shipkit-review-direction

shipkit-review-direction is a skill for Claude Code, Codex from stefan-stepzero/shipkit. It costs 46 tokens per session (720 once invoked), scanned A, original, MIT.

An internal review skill for checking whether a product direction is complete and logically consistent. It examines the project’s vision, product decisions, engineering plans, architecture, design system, and goals.

In plain words
What is it for?
Use it as a review gate after direction documents are created, rather than as a general-purpose user-facing skill.
Why use it?
It helps find gaps or contradictions before development begins.

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-review-direction
Any agent
npx skills add stefan-stepzero/shipkit --skill shipkit-review-direction
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-review-direction

README.md
[![agentmods](https://agentmods.dev/badge/skills/stefan-stepzero/shipkit/shipkit-review-direction.svg)](https://agentmods.dev/skills/stefan-stepzero/shipkit/shipkit-review-direction)
Your own site
<a href="https://agentmods.dev/skills/stefan-stepzero/shipkit/shipkit-review-direction"><img src="https://agentmods.dev/badge/skills/stefan-stepzero/shipkit/shipkit-review-direction.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 720 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 $0.00046 $0.00720
Opus 5 $0.00023 $0.00360
Sonnet 5 $0.00009 $0.00144
Haiku 4.5 $0.00005 $0.00072

Measured 4d ago against content hash 7594483bebce, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shipkit-review-direction 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 4d 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-review-direction/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

shipkit-review-direction - Direction Assessment

Purpose: Read all direction artifacts and assess whether they are coherent, complete, and internally consistent. Write a structured assessment for the direction orchestrator.

Input

Required artifacts (the direction loop must produce all of these):

  • .shipkit/why.json (contains vision, purpose, stage)
  • .shipkit/product-discovery.json
  • .shipkit/product-definition.json
  • .shipkit/engineering-definition.json
  • .shipkit/architecture.json
  • .shipkit/design-system/ (DIRECTION.md, PRINCIPLES.md, tokens/)
  • .shipkit/goals/strategic.json
  • .shipkit/goals/product.json
  • .shipkit/goals/engineering.json

Optional context (read if present, don't flag as missing):

  • .shipkit/metrics/latest.json — only exists after implementation

Coherence Checks

  1. Completeness: Are ALL 9 required direction artifacts present with non-placeholder content? Missing artifacts are gaps.
  2. Vision coherence: Does why.json state a vision that fulfills its stated purpose? (vision and purpose both live inside why.json)
  3. Goals ↔ Vision: Do goals, if achieved, realize the vision stated in why.json?
  4. Goals ↔ Stage: Are thresholds realistic for the current stage? Do all goals have rubrics?
  5. Internal consistency: Do goals reference capabilities the vision describes?
  6. Architecture ↔ Engineering Definition: Are architecture decisions consistent with the mechanisms and components defined?
  7. Design System ↔ Vision: Do principles align with the vision? Does aesthetic direction fit the target audience? Does token format match the stack?
  8. Design System specificity: Does DIRECTION.md use concrete values (hex codes, exact font names, px values, CSS easing functions) for every field? Flag any field that uses vague language ("clean", "modern", "intuitive", "user-friendly", "seamless", "elegant") without a measurable specification alongside it. Flag any missing source citations. Every dimension must trace back to a specific .shipkit/ field.

Read the full file on GitHub · 58 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. 4d ago First seen · 58 lines · 46 tokens per session scan A 7594483bebce

Subscribe to this mod's changes

shipkit-review-direction is a skill published in the GitHub repository stefan-stepzero/shipkit (1 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 720 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.