A workflow for trying out a new or redesigned interface component in an isolated sandbox. A component is a reusable piece of an interface, such as a button, form, or navigation panel.

Use it to prototype a new component, try a redesigned version, or develop a component from a Figma design before shipping it.

It lets you test visual and interaction ideas without making unfinished work part of the production code. The workflow also checks whether the component is ready to move into the main application.

sb-explore — Skill for Claude Code and Codex by strongeron

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.

Any agent

npx skills add strongeron/storybook-workbench --skill sb-explore

Clone the repo

git clone --depth 1 https://github.com/strongeron/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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/strongeron/storybook-workbench/sb-explore/github.svg)](https://agentmods.dev/skills/strongeron/storybook-workbench/sb-explore)

Your own site

<a href="https://agentmods.dev/skills/strongeron/storybook-workbench/sb-explore"><img src="https://agentmods.dev/badge/skills/strongeron/storybook-workbench/sb-explore/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/strongeron/storybook-workbench/sb-explore"><img src="https://agentmods.dev/badge/skills/strongeron/storybook-workbench/sb-explore.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 724 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.

Model	Per session	Once invoked
Fable 5.1	$0.00060	$0.00724
Opus 5	$0.00030	$0.00362
Sonnet 5	$0.00012	$0.00145
Haiku 4.5	$0.00006	$0.00072

Measured 9d ago against content hash ddb5cbf24803, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

sb-explore 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 9d 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.

skills/sb-explore/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sb-explore — sandboxed iteration (Build mode: Explore)

The component is new or being redesigned. It lives outside src/components/ so production code can't depend on it. Load references/labs-workflow.md before scaffolding. If the user pasted a Figma URL, ALSO load references/figma-to-storybook.md. Do NOT load composition-patterns.md (that's Compare → sb-wrappers).

Naming: Explore is the canonical term used throughout this skill (titles, disk paths, tags). references/labs-workflow.md predates the rename and says Labs / src/stories/labs/ — read it as the same track (Explore = Labs). Author with Explore; treat Labs only as a legacy alias you may meet in an existing repo.

Before scaffolding (ask yourself)

Iterating on a shipping component, or net-new? Determines Path A vs Path B at Ship time.
Figma URL pasted? If yes — set parameters.design = { type: 'figma', url } immediately and iterate against the frame (see figma-to-storybook.md).
API stable enough to graduate? See the 4 criteria in labs-workflow.md. If not — stay in Explore.

Scaffold

Disk path — honor the recorded storiesLocation (.storybook/audit/status.md): when stories are isolated (the audit/client default), scaffold the experiment under .storybook/explore/<topic>/ — don't scatter into a src/ you don't own. Only use src/explore/<topic>/ when the user opted into co-located for a project they own. Vite excludes either from the production bundle.
Title — Explore/<topic>/<name> — last in storySort.order, bottom of sidebar.
Tags — ['explore', '!autodocs', '!test']. Optional: 'motion', 'figma-sync', 'v2-preview'.

Graduation gate (Explore → Component)

Four criteria in labs-workflow.md: stable API · ≥3 callsites planned · designer-reviewed · tokens not magic numbers. When all met → trigger sb-ship (it preserves the experiment, never git mv). Until then, keep iterating here.

Read the full file on GitHub · 55 lines

Files

What ships with it

4 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.

9d ago First seen · 55 lines · 60 tokens per session scan A ddb5cbf24803

Subscribe to this mod's changes

sb-explore is a skill published in the GitHub repository strongeron/storybook-workbench (33 stars, last pushed 2mo ago), licensed MIT. It adds 60 tokens to every session and 724 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.

Claude Code Design and UX agent-skills codex component-inventory csf3 cursor

create-chatgpt-mockup

Render pixel-accurate ChatGPT mobile (iOS) screen mockups in light mode from a thread JSON. Supports user text bubbles, user image attachments, assistant markdown prose, citation chips, the OpenAI spiral logo, the Apps-SDK GPT chip in the composer, and three header styles (model-tag, plain title, "Get Plus"). Fixed…

gooseworks-ai/goose-skills · 90 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

ui-designer/design-system

A shared set of rules for a product’s visual design, covering colors, fonts, spacing, corner shapes, shadows, and animations.

echoVic/boss-skill · 30 tokens

layout-skill

Layer A layout-mechanics reference. Stacks on any style skill when the screen is an app shell, dashboard, settings, list-detail, mail/inbox, or any layout with fixed regions plus a scrolling body — or when a layout breaks under long, empty, or unbroken content. Owns spatial structure and scroll ownership; owns zero…

code-yeongyu/oh-my-openagent · 88 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

baoyu-design

Create polished design artifacts as self-contained HTML: UI mockups, interactive prototypes, wireframes, landing pages, dashboards, app screens, mobile apps, slide decks (a.k.a. PPT / PowerPoint presentations), documents and résumés, animations, 3D objects, research reports, HTML email, diagrams, fliers, and visual…

JimLiu/baoyu-design · 231 tokens