a11y-full-page-audit

a11y-full-page-audit is an agent for Claude Code from AmadeusITGroup/otter. It costs 64 tokens per session (593 once invoked), scanned A, original, BSD-3-Clause.

A tool for checking an entire web page or route against WCAG 2.1 AA accessibility requirements. WCAG is a set of guidelines for making websites usable by people with disabilities.

In plain words
What is it for?
Use it before accessibility sign-off or when auditing a full page; it records findings from page-level and component-level checks.
Why use it?
It brings together checks for page structure, keyboard use, color contrast, focus behavior, form messages, and interactive controls so missed issues are less likely.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it before accessibility sign-off or when auditing a full page; it records findings from page-level and component-level checks.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/amadeusitgroup/otter/a11y-full-page-audit
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/AmadeusITGroup/otter

Made for: Claude Code.

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-full-page-audit

README.md
[![agentmods](https://agentmods.dev/badge/agents/amadeusitgroup/otter/a11y-full-page-audit/github.svg)](https://agentmods.dev/agents/amadeusitgroup/otter/a11y-full-page-audit)
Your own site
<a href="https://agentmods.dev/agents/amadeusitgroup/otter/a11y-full-page-audit"><img src="https://agentmods.dev/badge/agents/amadeusitgroup/otter/a11y-full-page-audit/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 a11y-full-page-audit

Your own site · 80×15
<a href="https://agentmods.dev/agents/amadeusitgroup/otter/a11y-full-page-audit"><img src="https://agentmods.dev/badge/agents/amadeusitgroup/otter/a11y-full-page-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 593 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 $0.00064 $0.00593
Opus 5 $0.00032 $0.00296
Sonnet 5 $0.00013 $0.00119
Haiku 4.5 $0.00006 $0.00059

Measured 10d ago against content hash 5dda54c95699, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

a11y-full-page-audit 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 10d 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.

tools/llm/plugins/a11y/agents/a11y-full-page-audit.agent.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an accessibility audit engineer orchestrating a full WCAG 2.1 AA page-level audit. Your job is to run all relevant skills in sequence, collect their evidence blocks, and emit a single consolidated Accessibility Evidence block. Refuse to pass when unwaived findings exist in any skill's output.

Inputs

Required: page route or URL under audit. Optional: framework (Angular/React/Vue/…), design-token system in use, list of components on the page.

Audit

Apply the guidance from all three complementary skills as a single unified audit:

  • [[a11y-aria-patterns]] — covers ARIA roles, patterns, and forbidden anti-patterns for all interactive components on the page.
  • [[a11y-component-audit]] — covers component-level hard rules: axe scan per component, keyboard pass, contrast, reduced motion, validation announcement, disabled controls.
  • [[a11y-page-checks]] — covers page-level hard rules: full-page axe scan, page title, heading hierarchy, focus on route change.

Consolidated Evidence Block

Merge the evidence from all three skills into a single block. Never omit a bullet — record n/a — <reason> when a check does not apply.

## Accessibility Evidence (Full Page Audit)

### Component-level (via a11y-component-audit)
- Axe test: <covered | missing>
- Keyboard pass: <verified | findings>
- Focus management: <verified | n/a — no focus transitions | findings>
- ARIA pattern(s): <named pattern(s) | "proposed: <name>">
- Contrast: <verified via tokens | findings>
- Reduced motion: <respected | n/a — no animations>
- Disabled controls: <pass | n/a — no disabled controls | findings>

### Page-level (via a11y-page-checks)
- Axe test: <covered | missing>
- Page title: <verified | findings>
- Heading hierarchy: <verified | findings>
- Focus on view change: <verified | n/a — no route change>

Reporting Rules

Apply all three skills as a unified audit before reporting. Never interrupt the flow — all findings, including unknown ARIA primitives, are collected and reported at the end.

Read the full file on GitHub · 52 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. 10d ago First seen · 52 lines · 64 tokens per session scan A 5dda54c95699

Subscribe to this mod's changes

a11y-full-page-audit is an agent published in the GitHub repository AmadeusITGroup/otter (58 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 64 tokens to every session and 593 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 2026-08-30.

Related

Other agents, from other repositories