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 skills add jaywilburn/refactoring-ui-skill --skill refactoring-uigit clone --depth 1 https://github.com/jaywilburn/refactoring-ui-skillWrote 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/jaywilburn/refactoring-ui-skill/refactoring-ui)<a href="https://agentmods.dev/skills/jaywilburn/refactoring-ui-skill/refactoring-ui"><img src="https://agentmods.dev/badge/skills/jaywilburn/refactoring-ui-skill/refactoring-ui/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/skills/jaywilburn/refactoring-ui-skill/refactoring-ui"><img src="https://agentmods.dev/badge/skills/jaywilburn/refactoring-ui-skill/refactoring-ui.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 | $0.00154 | $0.11430 |
| Opus 5.5 | $0.00062 | $0.04572 |
| Sonnet 5.5 | $0.00031 | $0.02286 |
| Haiku 4.5 | $0.00015 | $0.01143 |
Grade A, and why
refactoring-ui 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 — 1,119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactoring UI Design System
Core Philosophy
Design decisions should be made with intention, not decoration. Every visual choice—color, size, spacing, weight—communicates hierarchy and guides the user's attention. Start with too much whitespace, then remove it. Start with less contrast, then add it where needed.
Before writing any CSS, answer: what should this feel like? A financial dashboard and a children's learning app demand completely different visual treatments. The sections below move from strategic thinking (personality, color theory, layout strategy) down to tactical execution (spacing values, shadow syntax, animation timing).
Design Thinking
Design Personality & Tone
Every interface has a personality whether you choose one or not. Choosing intentionally is the difference between a design that feels right and one that feels generic.
The Personality Spectrum
Plot your design on two axes:
- Formal ↔ Casual: How structured and serious vs relaxed and approachable
- Reserved ↔ Expressive: How restrained and minimal vs bold and vibrant
Four quadrants:
| Reserved | Expressive | |
|---|---|---|
| Formal | Banking, legal, enterprise, government | Luxury brands, high-end retail, fashion |
| Casual | Developer tools, documentation, utilities | Gaming, social apps, children's education |
Mapping Design Signals to Personality
Each visual lever pushes the design toward a quadrant:
- Border-radius: 2-4px (formal) → 8-12px (moderate) → 16px+ (casual). Match to personality—don't default to max.
- Font choice: Geometric sans like Inter/Roboto (modern, neutral), humanist sans like Source Sans/Nunito (friendly, approachable), serif like Merriweather/Playfair (traditional, authoritative), monospace accents (technical, developer-oriented)
- Color saturation: Low/muted (reserved) → high/vibrant (expressive). See Color Theory section.
- Whitespace density: Generous (formal, premium) → tight (casual, energetic, data-dense)
- Shadow style: Subtle and diffused (reserved) → dramatic with strong offsets (expressive). Or no shadows at all for minimal/flat designs.
- Imagery style: Photography (authentic, serious) → illustration (approachable, playful) → icons only (utilitarian, technical)
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 · 1,119 lines · 154 tokens per session scan A e8df9a646129
refactoring-ui is a skill published in the GitHub repository jaywilburn/refactoring-ui-skill (96 stars, last pushed 5mo ago), licensed MIT. It adds 154 tokens to every session and 11,430 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
anti-slop-design
Autonomous Principal Design Technologist. Cures vibe-coded software from AI frontend slop using curated token archetypes and 7-axis quality gating.
setting-up-charcoal-tailwind
Use before writing or editing code that uses @charcoal-ui with Tailwind, and whenever such a project's charcoal setup is unverified or incomplete. The v2 token route still needs the theme CSS and the .ch-token-v2 opt-in, which the preset does not supply.
choosing-charcoal-styling
Use before writing or editing any code that imports @charcoal-ui, and whenever a project's charcoal setup is unverified or incomplete. Decides between the CSS variables, Tailwind and styled-components routes, and names the setup steps that are silently missing in most projects.
setting-up-charcoal-styled
Use before writing or editing code that uses @charcoal-ui with styled-components, TokenInjector, createTheme or addThemeUtils, and whenever such a project's charcoal setup is unverified or incomplete.
choosing-charcoal-tokens
Use before choosing any color, text style, spacing, radius or border value in code that uses @charcoal-ui, and whenever a literal is about to be written where a token exists — a hex color, a px padding or gap, a font-size, a border-radius or border-width. Charcoal has one correct token for each of these and the choice…
variant-design-system
Design System mode — tokens → components → pages three-layer workflow. Generate a complete token set (palette/type/spacing/motion/elevation/radius), confirm it, then all downstream outputs are visually consistent. Triggers on: ds, design system, tokens, create token set, define palette, define tokens, set up tokens…