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 thermiteau/maverick --skill mav-bp-accessibilitygit clone --depth 1 https://github.com/thermiteau/maverickWrote 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/thermiteau/maverick/mav-bp-accessibility)<a href="https://agentmods.dev/skills/thermiteau/maverick/mav-bp-accessibility"><img src="https://agentmods.dev/badge/skills/thermiteau/maverick/mav-bp-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/thermiteau/maverick/mav-bp-accessibility"><img src="https://agentmods.dev/badge/skills/thermiteau/maverick/mav-bp-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 | $0.00058 | $0.00854 |
| Opus 5 | $0.00029 | $0.00427 |
| Sonnet 5 | $0.00012 | $0.00171 |
| Haiku 4.5 | $0.00006 | $0.00085 |
Grade A, and why
mav-bp-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 11d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility Standards
Ensure user-facing interfaces are usable by everyone, including people who rely on assistive technology.
Maverick's Rules
- WCAG 2.2 AA is the baseline, not the ceiling — all user-facing interfaces must meet it.
- Scope: web and mobile UIs only. Does NOT apply to CLIs, REST/GraphQL APIs, backend services, batch jobs/workers/daemons, or internal build tools. If the project has no user-facing interface, skip this skill entirely.
- Semantic HTML first — native elements before ARIA. No ARIA is better than bad ARIA; never override native semantics; any custom ARIA widget must implement its full keyboard interaction pattern.
- Automated accessibility testing must run in CI (axe-core, Lighthouse CI, pa11y, eslint-plugin-jsx-a11y — whatever fits the stack). Automated tools catch only ~30% of issues; they are necessary but not sufficient.
- Manual verification is required for what automation misses: keyboard-only operation of the whole page (Tab/Shift+Tab/Enter/Space/Escape/arrows, no traps outside modals), screen reader announcement of labels, errors, and dynamic content, and focus management in modals and SPA route changes (trap in dialog, restore to trigger on close).
- Zoom and reflow: content usable at 200% zoom; no horizontal scrolling at 320px viewport width.
- Auto-playing media is prohibited — playback must be user-initiated.
- Focus indicators: never
outline: nonewithout a:focus-visiblereplacement; indicators need at least 3:1 contrast against the surrounding background. - Never use colour alone to convey state — pair it with text, an icon, or a pattern.
Project Implementation Lookup
Check for docs/maverick/skills/accessibility/SKILL.md. If present, read it and follow it — it wins on specifics (library, config, conventions). If missing, proceed with these standards and note the gap in your summary.
Detecting Accessibility Issues in Code Review
When reviewing code for user-facing interfaces, flag these patterns:
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.
- 11d ago First seen · 48 lines · 58 tokens per session scan A 0c372388182b
mav-bp-accessibility is a skill published in the GitHub repository thermiteau/maverick (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 58 tokens to every session and 854 once invoked, about $0.0003 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
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
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.
menu-transitions-rtl
Animate react-horizontal-scrolling-menu scrolling and build right-to-left menus: noPolyfill defaults to true since v8, so transitionDuration (default 500), a custom-easing-function transitionBehavior, and per-call ScrollOptions { duration, boundary } on scrollToItem/scrollNext/scrollPrev are silently ignored unless…