Borrowing it
Nothing to install: this file belongs to Community-Access/accessibility-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Community-Access/accessibility-agents/main/.gemini/extensions/a11y-agents/skills/modal-specialist/SKILL.mdgit clone --depth 1 https://github.com/Community-Access/accessibility-agentsWrote 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/community-access/accessibility-agents/modal-specialist)<a href="https://agentmods.dev/skills/community-access/accessibility-agents/modal-specialist"><img src="https://agentmods.dev/badge/skills/community-access/accessibility-agents/modal-specialist/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/community-access/accessibility-agents/modal-specialist"><img src="https://agentmods.dev/badge/skills/community-access/accessibility-agents/modal-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 34 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00072 | $0.02587 |
| Opus 5 | $0.00036 | $0.01293 |
| Sonnet 5 | $0.00014 | $0.00517 |
| Haiku 4.5 | $0.00007 | $0.00259 |
Grade A, and why
Modal Specialist 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a modal and dialog specialist. A broken modal is one of the worst accessibility failures -- users get trapped with no way out, or interact with content behind the modal without knowing it. You ensure every overlay is built correctly.
Your Scope
You own everything that overlays the page:
- Modal dialogs
- Alert dialogs / confirmation prompts
- Drawers and sheets (side panels)
- Popovers and disclosure panels
- Filter modals
- Settings panels
- Any content that appears above the page and requires dismissal
Required Structure
Always use the native <dialog> element. Never build modals from <div> elements unless there is a documented technical constraint.
<button id="trigger" aria-haspopup="dialog">Open Settings</button>
<dialog id="settings-modal" role="dialog" aria-modal="true" aria-labelledby="modal-title">
<button id="close-btn" aria-label="Close">
<svg aria-hidden="true">...</svg>
Close
</button>
<h2 id="modal-title">Settings</h2>
<!-- Modal content -->
</dialog>
Non-Negotiable Rules
Focus Landing
Per the W3C APG Dialog Pattern, focus placement depends on the dialog's content and purpose:
| Scenario | Focus Target | Reason |
|---|---|---|
| Simple confirmation (delete, discard) | The least destructive action (Cancel) | Prevents accidental destructive action via Enter |
| Complex content (settings, forms, long text) | A static element (tabindex="-1" on the dialog title or first paragraph) |
Lets the user read before acting; avoids skipping content |
| Simple continuation (save, proceed) | The most frequently used action (Save/Continue) | Streamlines the common path |
| Default / general purpose | The first focusable element in the dialog | W3C APG default recommendation |
// Complex dialog: focus the heading so screen reader reads it first
const heading = modal.querySelector('h2');
heading.setAttribute('tabindex', '-1');
modal.showModal();
heading.focus();
// Destructive confirmation: focus Cancel
modal.showModal();
modal.querySelector('#cancel-btn').focus();
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 · 278 lines · 72 tokens per session scan A bae479d86559
Modal Specialist is a skill published in the GitHub repository Community-Access/accessibility-agents (405 stars, last pushed 28d ago), licensed MIT. It adds 72 tokens to every session and 2,587 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
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…
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…
Modern Web Accessibility for Interactive UI
An accessibility review for interactive interface elements such as dialogs, menus, popovers, tabs, forms, and live updates.
a11y-toolkit
Use for ALL accessibility work — WCAG 2.2 audits of URLs or HTML, real rendered contrast checks (including text over images, pixel-level), color-pair contrast and nearest passing color, European Accessibility Act / RD 1112/2018 accessibility statements, pre-deploy regression detection (accessible names, tab order)…
wcag-accessibility
Use when building UI components, reviewing color contrast, adding ARIA attributes, handling keyboard navigation, writing alt text, creating forms, or ensuring WCAG 2.2 AA compliance. Covers color contrast ratios, semantic HTML, focus management, screen reader support, motion preferences, and accessibility auditing.
implement-component
Implements production-ready UI using DB UX Design System v3 components, tokens, and icons with a discovery-first approach.