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 skills-il/developer-tools --skill wcag-accessibility-widgetgit clone --depth 1 https://github.com/skills-il/developer-toolsWrote 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/skills-il/developer-tools/wcag-accessibility-widget)<a href="https://agentmods.dev/skills/skills-il/developer-tools/wcag-accessibility-widget"><img src="https://agentmods.dev/badge/skills/skills-il/developer-tools/wcag-accessibility-widget/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/skills-il/developer-tools/wcag-accessibility-widget"><img src="https://agentmods.dev/badge/skills/skills-il/developer-tools/wcag-accessibility-widget.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 | $0.00177 | $0.06344 |
| Opus 5.5 | $0.00071 | $0.02538 |
| Sonnet 5.5 | $0.00035 | $0.01269 |
| Haiku 4.5 | $0.00018 | $0.00634 |
Grade A, and why
wcag-accessibility-widget 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- wcag-accessibility-widget — 95% identical, 403 lines differ
How it starts
The opening of the file, as written. The whole thing — 408 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WCAG Accessibility Widget
Legal notice
This skill explains the Israeli web accessibility rules in general terms and helps you build a preferences widget and a statement page. It is not legal advice and not an accessibility audit. A widget does not by itself make a site meet ת"י 5568: the obligation is on the site's own content and markup. Whether a particular site is obliged, exempt, or conforms is a question for a מורשה לנגישות השירות or a lawyer who has examined that site.
Overview
A self-hosted floating accessibility widget: a fixed button that opens a panel of preference toggles. Settings are persisted in localStorage and applied as CSS classes on <html>. No third-party service needed.
Build the site right first, then add the widget. The regulation requires the content itself to conform. A toolbar does not add missing labels, fix focus order, caption a video, or tag a PDF. In April 2025 the US FTC approved a final order requiring accessiBe to pay $1 million over claims that its widget could make any website WCAG-compliant. Never describe the widget to a client as the compliance solution.
The Israeli Legal Floor
| Topic | What the rules say |
|---|---|
| Standard | Regulation 35א(א): web services must meet the "תקן נגישות אינטרנט", defined in regulation 35 as ת"י 5568, at level AA. |
| WCAG version | The May 2021 edition of ת"י 5568 Part 1 replaced the March 2013 edition and still adopts WCAG 2.0 (December 2008) with Israeli changes. WCAG 2.1 and 2.2 AA are supersets; W3C states that content conforming to 2.2 also conforms to 2.0 and 2.1. Target 2.1 or 2.2 AA, but do not write "WCAG 2.1 = ת"י 5568". |
| Documents | A document such as a PDF prepared from 26 October 2017 and uploaded to the site must be accessible (35א(ג)). |
| Video | Captions for prerecorded video (SC 1.2.2) are required of public authorities and of businesses whose average turnover exceeds 5 million NIS that edit or produce recorded video (35ד). |
| Exemptions | An עוסק פטור, or a business whose average annual turnover does not exceed 100,000 NIS, is exempt from the web chapter (35ו(ז)). Other exemptions exist (35ו). Do not decide exemption for a client; point them to the regulation and a professional. |
| Notice and cure | A deviation is not treated as a breach unless the owner received notice and did not fix it within a reasonable time, no later than 60 days (35א(ד)). |
| Exposure | A court may award compensation of up to 50,000 NIS without proof of damage for a breach of the accessibility provisions (Equal Rights law, s.19נא(ב)); the figure is index-linked. |
What ships with it
7 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.
- 1mo ago Changed · +163 lines · +12 tokens per session 674da515b165
- 1mo ago First seen · 245 lines · 165 tokens per session scan A ddc086a7c38f
wcag-accessibility-widget is a skill published in the GitHub repository skills-il/developer-tools (13 stars, last pushed 3d ago), licensed MIT. It adds 177 tokens to every session and 6,344 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
anti-slop-design
Autonomous Principal Design Technologist. Cures vibe-coded software from AI frontend slop using curated token archetypes and 7-axis quality gating.
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
open-design-setup
Prepare or repair a project's prototyping environment so open-design can build prototypes with the project's own component library and render them through the project's toolchain. Use when the library target is needed and docs/design/prototyping.md is missing, stale, or failing; excludes HTML-only design work and…
frontend-visual-qa
Audits rendered UI and specific task/object-link handoffs; excludes ordinary source citations alone. Audits already-rendered UI and Markdown/Obsidian image layout — web app, deck/slide, dashboard, design-system, or Electron/native app — via real-browser/native-app journeys and a Playwright sweep. Use after UI…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.