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/Muminur/frontend-design-craft-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/commands/muminur/frontend-design-craft-skill/colorize)<a href="https://agentmods.dev/commands/muminur/frontend-design-craft-skill/colorize"><img src="https://agentmods.dev/badge/commands/muminur/frontend-design-craft-skill/colorize.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 5.1 | $0.00006 | $0.00674 |
| Opus 5 | $0.00003 | $0.00337 |
| Sonnet 5 | $0.00001 | $0.00135 |
| Haiku 4.5 | $0.00001 | $0.00067 |
Grade A, and why
colorize 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 7d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/colorize
Build or fix a color system. Author in OKLCH; ship as CSS custom properties.
Target
$ARGUMENTS
Procedure
- Identify the brand color. If unclear, ask the user. Avoid defaulting to blue.
- Build the palette. A complete palette for most sites is 4–6 colors:
- Tinted neutral scale — 8–10 stops, all sharing the brand hue at very low chroma (
oklch(98% 0.005 H)tooklch(15% 0.02 H)whereHis the brand hue). - Brand color — used sparingly for primary action, one or two accents.
- Semantic set — success, warning, error, info. Each at 2–3 lightness stops.
- Tinted neutral scale — 8–10 stops, all sharing the brand hue at very low chroma (
- Check perceptual uniformity. OKLCH lets you generate hover/active states by stepping lightness, not by adding black or white.
--brand-hover: oklch(from var(--brand) calc(l - 4%) c h). - Verify contrast. Every text-on-background combination must hit WCAG AA (4.5:1 for body, 3:1 for large). Tools: browser devtools,
contrast-checkerCLIs. - Apply restraint. The palette has 12 tokens; the page should still feel like it uses 3–4. The rest are for states, not primaries.
Banned color moves
- Pure
#000text or#FFFbackgrounds in content - Purple → blue, pink → orange, teal → blue gradients
- Using Tailwind default colors (
blue-500, etc.) directly in components without a semantic alias - Gradient text
- More than one gradient moment per page
Output
/* Example output structure */
:root {
/* Brand */
--brand: oklch(60% 0.18 250);
--brand-hover: oklch(56% 0.18 250);
--brand-active: oklch(52% 0.18 250);
/* Tinted neutrals (8 stops) */
--neutral-0: oklch(99% 0.003 250);
--neutral-50: oklch(96% 0.005 250);
--neutral-100: oklch(92% 0.007 250);
/* ... */
--neutral-900: oklch(18% 0.015 250);
/* Semantic */
--success: oklch(60% 0.15 145);
--warning: oklch(70% 0.15 75);
--error: oklch(58% 0.20 25);
--info: oklch(60% 0.15 230);
}
Show the user the palette as a visual swatch (HTML or markdown table) before applying 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.
- 7d ago First seen · 59 lines · 6 tokens per session scan A 10269bbe7dfd
colorize is a command published in the GitHub repository Muminur/frontend-design-craft-skill (4 stars, last pushed 3mo ago), licensed MIT. It adds 6 tokens to every session and 674 once invoked, about $0.0000 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 commands, from other repositories
combo
A collection of reusable interface patterns that combine icons with labels, badges, and buttons. It documents variants such as status-colored tags and different button styles.
ux-recommend
The v2 flagship. Runs the 5-parallel-search Python engine across 11 data manifests (75+ styles, 170+ palettes, 65+ type pairs, 120+ components, 170+ industries, 110+ UX laws, 50+ motion presets, 120+ anti-patterns, 92 brand specs) and returns a complete recommended design system for your project — with always-on…
color-specialist
Use when colour is failing. Contrast below AA, a palette with no system behind it, dark mode that is only inverted light mode, or semantic colours that carry no meaning.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
revisar-ui
Auditoria visual retroativa de 6 pilares do código frontend implementado.
improve-ui-ux
Audit and improve an existing interface through one evidence-backed, design-system-aware implementation and browser-verification pass.