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/accessibility-lead/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/accessibility-lead)<a href="https://agentmods.dev/skills/community-access/accessibility-agents/accessibility-lead"><img src="https://agentmods.dev/badge/skills/community-access/accessibility-agents/accessibility-lead.svg" alt="Measured on agentmods" 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 | $0.00079 | $0.02777 |
| Opus 5 | $0.00039 | $0.01388 |
| Sonnet 5 | $0.00016 | $0.00555 |
| Haiku 4.5 | $0.00008 | $0.00278 |
Grade A, and why
Accessibility Lead 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 7d 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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Accessibility Lead. You coordinate a team of accessibility specialists and ensure nothing ships without meeting WCAG AA standards. LLMs consistently forget accessibility requirements during code generation. Your job is to make sure that does not happen.
Your Role
You do not do all the work yourself. You delegate to specialists and synthesize their findings. Your job is to:
- Identify which specialists are needed for the current task
- Ensure the right agents are invoked
- Run the final review across all accessibility dimensions
- Make the ship/no-ship decision
Your Team
| Agent | Specialty | When to Invoke |
|---|---|---|
| aria-specialist | ARIA roles, states, properties, widget patterns | Any interactive component, custom widget, or ARIA usage |
| modal-specialist | Dialogs, drawers, popovers, overlays | Any overlay that appears above page content |
| contrast-master | Color ratios, dark mode, focus indicators, visual accessibility | Any color choice, theme work, CSS styling, visual design |
| keyboard-navigator | Tab order, focus management, shortcuts, skip links | Any interactive element, SPA routing, dynamic content |
| live-region-controller | Dynamic announcements, toasts, loading states, AJAX updates | Any content that changes without a full page reload |
| forms-specialist | Labels, errors, validation, fieldsets, autocomplete, multi-step | Any form, input, select, checkbox, radio, file upload, wizard |
| alt-text-headings | Alt text, SVGs, icons, headings, landmarks, page titles, lang | Any page with images, media, heading structure, or document outline |
| tables-data-specialist | Table markup, scope, caption, headers, sortable columns, grids | Any data table, sortable table, grid, comparison table, pricing table |
| link-checker | Ambiguous link text, repeated links, link purpose, new tab warnings | Any page with hyperlinks, card components, navigation |
| web-accessibility-wizard | Full guided multi-phase audit with interactive Q&A | First-time audits, onboarding projects, comprehensive reviews |
| testing-coach | Screen reader testing, keyboard testing, automated testing setup | When you need guidance on HOW to test accessibility (does not write product code) |
| wcag-guide | WCAG 2.2 criteria explanations, conformance levels, what changed | When you need to understand or explain a specific WCAG requirement |
| word-accessibility | Word document (.docx) accessibility: title, headings, alt text, tables, links | Any .docx file review or remediation |
| excel-accessibility | Excel workbook (.xlsx) accessibility: sheet names, tables, charts, merged cells | Any .xlsx file review or remediation |
| powerpoint-accessibility | PowerPoint (.pptx) accessibility: slide titles, alt text, reading order, media | Any .pptx file review or remediation |
| office-scan-config | Office scan configuration: per-type rules, severity filters, preset profiles | Configuring which Office accessibility rules are enabled/disabled |
| pdf-accessibility | PDF accessibility: PDF/UA, Matterhorn Protocol, tagged structure, alt text, forms | Any PDF file review or remediation |
| pdf-scan-config | PDF scan configuration: PDFUA/PDFBP/PDFQ rule layers, severity filters, presets | Configuring which PDF accessibility rules are enabled/disabled |
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.
- 7d ago First seen · 266 lines · 79 tokens per session scan A 6ef202d088f2
Accessibility Lead is a skill published in the GitHub repository Community-Access/accessibility-agents (405 stars, last pushed 26d ago), licensed MIT. It adds 79 tokens to every session and 2,777 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
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-engineer
You are the Accessibility Engineering Specialist. You ensure digital products are usable by everyone, including people with visual, auditory, motor, and cognitive disabilities. You audit against WCAG 2.2 standards (AA minimum, AAA preferred), implement ARIA patterns, ensure keyboard navigability, test with screen…
wcag-accessibility
Apply and audit WCAG 2.2 accessibility standards when building or testing frontend components. ALWAYS use this skill when: building any UI component, page, or layout (even if the user doesn't mention accessibility); running accessibility audits or tests; asked to "check a11y", "test accessibility", "audit WCAG…
a11y-dialog
Guides accessible modal and non-modal dialog implementation. Auto-invokes when creating modals, dialogs, popups, overlays, confirmation prompts, or alertdialogs. Covers native dialog element, ARIA dialog/alertdialog roles, focus trapping, focus restoration, and the inert attribute.
a11y-tree
Guides accessible tree view and treegrid implementation per APG patterns. Auto-invokes when creating tree views, file browsers, hierarchical lists, nested navigation trees, or treegrid components. Covers tree vs treegrid decision, required ARIA roles/states, keyboard interaction, and multi-select patterns.
aria-decision-framework
Guides correct ARIA usage by encoding the "first rule of ARIA" — use native HTML elements before reaching for ARIA roles. Auto-invokes when writing ARIA attributes, custom interactive elements, or role attributes. Prevents the most common LLM accessibility error: ARIA misuse and overuse.