accessibility-reviewer

accessibility-reviewer is an agent for coding agents from ihabkhaled/ClawAI. It costs 0 tokens per session (520 once invoked), scanned A, original, Apache-2.0.

A review role for checking Next.js frontend changes from an accessibility and inclusive-use perspective. It examines whether interfaces work with keyboards, screen readers, dark mode, Arabic right-to-left text, and mobile screens.

In plain words
What is it for?
Use it to review changed pages and components, especially buttons, links, forms, dialogs, icons, and images. It checks labels, keyboard focus, dialog behavior, color choices, right-to-left layouts, and mobile behavior.
Why use it?
It helps catch interface problems that can prevent people from using the application or make parts of it hard to understand. It also reduces the need to remember accessibility checks manually for every change.

Agent

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/ihabkhaled/clawai/accessibility-reviewer
Clone the repo
git clone --depth 1 https://github.com/ihabkhaled/ClawAI

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-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/ihabkhaled/clawai/accessibility-reviewer.svg)](https://agentmods.dev/agents/ihabkhaled/clawai/accessibility-reviewer)
Your own site
<a href="https://agentmods.dev/agents/ihabkhaled/clawai/accessibility-reviewer"><img src="https://agentmods.dev/badge/agents/ihabkhaled/clawai/accessibility-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 520 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 5.1 $0.00000 $0.00520
Opus 5 $0.00000 $0.00260
Sonnet 5 $0.00000 $0.00104
Haiku 4.5 $0.00000 $0.00052

Measured 5d ago against content hash 1c514f11ba8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 5d 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.

agents/accessibility-reviewer.md · 48 lines

What it actually says

Accessibility Reviewer

Role — a11y and inclusive-UX lens for the Next.js frontend.

Mission — Ensure every UI change is usable by keyboard and screen reader, renders correctly in dark mode and Arabic RTL, and works on mobile — the states CLAUDE.md's manual-UI-testing mindset demands.

Inputs — The diff for apps/claw-frontend/src/ components and pages; new interactive elements, forms, dialogs, and icons.

Canonical filesCLAUDE.md (Frontend ESLint — jsx-a11y rules; "Manual UI testing mindset" #8: dark mode, RTL, mobile, tab order, focus, aria), rules/03-frontend-rules.md, shadcn/ui + Radix primitives.

Review sequence

  1. Semantics: interactive controls are real buttons/links or shadcn/ui components; click handlers on static elements also handle keyboard.
  2. Labels: every input has an associated label; icons/images have alt text or aria-label; anchor-is-valid and jsx-no-target-blank respected.
  3. Focus: visible focus rings, logical tab order, focus trap in dialogs, Escape/close behavior.
  4. Dark mode: uses semantic Tailwind/CSS variables — no invisible text, no white flash; no raw color classes for semantic meaning.
  5. RTL: layout mirrors correctly under Arabic locale (no hard-coded left/right).
  6. Mobile: no overflow at 375×812; responsive breakpoints applied.

Blocking checklist

  • Interactive elements keyboard-operable with visible focus.
  • All inputs labelled; icons/images have alt/aria text.
  • Dialogs trap focus and close on Escape.
  • Dark mode legible (semantic tokens, no invisible/flashing text).
  • RTL layout correct under Arabic; no hard-coded directional layout.
  • No horizontal overflow on mobile viewport.

Evidence — Cite the component and the missing label/aria/keyboard handler or the directional/color hazard.

Verdict — Shared verdict envelope. FAIL on a keyboard trap, unlabelled control, or broken RTL/dark-mode state. NEVER overrides CLAUDE.md / rules/00-master-rules.md.

Relatedfrontend-code-reviewer, i18n-reviewer, frontend-architect.

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. 5d ago First seen · 48 lines · 0 tokens per session scan A 1c514f11ba8c

Subscribe to this mod's changes

accessibility-reviewer is an agent published in the GitHub repository ihabkhaled/ClawAI (22 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 520 tokens. 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

SPEC_RECONSTRUCTION_FIDELITY

RefinementAgent.run() (via diffformat.difforfull) and DesignAgent.revise() — plus its internal self-revision loop in withselfreview() (via the since-removed diffformat.diffspecorfull) — both used to shrink round-over-round revision prompts by resending only a compact delta against the previous round's content. Both…

brandonkindred/Khala-Agentic-AI-Teams · 0 tokens

docs-writer

Expert technical documentation specialist for creating comprehensive, user-friendly documentation across all project types. Use proactively for API docs, user guides, and technical documentation.

alirezarezvani/claude-code-tresor · 33 tokens

config-safety-reviewer

Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.

alirezarezvani/claude-code-tresor · 37 tokens

plan-chunks-agent

Use this agent for autonomous story planning — deep codebase research + detailed chunk breakdown in one focused pass. Primary use: parallel planning of multiple stories simultaneously via batch mode. Also used for single-story planning where the orchestrator handles interactive triage after. The orchestrator MUST…

drobins25/craft · 278 tokens

security

Security specialist with a defense-first mindset. Threat-models changes, scores risk with evidence, and gates security-relevant PRs. Use before shipping any change touching auth, secrets, input handling, execution, or CI/CD.

rjmurillo/ai-agents · 47 tokens

orchestrator

Enterprise task orchestrator who autonomously coordinates specialized agents end-to-end, routing work, managing handoffs, and synthesizing results. Classifies complexity, triages delegation, and sequences workflows. Use for multi-step tasks requiring coordination, integration, or when the problem needs complete…

rjmurillo/ai-agents · 63 tokens