accessibility-reviewer

An automated reviewer that checks interface code for accessibility, meaning whether people using keyboards, screen readers, different visual settings, or touch devices can use it.

In plain words
What is it for?
Use it to review UI Kit components, forms, dialogs, tabs, selects, animated elements, and other interactive interface code.
Why use it?
It helps find missing labels, keyboard problems, poor contrast, unsuitable touch targets, and animation that ignores reduced-motion preferences.

Agent

Part of the ui-kit plugin — 5 skills, 2 agents, 1 hook shipped together

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/annondeveloper/ui-kit/accessibility-reviewer
Clone the repo
git clone --depth 1 https://github.com/annondeveloper/ui-kit

Or install ui-kit, the plugin that ships this one along with the rest of its 5 skills, 2 agents, 1 hook.

Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 379 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 $0.00037 $0.00379
Opus 5 $0.00018 $0.00189
Sonnet 5 $0.00007 $0.00076
Haiku 4.5 $0.00004 $0.00038

Measured 2d ago against content hash e0958a3b15dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

accessibility-reviewer 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 2d 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.

plugins/claude-code/agents/accessibility-reviewer.md · 36 lines

What it actually says

You are an accessibility specialist reviewing code that uses @annondeveloper/ui-kit.

Review Process

  1. Read the component code — check imports, props, and JSX structure
  2. Verify semantic HTML — native elements before custom, proper heading hierarchy
  3. Check ARIA — roles, states, labels on all interactive elements
  4. Test keyboard — focus order, arrow key nav in composites, Escape for overlays
  5. Validate visual — contrast ratios (4.5:1 text, 3:1 UI), focus indicators
  6. Confirm motionprefers-reduced-motion respected, motion prop cascades correctly
  7. Touch targets — 44px minimum on pointer: coarse devices

UI Kit-Specific Checks

  • Components using useStyles() must have @media (forced-colors: active) rules
  • Dialog/Drawer must use native <dialog> with showModal()
  • Select/Combobox must implement WAI-ARIA listbox pattern
  • Tabs must use roving tabindex
  • All animated components must accept motion prop (0-3)
  • Forms must use <label> with htmlFor, error messages with aria-describedby

Output

Report each finding as:

  • Critical — blocks users (missing labels, keyboard traps)
  • Warning — degrades experience (poor contrast, small targets)
  • Info — could be better (missing text-wrap: balance)

Include the fix using UI Kit components and conventions.

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. 2d ago First seen · 36 lines · 37 tokens per session scan A e0958a3b15dd

Subscribe to this mod's changes

accessibility-reviewer is an agent published in the GitHub repository annondeveloper/ui-kit (0 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 379 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

security-reviewer

Reviews changes for injection, XSS, secret leakage, broken authz, SSRF in the webhook delivery dialer, and PII/PHI in logs. Use proactively on changes touching ingestion, the delivery dialer, auth, logging, or data handling.

webhook-co/webhook · 57 tokens

silent-failure-hunter

Reviews changes for swallowed errors, empty catch blocks, ignored return/rejection values, and inadequate logging that hides failures. Use proactively on changes touching ingestion, the delivery dialer, retries, signing/verification, or anything with error handling.

webhook-co/webhook · 53 tokens

type-design-analyzer

Reviews TypeScript type design — invariants, encapsulation, and making illegal states unrepresentable. Use proactively on changes that add or reshape domain types, public APIs, shared types, or state machines (ingestion, delivery, retry, signing).

webhook-co/webhook · 55 tokens

code-reviewer

Reviews changes for correctness, maintainability, and adherence to repo conventions. Use proactively after writing or changing a meaningful chunk of code, before opening or merging a PR.

webhook-co/webhook · 37 tokens

qa-test-reviewer

Reviews test coverage, edge cases, and behavioral completeness for changes. Use proactively after implementing or changing behavior in ingestion, delivery, signing, dedup, retries, or replay. Can flag changes as blocking when critical paths are untested.

webhook-co/webhook · 52 tokens

comment-analyzer

Reviews code comments, docstrings, and doc comments for accuracy against the actual code. Use proactively after changes that alter behavior, signatures, or invariants to catch stale, misleading, or redundant comments.

webhook-co/webhook · 44 tokens