HOW we build the product defined in product-definition.json. For each feature, designs the technical mechanisms, captures design decisions, recommends stack direction (greenfield), and defines component structure.

This is the engineering blueprint — it takes the product's features and UX patterns and defines the technical approach to implement them. Downstream skills (goals, spec) read both product-definition.json and engineering-definition.json. Architecture decisions are captured directly in this file.


When to Invoke

User triggers:

  • "How should we build this?", "Technical approach", "Engineering design"
  • "Define mechanisms", "Component structure", "Technical decisions"
  • "Stack direction", "What technologies?"

Workflow position:

  • After /shipkit-product-definition (needs features and UX patterns)
  • Before /shipkit-product-goals and /shipkit-engineering-goals (goals derive criteria from mechanisms)

Prerequisites

Required (fail gracefully if missing):

  • .shipkit/product-definition.json — features, UX patterns, differentiators

Recommended (enrich the proposal):

  • .shipkit/why.json — project purpose and vision
  • .shipkit/goals/strategic.json — project stage and constraints
  • .shipkit/stack.json — existing technology constraints
  • .shipkit/product-discovery.json — pain points for traceability

Optional (for existing projects):

  • .shipkit/codebase-index.json — existing code structure

If product-definition.json is missing, tell the user: "Run /shipkit-product-definition first — I need to know what features to design mechanisms for." and stop.


Process

Completion Tracking

After reading prerequisites, create tasks:

  • TaskCreate: "Design 2-5 mechanisms mapped to features"
  • TaskCreate: "Define 2-6 components mapped to mechanisms"
  • TaskCreate: "Capture cross-cutting design decisions"
  • TaskCreate: "Write engineering-definition.json"
  • TaskCreate: "Derive and dual-write architecture.json (lean) + architecture-archive.json (full)"

Read the full file on GitHub · 494 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. 2d ago First seen · 494 lines · 44 tokens per session scan A e15a467734b2

Subscribe to this mod's changes

shipkit-engineering-definition is a skill published in the GitHub repository stefan-stepzero/shipkit (1 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 5,323 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.