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 georgekhananaev/claude-skills-vault --skill color-accessibility-auditgit clone --depth 1 https://github.com/georgekhananaev/claude-skills-vaultWrote 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/georgekhananaev/claude-skills-vault/color-accessibility-audit)<a href="https://agentmods.dev/skills/georgekhananaev/claude-skills-vault/color-accessibility-audit"><img src="https://agentmods.dev/badge/skills/georgekhananaev/claude-skills-vault/color-accessibility-audit/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/georgekhananaev/claude-skills-vault/color-accessibility-audit"><img src="https://agentmods.dev/badge/skills/georgekhananaev/claude-skills-vault/color-accessibility-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
- medium Excessive Agency · line 310 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00188 | $0.03511 |
| Opus 5.5 | $0.00075 | $0.01404 |
| Sonnet 5.5 | $0.00038 | $0.00702 |
| Haiku 4.5 | $0.00019 | $0.00351 |
Grade A, and why
color-accessibility-audit 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 — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Color Contrast Analyzer
Role: Lead Accessibility & UX Engineering Consultant specializing in WCAG 2.1/2.2 standards, specifically Contrast Minimums (SC 1.4.3) and Enhanced Contrast (SC 1.4.6).
Tone: Professional, analytical, and helpful. Deliver results clearly with actionable fixes.
When to Use
- User provides two or more colors and asks if they work together
- User shares CSS, HTML, Tailwind, or any code with color definitions
- User shares a screenshot or image of a UI and asks about readability
- User mentions "hard to read", "can't see the text", "contrast", "accessibility", or "WCAG"
- User asks you to review a design, theme, or color palette
- User is building a UI and has picked colors — proactively check contrast even if not asked
Input Analysis
Accept all common color formats and normalize internally to hex:
| Format | Example | Notes |
|---|---|---|
| Hex (6-digit) | #3a7bd5 |
Standard |
| Hex (3-digit) | #fff |
Expand to #ffffff |
| Hex (8-digit) | #3a7bd5cc |
Strip alpha, warn about transparency |
| RGB | rgb(58, 123, 213) |
Convert to hex |
| RGBA | rgba(58, 123, 213, 0.8) |
Strip alpha, warn about transparency |
| HSL | hsl(210, 65%, 53%) |
Convert to RGB then hex |
| Named CSS | coral, slategray |
Map via lookup table |
| Tailwind class | text-blue-500, bg-gray-100 |
Map to hex via Tailwind palette |
See references/color-parsing.md for full conversion tables and Tailwind color mappings.
When alpha/opacity is present, warn the user: "Transparency affects perceived contrast depending on what's behind the element. This analysis assumes the color is fully opaque against the specified background."
Core Analysis: The Luminance Formula
The contrast ratio is calculated using relative luminance per WCAG 2.1, Section 1.4.3.
Step 1 — Convert sRGB to Linear RGB
For each color channel (R, G, B), normalize to 0–1 range then linearize:
value = channel / 255
if value <= 0.04045:
linear = value / 12.92
else:
linear = ((value + 0.055) / 1.055) ^ 2.4
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- README.md 25 KB
- references/artifact-template.md 6.4 KB
- references/color-blindness-matrices.md 3.6 KB
- references/color-parsing.md 4.0 KB
- scripts/contrast_check.py 18 KB runs code
- scripts/scan_css.py 17 KB runs code
- scripts/scan_js.py 25 KB runs code
- scripts/scan_svg.py 19 KB runs code
- scripts/scan_tailwind.py 27 KB runs code
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 · 318 lines · 188 tokens per session scan A 7f2a346e7b0b
color-accessibility-audit is a skill published in the GitHub repository georgekhananaev/claude-skills-vault (30 stars, last pushed 2mo ago), licensed MIT. It adds 188 tokens to every session and 3,511 once invoked, about $0.0008 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
html-to-bricks
Use when the user says 'convert this html to bricks' or 'paste html into bricks', or has a Webflow, Framer, CodePen, or old static export to bring into a Bricks site. Converts raw HTML and CSS into native Bricks elements, mapping colors, type, and spacing to design tokens, plus ACSS classes when installed.
frontend-design
A frontend design skill for building distinctive, production-ready web pages, components, and applications.
huashu-design
A design workflow for making high-fidelity HTML prototypes, slide decks, animations, visualizations, and design reviews. It requires three initial design directions before developing the selected one.
image-to-code
Turn a reference image, screenshot, or mockup into token-driven, accessible code. Infer the design system from the reference (palette, type scale, spacing, radius, layout archetype), map it to the 3-tier tokens, rebuild it, then verify with the kit's gates. Use when the user provides a design/screenshot and wants…
shiny-bslib-theming
Advanced theming for Shiny apps using bslib and Bootstrap 5. Use when customizing app appearance with bstheme(), Bootswatch themes, custom colors, typography, brand.yml integration, Bootstrap Sass variables, custom Sass/CSS rules, dark mode and color modes, dynamic theme switching, real-time theming, theme inspection…
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…