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 ThomasSweet/a11y-foundation --skill llmsgit clone --depth 1 https://github.com/ThomasSweet/a11y-foundationWrote 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/thomassweet/a11y-foundation/llms)<a href="https://agentmods.dev/skills/thomassweet/a11y-foundation/llms"><img src="https://agentmods.dev/badge/skills/thomassweet/a11y-foundation/llms/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/thomassweet/a11y-foundation/llms"><img src="https://agentmods.dev/badge/skills/thomassweet/a11y-foundation/llms.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00082 | $0.01807 |
| Opus 5 | $0.00041 | $0.00903 |
| Sonnet 5 | $0.00016 | $0.00361 |
| Haiku 4.5 | $0.00008 | $0.00181 |
Grade A, and why
accessible-by-default 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 9d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- accessible-by-default — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessible by default
The web platform ships most of accessibility already built in. Most barriers
are not missing ARIA — they are a native element that was replaced by a div,
and then partially rebuilt.
So the rule is: use the thing that already does the job, and don't break what it gives you. Everything below follows from that.
Before building a component, check what already exists
| You need | Use | Not |
|---|---|---|
| A modal | <dialog> + showModal() |
div + focus-trap library |
| A menu, tooltip, or any transient overlay | popover attribute (+ anchor positioning) |
div + click-outside handler |
| Expand/collapse | <details> / <summary> |
div + aria-expanded + height JS |
| A dropdown | <select> (customisable <select> if you must restyle) |
div + listbox roles |
| Any clickable thing | <button> |
<div onclick> |
| Anything that navigates | <a href> |
<button> + router.push |
| A form field label | <label for> |
placeholder, aria-label |
| Grouped controls | <fieldset> + <legend> |
div + aria-labelledby |
| Field validation styling | :user-valid / :user-invalid |
JS class toggling on every keystroke |
| A progress or loading state | <progress>, aria-busy |
animated div with no name |
Each native element brings keyboard behaviour, focus management, a role, an accessible name, and platform conventions the user already knows. A rebuilt version starts at zero and has to earn all of it back.
The first rule of ARIA: if a native element gives you the semantics, use it instead of the ARIA attribute. No ARIA is better than bad ARIA — a wrong role overrides what the element correctly reported.
Non-negotiables in anything you write
- Never remove focus visibility.
outline: noneis only acceptable when the same rule paints a visible replacement. Style:focus-visible, keep it at least 3:1 against what surrounds it, and never let sticky headers cover the focused element (WCAG 2.2 adds 2.4.11 for exactly this). - Keyboard reaches everything, in a sensible order. Reading order is DOM
order; CSS reordering (
order,grid-area,flex-direction: row-reverse) desyncs the two. Never usetabindexgreater than 0. - Never signal with color alone. Pair it with text, an icon, or a shape.
- Text contrast 4.5:1, large text 3:1, and 3:1 for the visual boundary of any control or meaningful graphic.
- Pointer targets at least 24x24 CSS pixels, or spaced far enough apart to amount to the same thing. 44px is the comfortable choice.
- Reflow at 320 CSS pixels — equivalently 400% zoom — without a second
scroll direction. Logical properties, intrinsic grids, and
min-inline-size: 0on flex/grid children get you most of the way. - Never disable zoom. No
user-scalable=no, nomaximum-scale=1. - Every image, icon, and control has a name, and decorative ones are
explicitly empty (
alt="") rather than unnamed.
What ships with it
3 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.
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.
- 9d ago First seen · 154 lines · 82 tokens per session scan A b4bdda94c075
accessible-by-default is a skill published in the GitHub repository ThomasSweet/a11y-foundation (23 stars, last pushed 2d ago), licensed MIT. It adds 82 tokens to every session and 1,807 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
implement-component
Implements production-ready UI using DB UX Design System v3 components, tokens, and icons with a discovery-first approach.
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.
accessibility
Accessibility patterns for WCAG 2.2 compliance, keyboard focus management, React Aria component patterns, cognitive inclusion, native HTML-first philosophy, and user preference honoring. Use when implementing screen reader support, keyboard navigation, ARIA patterns, focus traps, accessible component libraries…
accessibility
Use when making a web UI conform to WCAG 2.2 Level AA — axe-core or Lighthouse a11y violations, keyboard operability, focus management, ARIA roles/names/live regions, contrast, tap-target size. NOT palette or visual intent (that is design), NOT test-runner setup (that is testing-web), NOT LCP/page-speed (that is…
absolute-ui
Build polished, intentional UIs with concrete CSS/Tailwind values — typography, color, layout, spacing, dark mode, accessibility, animations, components. Encodes specific, opinionated rules with exact values, not vague advice. Covers buttons, cards, forms, tables, navigation, dashboards, landing pages, onboarding, and…
design-engineering
Premium design engineering skill for agentic workflows — produces high-end, distinctive UI designs using DESIGN.md as the portable contract across Pencil MCP (in-IDE canvas), Figma MCP (team handoff + design tokens), and Google Stitch (vibe exploration + AI generation). Enforces anti-generic principles, WCAG 2.2 AA…