accessibility-lead

accessibility-lead is an agent for Claude Code from Community-Access/accessibility-agents. It costs 142 tokens per session (3,482 once invoked), scanned A, original, MIT.

A coordinator for checking the accessibility of user-facing web content and interfaces. Accessibility means ensuring people with disabilities can use websites and software, with WCAG AA as the target standard.

In plain words
What is it for?
Reviewing HTML, JSX, CSS, React components, web pages, server-rendered templates, and other user-facing web content for accessibility.
Why use it?
It helps catch accessibility issues across web code and coordinates specialist checks so important requirements are not overlooked.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/community-access/accessibility-agents/accessibility-lead
Clone the repo
git clone --depth 1 https://github.com/Community-Access/accessibility-agents

Made for: Claude Code.

Wrote 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.

agentmods badge for accessibility-lead

README.md
[![agentmods](https://agentmods.dev/badge/agents/community-access/accessibility-agents/accessibility-lead.svg)](https://agentmods.dev/agents/community-access/accessibility-agents/accessibility-lead)
Your own site
<a href="https://agentmods.dev/agents/community-access/accessibility-agents/accessibility-lead"><img src="https://agentmods.dev/badge/agents/community-access/accessibility-agents/accessibility-lead.svg" alt="Measured on agentmods" height="20"></a>
Per session 142 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,482 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00142 $0.03482
Opus 5 $0.00071 $0.01741
Sonnet 5 $0.00028 $0.00696
Haiku 4.5 $0.00014 $0.00348

Measured 4d ago against content hash 44ebb6782530, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 4d 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.

.claude/agents/accessibility-lead.md · 308 lines

How it starts

The opening of the file, as written. The whole thing — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Authoritative Sources

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.

Custom Skills: Need domain-specific accessibility rules not covered by standard agents? See Creating Custom Skills to build reusable knowledge modules that integrate with the agent ecosystem. Example use cases: industry-specific compliance (fintech, healthcare), framework-specific patterns (Svelte 5, Next.js 15), or regional standards (AODA, EAA).

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:

  1. Identify which specialists are needed for the current task
  2. Ensure the right agents are invoked
  3. Run the final review across all accessibility dimensions
  4. 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

Read the full file on GitHub · 308 lines

Changes

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.

  1. 4d ago First seen · 308 lines · 142 tokens per session scan A 44ebb6782530

Subscribe to this mod's changes

accessibility-lead is an agent published in the GitHub repository Community-Access/accessibility-agents (405 stars, last pushed 23d ago), licensed MIT. It adds 142 tokens to every session and 3,482 once invoked, about $0.0007 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.

Related

Other agents, from other repositories