story-ui: Instructions file for Claude Code

CLAUDE.md

story-ui CLAUDE.md is an instructions file for Claude Code from southleft/story-ui. It costs 7,589 tokens per session, scanned C, original, MIT.

Project instructions for Story UI, an AI assistant that creates Storybook stories from natural-language descriptions using a component library's actual components. Storybook is a tool for developing and testing interface components in isolation.

In plain words
What is it for?
Use them when changing the Story UI application, its component-library integrations, generated stories, previews, or provider support.
Why use it?
They explain the application's purpose, supported technologies, important files, and development context so an assistant can work on the project without rediscovering them.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is southleft/story-ui's own configuration. It tells Claude Code how to work on story-ui itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything story-ui configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is cd ../test-storybooks/react-mantine.

Reuse

Borrowing it

Nothing to install: this file belongs to southleft/story-ui. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/southleft/story-ui/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/southleft/story-ui

Made for: Claude Code.

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 story-ui CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/southleft/story-ui/claude-md/github.svg)](https://agentmods.dev/instructions/southleft/story-ui/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/southleft/story-ui/claude-md"><img src="https://agentmods.dev/badge/instructions/southleft/story-ui/claude-md/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 story-ui CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/southleft/story-ui/claude-md"><img src="https://agentmods.dev/badge/instructions/southleft/story-ui/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7,589 This file is loaded in full into every session.
When invoked 7,589 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.07589 $0.07589
Opus 5 $0.03794 $0.03794
Sonnet 5 $0.01518 $0.01518
Haiku 4.5 $0.00759 $0.00759

Measured 3d ago against content hash 44da284d1b9a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

story-ui CLAUDE.md scanned grade C with 1 finding 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 3d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf node_modules/.vite # Clear cache
CLAUDE.md · 668 lines

How it starts

The opening of the file, as written. The whole thing — 668 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Story UI - AI Assistant Project Guide

Last Updated: July 28, 2026 Current Version: 4.17.0 Production URL: https://app-production-16de.up.railway.app (Vue/Vuetify example) Repository: https://github.com/southleft/story-ui

This document provides comprehensive context for AI assistants working on the Story UI codebase. It captures what the project is, how it works, architecture decisions, and development workflows to minimize token consumption during codebase analysis.


What is Story UI?

Story UI is an AI-powered Storybook story generator that works with ANY component library. Users describe components in natural language, and the AI generates working Storybook stories using their design system's actual components.

Core Value Proposition

  • Design-System Agnostic: Works with React (Mantine, Chakra, MUI), Vue (Vuetify), Angular (Material), Svelte (Flowbite), Web Components (Shoelace)
  • Natural Language Interface: "Create a card with a header, image, and action buttons"
  • Live Preview: Generated stories appear instantly in Storybook
  • Multi-Provider LLM: Supports Claude, OpenAI, and Gemini
  • Self-Healing Code Generation: Validates generated code and auto-corrects errors via LLM retry loop

Quick Reference

Important Files

Purpose Location
MCP Server (Express) mcp-server/index.ts
STDIO MCP Server mcp-server/mcp-stdio-server.ts
Generation Pipeline (shared core) mcp-server/routes/generationCore.ts
Story Generation (JSON transport) mcp-server/routes/generateStory.ts
Streaming Generation (SSE transport) mcp-server/routes/generateStoryStream.ts
Import Isolation validateImportIsolation in generationCore.ts
Documentation Loader story-generator/documentationLoader.ts
Self-Healing Loop story-generator/selfHealingLoop.ts
Component Discovery story-generator/componentDiscovery.ts
LLM Providers story-generator/llm-providers/
Framework Adapters story-generator/framework-adapters/
Storybook Panel (V1) templates/StoryUI/StoryUIPanel.tsx
MDX Wrapper templates/StoryUI/StoryUIPanel.mdx
V2 Workspace templates/StoryUIV2/Workspace.tsx
V2 Element targeting (React fiber) templates/StoryUIV2/elementTargeting.ts
V2 Property panel (direct manipulation) templates/StoryUIV2/PropertyPanel.tsx
Verification orchestrator story-generator/verify/verifyStory.ts
DOM census probe story-generator/verify/probes/domCensus.ts
Layout probe (grid/alignment arithmetic) story-generator/verify/probes/layout.ts
Visual critique (vision model) story-generator/verify/probes/visualCritic.ts
Prop AST editor (no LLM) story-generator/editing/propEditor.ts
Prop edit endpoints mcp-server/routes/editProp.ts
Prop/type knowledge story-generator/knowledge/propExtractor.ts
Token + styling idiom story-generator/knowledge/stylingFacts.ts
Description quality predicate story-generator/knowledge/descriptionQuality.ts
CLI Entry cli/index.ts
CLI Setup cli/setup.ts

Read the full file on GitHub · 668 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. 3d ago Changed · +176 lines · +3,047 tokens per session 44da284d1b9a
  2. 9d ago First seen · 492 lines · 4,542 tokens per session scan C 0351914fb1ef

Subscribe to this mod's changes

story-ui CLAUDE.md is an instructions file published in the GitHub repository southleft/story-ui (200 stars, last pushed 2d ago), licensed MIT. It adds 7,589 tokens to every session, about $0.0379 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens