agentmods.dev

a11y-auditor

a11y-auditor is an agent for Claude Code from berrzebb/quorum. It costs 59 tokens per session (501 once invoked), scanned A, original, MIT.

A source-code checker for web accessibility, including WCAG 2.1 AA rules, HTML structure, ARIA attributes, and keyboard-related code patterns. It checks files without opening the site in a browser.

In plain words
What is it for?
Use it to review buttons, links, forms, images, headings, labels, and other interface code for missing or incorrect accessibility markup.
Why use it?
It finds accessibility problems that can be identified from code before they reach users. It does not test visual contrast, real keyboard behavior, or screen-reader output.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the quorum plugin — 10 commands, 13 agents shipped together

not rated 10repo 4mo ago A scan 59 tokens original MIT

Good fit Use it to review buttons, links, forms, images, headings, labels, and other interface code for missing or incorrect accessibility markup.

Compare 6 agents from other repositories ↓
View source ↗ berrzebb/quorum
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add berrzebb/quorum
Claude Code
/plugin install quorum

Made for: Claude Code.

Or install quorum, the plugin that ships this one along with the rest of its 10 commands, 13 agents.

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 a11y-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/berrzebb/quorum/a11y-auditor.svg)](https://agentmods.dev/agents/berrzebb/quorum/a11y-auditor)
Your own site
<a href="https://agentmods.dev/agents/berrzebb/quorum/a11y-auditor"><img src="https://agentmods.dev/badge/agents/berrzebb/quorum/a11y-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 501 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00059 $0.00501
Opus 5 $0.00030 $0.00251
Sonnet 5 $0.00012 $0.00100
Haiku 4.5 $0.00006 $0.00050

Measured 8d ago against content hash efc4b61bed0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

a11y-auditor 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 8d 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.

platform/adapters/claude-code/agents/a11y-auditor.md · 49 lines

What it actually says

Accessibility Auditor (Claude Code)

Read and follow:

  • Base protocol: ${CLAUDE_PLUGIN_ROOT}/../../../agents/knowledge/specialist-base.md
  • Domain knowledge: ${CLAUDE_PLUGIN_ROOT}/../../../agents/knowledge/domains/a11y.md
  • Language patterns: languages/{lang}/spec.mjs → qualityRules.a11y

Scope Clarification

Your scope: Code patterns, aria attributes, semantic HTML, heading structure, label associations — all verifiable from source code alone.

NOT your scope: Visual rendering, actual color contrast ratios, runtime keyboard behavior, screen reader output — these require a real browser (ui-reviewer's job).

Claude Code Tool Invocation

node "${CLAUDE_PLUGIN_ROOT}/../../core/tools/tool-runner.mjs" code_map --path src/ --filter fn,class
node "${CLAUDE_PLUGIN_ROOT}/../../core/tools/tool-runner.mjs" audit_scan --pattern all
# Targeted search for missing aria attributes
Grep for: <(button|a|input|img)\s without nearby aria-label/alt

Extended Output

Include wcag field in each finding (e.g., "1.1.1", "2.1.1", "4.1.2").

Domain-Specific Anti-Patterns

  • Do NOT attempt runtime browser testing — that is ui-reviewer's job
  • Do NOT flag non-UI files (utilities, configs, tests)
  • Do NOT assume color contrast from code alone — flag for ui-reviewer if suspicious
  • Do NOT flag a11y issues in test files — only production components
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. 8d ago First seen · 49 lines · 59 tokens per session scan A efc4b61bed0b

Subscribe to this mod's changes

a11y-auditor is an agent published in the GitHub repository berrzebb/quorum (10 stars, last pushed 4mo ago), licensed MIT. It adds 59 tokens to every session and 501 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 2026-08-31.

Claude CodeFrontendai-agentsastauditblast-radiuscli
Related

Other agents, from other repositories

ui-ux-designer

Use this agent when you need UI/UX design guidance, Current Project UI Framework implementation advice, or visual design improvements for the desktop application interface. Examples: Context: User wants to improve the layout of a chat interface component. user: "I want to improve the chat interface layout to make it…

UfoMiao/zcf · 0 tokens

designer

UI/UX design and frontend implementation specialist.

jmylchreest/aide · 10 tokens

frontend

Frontend development expert for UI component review, state management analysis, accessibility assessment, and bundle optimization. Use when reviewing React, Vue, TypeScript, CSS, or any client-side code.

restarter/lets-workflow · 39 tokens

ui-design-agent

UI design token management and prototype generation — W3C Design Tokens Format, state-based components, WCAG AA validation, responsive layout templates.

catlog22/maestro-flow · 32 tokens

frontend-developer

Framework-agnostic front-end implementation (JS/TS, React, Vue, Angular, Svelte) with accessibility and performance optimization.

FortiumPartners/ensemble · 30 tokens

frontend-engineer

Ingénieur front-end Hookstack (Next.js 15 App Router, Tailwind v4, Motion). Utiliser pour créer/modifier des composants React, des pages, le catalogue, le HookConfigurator, des animations, ou toucher au design system. Connaît les pièges du repo (m. pas motion., tokens motion.ts, i18n via T, Zustand persisté) — les…

steve-magne/hookstack · 94 tokens