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.
npx agentmods add skills/luqiang-code/claude-code-skills/react-component-scaffoldnpx skills add luqiang-code/claude-code-skills --skill react-component-scaffoldgit clone --depth 1 https://github.com/luqiang-code/claude-code-skillsWhat 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 | $0.00041 | $0.00660 |
| Opus 5 | $0.00020 | $0.00330 |
| Sonnet 5 | $0.00008 | $0.00132 |
| Haiku 4.5 | $0.00004 | $0.00066 |
Grade A, and why
react-component-scaffold 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
React Component Scaffold
Scaffold React components with tests, stories, and styles in one shot.
When to Use
- Creating a new React component from scratch
- User says "create a component", "scaffold a component"
- Need consistent component file structure across a project
When NOT to Use
- Modifying existing components
- Non-React component files
- The project has a code generator already (e.g., Plop, Hygen)
Workflow
- Ask user: component name, props (if known), and which optional files to generate
- Detect or ask: JavaScript or TypeScript, CSS Modules or styled-components
- Generate files:
ComponentName/
├── ComponentName.tsx # Component with typed props
├── ComponentName.test.tsx # Basic render + interaction tests
├── ComponentName.stories.tsx # Storybook story (if project uses Storybook)
├── ComponentName.module.css # CSS Module (if using CSS Modules)
└── index.ts # Barrel export
- Write the component with:
- Typed props interface
- Default exports
- Accessibility attributes (aria-label, role)
- Loading/empty/error states if data-dependent
Component Template
import { type FC } from 'react';
import styles from './Button.module.css';
interface ButtonProps {
/** Button label text */
children: string;
/** Visual variant */
variant?: 'primary' | 'secondary' | 'danger';
/** Disabled state */
disabled?: boolean;
/** Click handler */
onClick?: () => void;
}
export const Button: FC<ButtonProps> = ({
children,
variant = 'primary',
disabled = false,
onClick,
}) => {
return (
<button
className={`${styles.button} ${styles[variant]}`}
disabled={disabled}
onClick={onClick}
type="button"
>
{children}
</button>
);
};
Key Principles
- One component per folder — co-locate all related files
- Always include a barrel export (
index.ts) - Props interface should be exported (for consumers)
- Add JSDoc comments for each prop
- Use
type="button"on buttons to prevent form submission
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.
- 2d ago First seen · 103 lines · 41 tokens per session scan A e48f20aaa22f
react-component-scaffold is a skill published in the GitHub repository luqiang-code/claude-code-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 41 tokens to every session and 660 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.
Other skills, from other repositories
golden-chat
Use when testing the goldenchat golden build.
golden-epub
Use when testing the epub golden build.
golden-html-multi
Use when testing the multi-file html build.
golden-jupyter-dir
Use when testing the goldenjupyterdir golden build.
golden-jupyter-kw
Use when testing the goldenjupyterkw golden build.
golden-pdf
Use when testing the pdf golden build.