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/nonlinear-xyz/factory-kit/factory-designnpx skills add nonlinear-xyz/factory-kit --skill factory-designgit clone --depth 1 https://github.com/nonlinear-xyz/factory-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/skills/nonlinear-xyz/factory-kit/factory-design)<a href="https://agentmods.dev/skills/nonlinear-xyz/factory-kit/factory-design"><img src="https://agentmods.dev/badge/skills/nonlinear-xyz/factory-kit/factory-design.svg" alt="Measured on agentmods" 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 | $0.00100 | $0.03910 |
| Opus 5 | $0.00050 | $0.01955 |
| Sonnet 5 | $0.00020 | $0.00782 |
| Haiku 4.5 | $0.00010 | $0.00391 |
Grade A, and why
factory-design 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 5d 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 — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Factory design
Each section leads with Principle (one sentence, stack-agnostic), then Why (constraint → option → tradeoff), then Recipe (the Tailwind + CSS-vars shape we use), and Failure mode when there's one to name.
The kit's default styling layer is Tailwind. The discipline here is what turns Tailwind from "every page styled in isolation" into a coherent design system: a small shared vocabulary that every surface draws from.
Token vocabulary — name intent, not palette position
Principle. Tokens are named by the role they play in the layout, never by their position in a colour ladder.
Why. Palette-position names (primary, secondary, base-100, base-200, neutral-300) are the dominant failure mode of theme systems like daisyUI, Bootstrap, and stock Material. The names describe where on the ramp a colour lives, not what it's for. Asking "is this card a base-100 or base-200?" has no semantic answer — so each developer (and you-on-a-different-day) guesses, and drift accumulates invisibly until two surfaces side by side look subtly off and nobody can articulate why.
Intent-named tokens collapse the ambiguity. bg is the page background. surface is the raised thing on top of the background. fg is primary text. fg-muted is the dimmer label next to it. accent is the brand pull. border-subtle is a divider you barely see. When the vocabulary is small and meaning is unambiguous, the same decision gets made the same way every time. That's the cleanness users feel — it's not "better colours," it's lower entropy.
Recipe. Eight to twelve tokens covers most projects. Default set:
| Token | Role |
|---|---|
bg |
Page background |
surface |
Raised surface on top of bg (cards, panels) |
surface-hover |
What surface becomes on hover |
fg |
Primary text |
fg-muted |
Secondary text, captions, dimmer labels |
border |
Standard divider / outline |
border-subtle |
Faint divider (~50% the contrast of border) |
accent |
Brand pull — CTAs, active state, focus rings |
accent-hover |
What accent becomes on hover |
accent-fg |
Text colour that sits on top of accent |
code-bg |
Inline code / code-block background (only if the project ships docs) |
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.
- 5d ago First seen · 247 lines · 100 tokens per session scan A 331a65c6a368
factory-design is a skill published in the GitHub repository nonlinear-xyz/factory-kit (9 stars, last pushed 1mo ago), licensed MIT. It adds 100 tokens to every session and 3,910 once invoked, about $0.0005 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
polish
Frontend quick wins to wow effects (6 dimensions). Use when: "polish", "beautify", "improve", "wow", "improve design", "enhance", "quick wins".
ui-web
Web UI - glassmorphism, Tailwind, dark mode, accessibility.
frontend-ui-ux-system
提供公司级前端 UI/UX 设计知识库，覆盖产品类型、视觉方向、设计 token、布局、 交互、可访问性、动效与交付检查。当前端任务需要统一设计语言或体验门禁时使用。.
muapi-url-to-design
Analyze a website URL and generate a redesigned, improved UI — recreate the visual design with modern aesthetics, better hierarchy, and fresh brand direction.
generic-design-system
Complete design system reference for any project - colors, typography, spacing, components, animations. Adapts to project theme and tech stack. Use when implementing UI, choosing colors, creating animations, or ensuring brand consistency. For new design systems, use ui-research skill first.
generic-static-feature-developer
Guide feature development for static HTML/CSS/JS sites. Covers patterns, automation workflows, and content validation. Use when adding features, modifying automation, or planning changes.