sb-health

sb-health is a skill for Claude Code, Codex from strongeron/storybook-workbench. It costs 65 tokens per session (2,479 once invoked), scanned A, original, MIT.

A design-system health checker for React applications built with Vite. A design system is the shared set of colors, spacing rules, and other visual choices used across an interface.

In plain words
What is it for?
Use it to check color usage, token definitions, scale consistency, documentation drift, and—when configured—whether interface properties use the intended token families.
Why use it?
It reveals inconsistent or unused design tokens, raw color values, gaps in scales, and differences between the code and DESIGN.md documentation.

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 check color usage, token definitions, scale consistency, documentation drift, and—when configured—whether interface properties use the intended token families.

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-health

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/strongeron/storybook-workbench/sb-health"><img src="https://agentmods.dev/badge/skills/strongeron/storybook-workbench/sb-health.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,479 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 $0.00065 $0.02479
Opus 5 $0.00032 $0.01239
Sonnet 5 $0.00013 $0.00496
Haiku 4.5 $0.00006 $0.00248

Measured 12d ago against content hash 9792814d5f60, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

sb-health 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 12d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/check-property-tokens.py, scripts/scaffold-wrapper.sh, scripts/validate-design-system.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-health/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sb-health — design-system health gate

The browser can't shell out, so the script runs the checks and writes JSON the wrapper renders. design-system-health.json is a rendered output (Health Docs + DesignSystemHealth/TokenMatrix), so refresh-usage.sh re-runs this check with the other rendered extractors — see CONTEXT.md §STORAGE MAP.

Run it

SKILL=${CLAUDE_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}
CORE=${CLAUDE_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}
"$SKILL/scripts/validate-design-system.sh"       # → .storybook/design-system-health.json
# --emit-prompt  also outputs an LLM sub-agent prompt for semantic checks
#                (naming drift, semantic-vs-presentational, scale clarity)
"$CORE/scripts/scaffold-wrapper.sh" DesignSystemHealth   # → .storybook/wrappers/ (+ icons.tsx)

# Opt-in property→token-family check (off until a designer authors the rules file):
"$SKILL/scripts/check-property-tokens.py" --init   # scaffold design-system/lint/colors.json (+ schema)

What it checks

  • raw-color — hex/rgba/hsl literals in components (should be tokens). When the literal's value EQUALS an existing token's resolved value (e.g. #005596 on a tile whose siblings use bg-secondary--secondary resolves to #005596), the fix is to adopt that exact token, not invent a new one — the finding names the matching token when it can resolve one, so the fix is "replace with --x", not "add a token".
  • undefined-token — components reference --foo that's not declared
  • scale-gap — spacing/type scale has unexpected jumps
  • unused-token — declared but never referenced (var, Tailwind utility, or custom @utility). Read from sb-inventory's single source (.storybook/project-inventory.jsontokens.map), not re-scanned here, so health, inventory, and the token views never disagree. Run sb-inventory first; if the file is absent this check is skipped.
  • design-md — a DESIGN.md (Google Labs YAML-tokens-plus-markdown, an increasingly common way to brief agents on a visual identity) is a claim, not ground truth — like AGENTS.md it drifts as the code changes, or was wrong from the start. The script finds it and cross-checks the colors it claims against the colors the code's CSS tokens actually declare, emitting design-md-drift for each claimed color the code doesn't define. Treat a present DESIGN.md as untrusted until reconciled.
  • property-token-family (opt-in) — a valid, declared token used on the wrong property family (e.g. color: var(--color-container) — a container token used as text color). raw-color catches "no token at all"; undefined-token catches "token doesn't exist"; this catches "real token, wrong slot." Off until a designer authors design-system/lint/colors.json (see below), so the zero-config default is preserved. Findings are warning/info only — an opt-in never flips a green CI build red.
  • runs stylelint if configured

Read the full file on GitHub · 157 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. 12d ago First seen · 157 lines · 65 tokens per session scan A 9792814d5f60

Subscribe to this mod's changes

sb-health is a skill published in the GitHub repository strongeron/storybook-workbench (33 stars, last pushed 2mo ago), licensed MIT. It adds 65 tokens to every session and 2,479 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-composition-patterns

React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.

calesthio/OpenMontage · 58 tokens

frontend

Builds, styles, and polishes web UI and UX. Use for any frontend, page, component, styling, layout, animation, or visual-quality task, or when asked to make an interface look or feel a certain way.

code-yeongyu/oh-my-openagent · 49 tokens

ambience-skill

Layer A ambience-and-typographic-motion reference anchored to the react-bits catalog (reactbits.dev). Stacks on any style skill whenever work adds a hero atmosphere, an animated or shader background, a typographic reveal (split, blur, shimmer, typewriter, count-up, marquee), scroll storytelling, or card surface…

code-yeongyu/oh-my-openagent · 132 tokens

web-artifacts-builder

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

Prismer-AI/PrismerCloud · 64 tokens