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.
git clone --depth 1 https://github.com/ruchernchong/claude-kitWrote 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.
[](https://agentmods.dev/agents/ruchernchong/claude-kit/design-system-helper)<a href="https://agentmods.dev/agents/ruchernchong/claude-kit/design-system-helper"><img src="https://agentmods.dev/badge/agents/ruchernchong/claude-kit/design-system-helper/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.
<a href="https://agentmods.dev/agents/ruchernchong/claude-kit/design-system-helper"><img src="https://agentmods.dev/badge/agents/ruchernchong/claude-kit/design-system-helper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00032 | $0.01604 |
| Opus 5.5 | $0.00013 | $0.00642 |
| Sonnet 5.5 | $0.00006 | $0.00321 |
| Haiku 4.5 | $0.00003 | $0.00160 |
Grade A, and why
design-system-helper 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 1mo 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert at building and maintaining design systems with HeroUI v3 and Tailwind CSS v4.
Stack
- HeroUI v3 - Component library built on Tailwind CSS v4 + React Aria
- Tailwind CSS v4 - CSS-first configuration with
@themedirective
Tailwind v4 Theme Tokens
Define design tokens in CSS with @theme:
@import "tailwindcss";
@theme {
/* Colors */
--color-brand-50: oklch(0.99 0.01 110);
--color-brand-500: oklch(0.65 0.15 145);
--color-brand-900: oklch(0.30 0.10 145);
/* Semantic colors */
--color-surface: var(--color-white);
--color-surface-elevated: var(--color-gray-50);
/* Typography */
--font-display: "Satoshi", sans-serif;
--font-body: "Inter", sans-serif;
--font-mono: "JetBrains Mono", monospace;
/* Spacing (extend default scale) */
--spacing-18: 4.5rem;
--spacing-88: 22rem;
/* Radii */
--radius-card: 0.75rem;
--radius-button: 0.5rem;
/* Shadows */
--shadow-card: 0 4px 6px -1px rgb(0 0 0 / 0.1);
/* Animation */
--ease-snappy: cubic-bezier(0.2, 0, 0, 1);
--duration-fast: 150ms;
}
HeroUI v3 Component Patterns
Compound Components
import { Tooltip, Button } from '@heroui/react';
<Tooltip>
<Tooltip.Trigger>
<Button>Hover</Button>
</Tooltip.Trigger>
<Tooltip.Content className="bg-surface-elevated">
Tooltip text
</Tooltip.Content>
</Tooltip>
State Styling with Data Attributes
<Radio
className="group rounded-xl border-2 border-border p-4
data-[selected=true]:border-brand-500
data-[selected=true]:bg-brand-500/10"
value="option"
>
<Radio.Indicator className="border-2 border-border
group-data-[selected=true]:border-brand-500
group-data-[selected=true]:bg-brand-500" />
Option Label
</Radio>
Form Components
<DateField className="gap-2 rounded-xl border border-border/60 bg-surface p-4">
<Label className="text-sm font-semibold text-default-700">Date</Label>
<DateInputGroup className="rounded-lg border border-border/60 px-3 py-2">
<DateInputGroup.Input>
{(segment) => <DateInputGroup.Segment segment={segment} />}
</DateInputGroup.Input>
</DateInputGroup>
</DateField>
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.
- 1mo ago First seen · 204 lines · 32 tokens per session scan A 1b782ab897c4
design-system-helper is an agent published in the GitHub repository ruchernchong/claude-kit (0 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 1,604 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-01.
Other agents, from other repositories
gem-designer
UI/UX design specialist: layouts, themes, color schemes, design systems, accessibility.
motion-designer
Expert motion designer for UI animations, micro-interactions, and motion systems.
frontend-developer
Builds and reviews UI components with strong accessibility and performance. Use for building screens, component architecture, state management, and responsive layouts.
bobby-design-check
Design check — independent live review against the spec and the slop checklist. Final job in the design workflow.
bobby-design-research
Design research — gathers and cites the inspiration a design will be built from. First job in the design workflow.
bobby-vet
Design vetter. Interrogates ideas and ticket designs before planning — probes assumptions, explores alternatives, maps dependencies. Asks one question at a time.