reviewer-accessibility

reviewer-accessibility is an agent for Claude Code from Jamie-BitFlight/claude_skills. It costs 106 tokens per session (1,827 once invoked), scanned A, original, MIT.

An accessibility review agent checks user-interface and command-line changes for missing accessibility labels, keyboard navigation problems, color-only signals, and similar barriers.

In plain words
What is it for?
Use it during review of UI or CLI changes to check labels, state indicators, keyboard access, and accessible output.
Why use it?
It helps ensure people using keyboards, assistive technology, or text-based interfaces can understand and operate the changed software.

Agent for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: model in frontmatter; mentions subagents.

Part of the dh plugin — 53 skills, 28 agents shipped together

Good fit Use it during review of UI or CLI changes to check labels, state indicators, keyboard access, and accessible output.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jamie-bitflight/claude_skills/reviewer-accessibility
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.

Clone the repo
git clone --depth 1 https://github.com/Jamie-BitFlight/claude_skills

Made for: Claude Code.

Or install dh, the plugin that ships this one along with the rest of its 53 skills, 28 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 reviewer-accessibility

README.md
[![agentmods](https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/reviewer-accessibility/github.svg)](https://agentmods.dev/agents/jamie-bitflight/claude_skills/reviewer-accessibility)
Your own site
<a href="https://agentmods.dev/agents/jamie-bitflight/claude_skills/reviewer-accessibility"><img src="https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/reviewer-accessibility/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.

agentmods 80×15 button for reviewer-accessibility

Your own site · 80×15
<a href="https://agentmods.dev/agents/jamie-bitflight/claude_skills/reviewer-accessibility"><img src="https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/reviewer-accessibility.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 106 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,827 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 $0.00106 $0.01827
Opus 5 $0.00053 $0.00914
Sonnet 5 $0.00021 $0.00365
Haiku 4.5 $0.00011 $0.00183

Measured 4d ago against content hash e4ab0fa5f63c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

reviewer-accessibility 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.

plugins/development-harness/agents/reviewer-accessibility.md · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Accessibility Reviewer Agent

You are the accessibility-perspective reviewer in a multi-perspective review. Your job is to examine changed files for accessibility deficiencies: missing ARIA attributes, color-only state indicators, keyboard navigation gaps, and CLI ANSI-color-only output differentiation. You write a structured verdict block into the task's Review Results section.

You are never the implementer. You do not fix issues — you identify them and verdict the change.

Role

You do:

  • Check whether any changed file matches the UI file pattern list (§2.3 of verdict-schema.md)
  • If no UI files present: emit SKIP verdict immediately and stop
  • If UI files present: apply accessibility SOP (Steps 3–6 below)
  • Write the structured verdict into the task's Review Results section — that section is the only channel a consumer reads the accessibility verdict from

You do NOT:

  • Implement accessibility fixes
  • Review files outside the changed-files list provided by the orchestrator
  • Embed or duplicate the UI file pattern list in your output

SOP

Step 1: Read Verdict Schema

Activate /dh:review-verdict-contract to load the SKIP detection rule and output schema.

Extract from §2.3:

  • The authoritative UI file pattern list
  • The pattern matching rule (Unix glob, case-insensitive, applied to relative file paths)

Extract from §2.1:

  • The structured verdict block schema (schema_version, perspective, verdict, findings, skip_reason)

Step 2: SKIP Detection (execute before any other file access)

Take the changed_files list passed in your task context (newline-separated list in the task body).

Check each file path against every pattern in the §2.3 UI file pattern list using standard Unix glob semantics, case-insensitive.

If NO changed file matches any UI pattern:

Emit the SKIP verdict immediately. Do NOT read any source files. Do NOT run any Grep or Bash commands. Proceed directly to Step 7.

{
  "schema_version": "1.0",
  "perspective": "accessibility",
  "verdict": "SKIP",
  "findings": [],
  "skip_reason": "no UI changes"
}

Read the full file on GitHub · 211 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 Changed e4ab0fa5f63c
  2. 6d ago First seen · 211 lines · 106 tokens per session scan A 396ff6eabefc

Subscribe to this mod's changes

reviewer-accessibility is an agent published in the GitHub repository Jamie-BitFlight/claude_skills (66 stars, last pushed today), licensed MIT. It adds 106 tokens to every session and 1,827 once invoked, about $0.0005 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.

Related

Other agents, from other repositories

liquid-glass-auditor

Use this agent when the user mentions Liquid Glass review, iOS 26 UI updates, toolbar improvements, or visual effect migration. Automatically scans SwiftUI codebase for Liquid Glass adoption opportunities - identifies views for glass effects, toolbar improvements, migration from old blur effects, and tinting…

CharlesWiltgen/Axiom · 163 tokens

review-ui-blazor

UI/Blazor reviewer for Razor components. Checks accessibility, culture-dependent rendering, CSS correctness, component lifecycle, and Blazor-specific pitfalls. Returns PASS or FAIL with specific findings. Only runs when .razor files are changed.

dodobrands/ai-hub · 53 tokens

cosmo

Cosmo - CSS Consistency Reviewer for web application styling.

sam-agents/sam · 11 tokens

ui-interaction-reviewer

Interactive-component review — buttons, modals, drawers, forms, focus states, loading patterns, UX writing, empty states. Checks the invisible details that compound into "feels right": :active states, spatial-consistency entry/exit, modal vs popover transform-origin, inline form errors, focus-visible, optimistic UI…

RaNDoM6913/claude-code-superkit · 208 tokens

ui-motion-reviewer

Motion-specific review — runs the 4-question Animation Decision Framework (should it animate? purpose? easing? duration?), catches ease-in on UI, transition:all, scale(0) entry, bounce/elastic defaults, animations on keyboard-triggered actions, prefers-reduced-motion gaps, and poorly-chosen spring vs duration…

RaNDoM6913/claude-code-superkit · 189 tokens

ui-typography-reviewer

Typography-specific deep review — font selection, modular scale, line-height, line-length, pairing, tracking, OpenType features, web-font loading. Dispatch when a font-family, font-weight, or type-scale token changed; when a Google Fonts or font-loading import was added or changed; when the user asks about fonts…

RaNDoM6913/claude-code-superkit · 129 tokens