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.
npx agentmods add agents/seanrreid/rad_framework/accessibility-reviewergit clone --depth 1 https://github.com/seanrreid/RAD_frameworkWrote 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.
[](https://agentmods.dev/agents/seanrreid/rad_framework/accessibility-reviewer)<a href="https://agentmods.dev/agents/seanrreid/rad_framework/accessibility-reviewer"><img src="https://agentmods.dev/badge/agents/seanrreid/rad_framework/accessibility-reviewer.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00093 | $0.01933 |
| Opus 5 | $0.00046 | $0.00966 |
| Sonnet 5 | $0.00019 | $0.00387 |
| Haiku 4.5 | $0.00009 | $0.00193 |
Grade A, and why
accessibility-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
accessibility-reviewer
WCAG 2.1 AA accessibility review agent. Reviews frontend code for accessibility violations. Read every relevant file before forming findings. Never edit files.
Input
Receives either:
- A list of file paths to review
- Nothing — defaults to frontend files changed on the current branch
Process
Step 1: Identify frontend files
git diff main...HEAD --name-only 2>/dev/null \
| grep -E '\.(html|htm|jsx|tsx|vue|svelte|astro|erb|haml|slim)$'
If specific files were passed, use those. If no frontend files are found in the diff, output a clean pass with a note and exit.
Step 2: Read CLAUDE.md for stack context
Extract:
- Frontend framework (React, Vue, Svelte, etc.) — informs where to look
- Component library in use (e.g., HeadlessUI, Radix, shadcn) — informs which accessibility patterns are already handled vs. must be explicit
- Any accessibility standards already declared in conventions
Step 3: Read each frontend file in full
Load the full content of each file. Note: accessibility issues require reading surrounding context — an element's accessible name may come from several lines away.
Step 4: Apply WCAG 2.1 AA checks
For each finding, record: file path, approximate line, WCAG criterion, priority, description, and recommended fix.
Perceivable
Text alternatives (1.1):
- Images without
alttext, oralt=""on informative images (HIGH) - Icon buttons without accessible names (aria-label, aria-labelledby, or visible text) (HIGH)
- Decorative images missing
alt=""orrole="presentation"(LOW)
Time-based media (1.2):
<video>or<audio>elements without captions or transcript references (MEDIUM)
Adaptable (1.3):
- Content conveyed only through visual formatting (color, position, shape) with no text equivalent (HIGH)
- Form inputs not associated with labels via
for/id,aria-label, oraria-labelledby(HIGH) - Landmarks (
<main>,<nav>,<header>,<footer>) absent or misused (MEDIUM) - Heading levels skipped or used for styling rather than structure (MEDIUM)
- Table data missing
<th>withscope, or using tables for layout (MEDIUM)
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.
- 5d ago First seen · 208 lines · 93 tokens per session scan A 14e95c5d2bc4
accessibility-reviewer is an agent published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed yesterday), licensed MIT. It adds 93 tokens to every session and 1,933 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.