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 AsyrafHussin/agent-skills --skill web-design-guidelinesgit clone --depth 1 https://github.com/AsyrafHussin/agent-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/asyrafhussin/agent-skills/web-design-guidelines)<a href="https://agentmods.dev/skills/asyrafhussin/agent-skills/web-design-guidelines"><img src="https://agentmods.dev/badge/skills/asyrafhussin/agent-skills/web-design-guidelines/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/asyrafhussin/agent-skills/web-design-guidelines"><img src="https://agentmods.dev/badge/skills/asyrafhussin/agent-skills/web-design-guidelines.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00071 | $0.01964 |
| Opus 5 | $0.00036 | $0.00982 |
| Sonnet 5 | $0.00014 | $0.00393 |
| Haiku 4.5 | $0.00007 | $0.00196 |
Grade A, and why
web-design-guidelines 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 12d 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Design Guidelines
WCAG accessibility, semantic HTML, keyboard navigation, forms, and performance patterns for inclusive web interfaces. Contains 23 rules across 4 categories. Supports both coding reference and audit mode.
Metadata
- Version: 2.1.0
- Rule Count: 23 rules across 4 categories
- License: MIT
How to Audit
When the user asks to "audit accessibility", "check WCAG compliance", or "review accessibility" — run the checklist below against their codebase.
Step 1: Determine Scope
- If arguments provided (
$ARGUMENTS): audit only those files or components - If no arguments: audit all UI components and pages in the codebase
Step 2: Detect Stack
Check the project for:
.tsx/.jsxfiles → React.vuefiles → Vue.blade.phpfiles → Laravel Blade.htmlfiles → Static HTML
Step 3: Run Accessibility Checklist
Work through every item below. For each, output:
- PASS — brief confirmation of what was verified
- FAIL — exact
file:line, description of the issue, and fix recommendation - N/A — if the check does not apply to this project
Semantic HTML & Structure
- Pages use semantic elements (
<header>,<main>,<nav>,<footer>,<article>,<section>) — not<div>soup - Heading hierarchy is sequential (
h1→h2→h3) — no skipped levels - One
<h1>per page - Skip link exists to bypass navigation (
<a href="#main-content">Skip to content</a>) - Landmark regions are labelled when duplicated (
aria-labelon multiple<nav>elements)
Keyboard Navigation
- All interactive elements are reachable via Tab key
- Focus order follows visual order (no positive
tabindexvalues) - Focus indicator is visible on all focusable elements (not removed with
outline: nonewithout replacement) - Modal dialogs trap focus and return focus on close
- Custom components (dropdowns, tabs, accordions) support expected keyboard patterns (Arrow keys, Escape, Enter)
What ships with it
28 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.
- AGENTS.md 127 KB
- metadata.json 1.3 KB
- README.md 1.6 KB
- rules/_sections.md 1.6 KB
- rules/_template.md 881 B
- rules/a11y-alt-text.md 3.9 KB
- rules/a11y-aria-labels.md 2.5 KB
- rules/a11y-color-contrast.md 3.4 KB
- rules/a11y-error-messages.md 6.5 KB
- rules/a11y-focus-management.md 3.8 KB
- rules/a11y-form-labels.md 5.4 KB
- rules/a11y-heading-hierarchy.md 4.4 KB
- rules/a11y-keyboard-nav.md 4.5 KB
- rules/a11y-live-regions.md 5.6 KB
- rules/a11y-screen-reader.md 3.4 KB
- rules/a11y-semantic-html.md 4.9 KB
- rules/a11y-skip-links.md 4.3 KB
- rules/form-autocomplete.md 5.8 KB
- rules/form-error-display.md 8.2 KB
- rules/form-inline-validation.md 11 KB
- rules/form-input-types.md 4.5 KB
- rules/form-multi-step.md 12 KB
- rules/form-placeholder-usage.md 5.2 KB
- rules/form-submit-feedback.md 6.5 KB
- rules/form-validation-ux.md 7.5 KB
- rules/motion-reduced.md 5.6 KB
- rules/perf-image-loading.md 3.9 KB
- rules/perf-layout-stability.md 5.3 KB
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.
- 12d ago First seen · 211 lines · 71 tokens per session scan A 01bd9762a820
web-design-guidelines is a skill published in the GitHub repository AsyrafHussin/agent-skills (75 stars, last pushed 16d ago), licensed MIT. It adds 71 tokens to every session and 1,964 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
recipe-front-design
Execute from repository evidence through applicable UI Spec and optional ADR decisions to complete frontend Design Doc approval.
recipe-front-adjust
Adjust an already-implemented UI in-session with verification against the design source.
ring:validating-ux-completeness
Validating that UX specifications are complete before technical design: a read-only checklist over wireframes, states, responsive behavior, accessibility, and component-library alignment, emitting a DESIGN VALIDATED / NEEDS REVISION verdict to design-validation.md. Standalone utility — run after a product-designer…
ring:checking-frontend-quality
Checking frontend quality against changed UI via ring:qa-frontend in accessibility, visual, e2e, or performance mode and aggregating pass/fail verdicts. Use when a frontend change needs standalone a11y, visual-snapshot, Playwright e2e, or Lighthouse/Core-Web-Vitals validation outside the dev cycle. Skip for…
recipe-front-adjust
Adjust an implemented UI with focused evidence, verification, and quality checks.
fidelity-gate
Build a UI against a frozen visual reference without drift - an inventory extracted before any code, a relics list, and a gate that MEASURES computed styles on a fixture carrying the reference's own data. Use when a mockup, design spec or screenshot is the contract.