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 SkillMedev/skills --skill color-palette-buildergit clone --depth 1 https://github.com/SkillMedev/skillsWrote 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/skillmedev/skills/color-palette-builder)<a href="https://agentmods.dev/skills/skillmedev/skills/color-palette-builder"><img src="https://agentmods.dev/badge/skills/skillmedev/skills/color-palette-builder/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/skillmedev/skills/color-palette-builder"><img src="https://agentmods.dev/badge/skills/skillmedev/skills/color-palette-builder.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 | $0.00127 | $0.01663 |
| Opus 5.5 | $0.00051 | $0.00665 |
| Sonnet 5.5 | $0.00025 | $0.00333 |
| Haiku 4.5 | $0.00013 | $0.00166 |
Grade A, and why
color-palette-builder 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 11d 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.
Color Palette Builder
A brand color palette is not a mood board - it is a functional system with roles, scales, and rules. The costly failure is shipping pretty swatches with no usage rules: developers guess, screens drift, and within months the product has fourteen slightly different blues and body text that fails contrast. Build the palette so a developer can implement it without asking a single question.
Operating procedure
Work the steps in order: roles before scales, scales before contrast checks - contrast is verified per color pair, and pairs only exist once the scales do.
Step 1: Gather inputs
Collect these before generating anything; label any guess as a guess.
- Anchor color, if one exists (hex value). If none, collect 3-5 brand adjectives plus the category's color conventions to derive one.
- Surfaces in scope: marketing site, product UI, or both. Product UI needs a deeper neutral scale.
- Dark mode: in scope now, later, or never. Default to architecting semantic tokens regardless - it adds no cost now and prevents significant rework later.
- Accessibility target: default WCAG 2.1 AA. Ask whether AAA is required (government, healthcare, and education products often require it).
- Constraints: category semantics (red and green in finance already mean loss and gain), competitor colors to avoid, and any existing token naming convention to match.
Step 2: Choose or validate the anchor
Every strong palette derives from a single anchor - the primary brand color. It must pass three tests: works on white, works on dark surfaces, and survives single-color reproduction (favicon, embroidery, one-color print). Derive the rest of the palette from the anchor rather than assembling unrelated colors; derivation is what keeps the system coherent.
Step 3: Assign roles before names
Every color gets a role before it gets a name:
- Primary - main brand actions, links, focus rings.
- Secondary - supporting accents, hover states, data visualization.
- Neutral - text, borders, backgrounds. The most underestimated role: a well-stepped gray scale does more work than any accent color.
- Semantic - success green, warning amber, error red, info blue. Keep them visually distinct from Primary, or status and interactivity blur together.
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.
- 11d ago Changed · +2 lines · +1 tokens per session 313fd144d3b1
- 1mo ago First seen · 101 lines · 126 tokens per session scan A a5e988aa884d
color-palette-builder is a skill published in the GitHub repository SkillMedev/skills (19 stars, last pushed 3d ago), licensed MIT. It adds 127 tokens to every session and 1,663 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
design-doctrine
The house rules for ANY design or UI work - the verification protocol (run the gate, never claim a number), the absolute no-emoji rule, token by intent, one shared theme, the eight states, one thing leads, and output completeness. Load this FIRST whenever building, reviewing, or theming a screen, component, or token…
design-loop
Autonomous multi-page site builder using a baton-passing loop. Each iteration reads a task from .design/next-prompt.md, generates a page in HTML/Tailwind, integrates it into the site, verifies visually, then writes the next task to keep the loop alive. Use whenever the user asks to build an entire site autonomously…
color-palette
Generate complete, accessible colour palettes from a single brand hex. Produces 11-shade scale (50-950), semantic tokens, dark mode variants, Tailwind v4 CSS output, WCAG contrast checks. Use whenever the user supplies a brand hex and asks for a palette, mentions setting up a design system, wants Tailwind theme…
tailwind-theme-builder
Set up Tailwind v4 + shadcn/ui themed UI with dark mode. Install deps, configure CSS variables via @theme inline, wire dark mode toggle, verify. Use whenever the user mentions Tailwind v4, setting up Tailwind theming, shadcn/ui colours, dark mode, or troubleshooting colours not working, tw-animate-css errors, @theme…
design-system
Extract a complete design system from an existing website or screenshot into a DESIGN.md file. Analyses colours, typography, component styles, spacing, and atmosphere through browser automation and HTML inspection. Produces a semantic design system document optimised for consistent page generation. Triggers: 'extract…
design-review
Review a web app or page for visual design quality — layout, typography, spacing, colour, hierarchy, consistency, interaction patterns, and responsive behaviour. Not a UX audit (that checks usability) — this checks whether it looks professional and polished. Produces a design findings report with screenshots.…