sb-inventory

sb-inventory is a skill for Claude Code, Codex from strongeron/storybook-workbench. It costs 58 tokens per session (3,429 once invoked), scanned A, original, MIT.

An inventory tool for React and Vite applications, which are web apps built with the React interface library and Vite development tooling. It finds which components are actually imported, identifies the main visual design system, and checks how component properties are used.

In plain words
What is it for?
Use it to list the app's libraries and components, find dead or orphaned components, identify the dominant design system, and inspect real property values at component call sites.
Why use it?
It replaces assumptions from project notes with evidence from the code, helping distinguish used components from unused or placeholder ones.

Skill for Claude CodeCodex

Written for Claude Code and Codex: allowed-tools in frontmatter, but also agents/openai.yaml present. Also seen: mentions CLAUDE.md; mentions subagents; mentions AGENTS.md.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the storybook-workbench plugin — 11 skills shipped together

Good fit Use it to list the app's libraries and components, find dead or orphaned components, identify the dominant design system, and inspect real property values at component call sites.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add strongeron/storybook-workbench
Claude Code
/plugin install storybook-workbench

Made for: Claude Code, Codex.

Or install storybook-workbench, the plugin that ships this one along with the rest of its 11 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 sb-inventory

README.md
[![agentmods](https://agentmods.dev/badge/skills/strongeron/storybook-workbench/sb-inventory/github.svg)](https://agentmods.dev/skills/strongeron/storybook-workbench/sb-inventory)
Your own site
<a href="https://agentmods.dev/skills/strongeron/storybook-workbench/sb-inventory"><img src="https://agentmods.dev/badge/skills/strongeron/storybook-workbench/sb-inventory/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 sb-inventory

Your own site · 80×15
<a href="https://agentmods.dev/skills/strongeron/storybook-workbench/sb-inventory"><img src="https://agentmods.dev/badge/skills/strongeron/storybook-workbench/sb-inventory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,429 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 $0.00058 $0.03429
Opus 5 $0.00029 $0.01715
Sonnet 5 $0.00012 $0.00686
Haiku 4.5 $0.00006 $0.00343

Measured 10d ago against content hash 1f70bb852bd9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

sb-inventory 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 10d ago.

The scan reads SKILL.md. This mod also ships 8 executable files (scripts/build-component-pages.py, scripts/extract-component-usage.sh, scripts/inventory-project.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/sb-inventory/SKILL.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sb-inventory — ground truth, not trust

Vibe-coded apps ship ~30% slop. This skill replaces "trust the AGENTS.md / CLAUDE.md / DESIGN.md" with "see what's actually imported." Read CONTEXT.md for the real/vendor/dead/kind vocabulary. (The dominant design system here comes from code signals, never from a doc. If a DESIGN.md brief is present, sb-health cross-checks its claimed colors against the code — it drifts/lies the same way an AGENTS.md does.)

Run it

SKILL=${CLAUDE_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}
CORE=${CLAUDE_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}
"$SKILL/scripts/inventory-project.sh"   # writes .storybook/project-inventory.json (atomic)

The script is the ground truth — do NOT recompute by hand. Read the JSON and cite its fields. For the known detector gotchas (what the discovery scripts get right vs. wrong across validation runs), load references/field-learnings.md only when a count looks surprising (a 0, an outlier, a suspected false orphan). Do NOT load it for a clean first-pass inventory whose numbers look right — the JSON fields stand on their own.

Report (read these fields, in this order)

  1. Stacklibraries (react/vite/tailwind v4|v3/shadcn/radix/baseui/r3f).
  2. Dominant design systemdesignSystem.dominant (one of tailwind-v4/shadcn/dtcg/css-vars/ none) + mixed flag. If mixed → tell the user the project is in transition; suggest sb-health.
  3. The user's own componentscomponents.realCount / deadCount are domain components only. Cite components.real[] (most-imported first) as the priority list for stories.
  4. Vendorcomponents.vendorCount + byKind.vendor = shadcn components/ui/ primitives. Call these out separately: "you also have N installed shadcn primitives — not your code, not slop, don't write stories for them first."
  5. Modules / support / scaffoldmoduleCount (byKind.module = types/helpers/hooks/utils/ lib/api — non-component source), supportCount (byKind.scaffold|support = test/factory/mock + SB init tutorial). All excluded from the headline AND the real[] most-imported list, so that list is your prod components, not a types.ts that's imported everywhere. Mention if non-zero.
  6. Tokens — used vs orphan. StoriesorphanStories (stories importing a component that no longer exists) AND components.storyCoverage — own components written vs. needed: {real, storyFiles, withColocatedStory, withStory, needsCount, needsStory[]}. Read coverage from withColocatedStory (own components with their own <name>.stories.*) and storyFiles (distinct story files that exist) — those are the hard counts. withStory is a loose upper bound: it also counts a component as covered when any story merely imports it (e.g. a dialog story importing a form to mock it), so it over-reports — treat withColocatedStory ≤ real_coverage ≤ withStory. needsStory[] is the "stories needed" worklist (the inverse of orphanStories); refresh-usage.sh keeps it current so sb-stories can work down needsStory[].

Read the full file on GitHub · 199 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. 10d ago First seen · 199 lines · 58 tokens per session scan A 1f70bb852bd9

Subscribe to this mod's changes

sb-inventory is a skill published in the GitHub repository strongeron/storybook-workbench (33 stars, last pushed 2mo ago), licensed MIT. It adds 58 tokens to every session and 3,429 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 2026-08-30.

Related

Other skills, from other repositories

skillshare-ui-website-style

Skillshare frontend design system for the React dashboard (ui/) and Docusaurus website (website/). Use this skill whenever you: build or modify a dashboard page or component in ui/src/, style or layout website pages or custom CSS in website/, create new React components for the dashboard, add pages to the dashboard…

runkids/skillshare · 147 tokens

21st-ui

Find, install, and generate UI with 21st.dev. Use when the user asks for a UI component (pricing table, hero, navbar, dashboard, form, etc.), wants design inspiration, needs a brand logo as an SVG component, or wants to generate new UI from a prompt.

21st-dev/magic-mcp · 63 tokens

vercel-react-view-transitions

Guide for implementing smooth, native-feeling animations using React's View Transition API ( component, addTransitionType, and CSS view transition pseudo-elements). Use this skill whenever the user wants to add page transitions, animate route changes, create shared element animations, animate enter/exit of components…

fcakyon/claude-codex-settings · 127 tokens

extract-source-sample

Given the path to a finished content-goose ad-run folder, extract everything that defines that ad — recipe shot list, VO script, characters, voices, world, atom-skills, master mp4 — and emit a source-sample.json in the exact shape the upload-ad-sample skill writes to the Goose Ads library. Also links every character…

gooseworks-ai/goose-skills · 160 tokens

vercel-react-native-skills

React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.

fcakyon/claude-codex-settings · 57 tokens

remotion-to-hyperframes

Port an existing Remotion (React) composition to HyperFrames HTML. Use ONLY when the user explicitly asks to port/convert/migrate/translate a Remotion source. Do NOT use: (a) authoring a new HyperFrames composition; (b) Remotion mentioned in passing; (c) Remotion code shared as reference only; (d) "same video as my…

calesthio/OpenMontage · 215 tokens