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 chadixearth/graphyloop --skill web-accessibilitygit clone --depth 1 https://github.com/chadixearth/graphyloopWrote 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/chadixearth/graphyloop/web-accessibility)<a href="https://agentmods.dev/skills/chadixearth/graphyloop/web-accessibility"><img src="https://agentmods.dev/badge/skills/chadixearth/graphyloop/web-accessibility/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/chadixearth/graphyloop/web-accessibility"><img src="https://agentmods.dev/badge/skills/chadixearth/graphyloop/web-accessibility.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 | $0.00083 | $0.01514 |
| Opus 5 | $0.00042 | $0.00757 |
| Sonnet 5 | $0.00017 | $0.00303 |
| Haiku 4.5 | $0.00008 | $0.00151 |
Grade A, and why
web-accessibility 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 5d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web accessibility (WCAG 2.2 AA, implementation-level)
Accessibility fails in a small number of predictable places: a div wired with
onClick, a modal that leaves focus behind it, an input whose label is only a
placeholder, an error announced in red and nowhere else, and an icon button with no
name. Fix those five and most of an audit disappears.
When to activate
- Building or changing forms, dialogs, dropdowns, menus, tabs, accordions, carousels, data tables, toasts, or any custom control.
- Anything described as "compliance", "WCAG", "508", "screen reader", "keyboard".
- A UI review pass, or a design handoff with hover-only affordances or thin grey text.
Rule 0: semantics before ARIA
Use the element that already has the behavior. <button>, <a href>, <input>,
<select>, <dialog>, <details>, <table>, <nav>, <main>, <label>,
<fieldset>. Each brings focusability, keyboard handling, and a role for free.
<div onClick>is not a button: no focus, no Enter/Space, no role. If you must, it needsrole="button" tabindex="0"and an Enter+Space handler — three ways to reintroduce a bug the native element never had.- Wrong ARIA is worse than no ARIA.
role="button"on a link,aria-hiddenon a focusable node, or anaria-labelthat contradicts visible text actively misleads. - One
<h1>per page; heading levels never skip. Landmarks (header,nav,main,footer) present once each,mainexactly once.
Keyboard and focus
- Everything interactive is reachable with Tab in visual order and operable with Enter (buttons/links), Space (buttons/checkboxes), arrows (radios, tabs, menus, listbox), Escape (dismiss).
- Never
outline: nonewithout a replacement. Visible focus needs ≥ 3:1 contrast against the adjacent color;:focus-visibleis the right hook. - Dialogs and drawers: move focus in on open (first focusable or the heading), trap
it while open, restore it to the trigger on close, close on Escape, and mark the
rest of the page inert (
inertattribute oraria-hiddenon the background). tabindexis0or-1. Positive values reorder the whole page and are a bug.- Skip link to
#mainas the first focusable element, visible on focus. - Never trap focus in a loop the user cannot leave, and never move focus on keystroke while typing (that includes "helpful" autofocus on search-as-you-type).
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.
- 5d ago First seen · 110 lines · 83 tokens per session scan A f606ccf993cb
web-accessibility is a skill published in the GitHub repository chadixearth/graphyloop (2 stars, last pushed 23d ago), licensed MIT. It adds 83 tokens to every session and 1,514 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 2026-09-03.
Other skills, from other repositories
hipson-visual-experience-director
Use for visual direction, premium UI/UX art direction, motion interaction design, Codex-ready implementation briefs, and visual QA for web experiences.
hipson-premium-ui-ux
Use for premium UI/UX review and implementation planning in Hipson frontend projects, especially screenshot-backed landing pages, forms, visual polish, accessibility, responsive behavior, and design-agent packets.
hipson-creative-frontend-motion-architect
Use for premium creative frontend, motion UI, scroll-driven animation, scrollytelling, cinematic landing pages, microinteractions, and implementation-ready prompts for React/Next.js frontend agents.
impeccable
Create distinctive, production-grade frontend interfaces with high design quality. Generates creative, polished code that avoids generic AI aesthetics. Use when the user asks to build web components, pages, artifacts, posters, or applications, or when any design skill requires project context. Call with 'craft' for…
figma-implement-design
Translates Figma designs into production-ready application code with 1:1 visual fidelity. Use when implementing UI code from Figma files, when user mentions "implement design", "generate code", "implement component", provides Figma URLs, or asks to build components matching Figma specs. For Figma canvas writes via…
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.