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.
git clone --depth 1 https://github.com/AmadeusITGroup/otterWrote 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/amadeusitgroup/otter/a11y-full-page-audit)<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.
<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>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 | $0.00064 | $0.00593 |
| Opus 5 | $0.00032 | $0.00296 |
| Sonnet 5 | $0.00013 | $0.00119 |
| Haiku 4.5 | $0.00006 | $0.00059 |
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.
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.
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.
- 10d ago First seen · 52 lines · 64 tokens per session scan A 5dda54c95699
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.
Other agents, from other repositories
bug-fixing-implementer-agent
Implements the minimum fix (GREEN phase) for bugs in igniteui-angular. Preserves the public API, accessibility, and localization. Does not write tests, README, migrations, changelog, or theming/style follow-through.
theming-styles-agent
Implements component theming and style changes for igniteui-angular, including in-repo SCSS, theme wiring, and style validation.
demo-sample-agent
Updates existing demo/sample areas in src/app/ for explicit user-visible Ignite UI for Angular feature or bug-fix changes.
frontend-specialist
Senior Frontend Architect. Expert in React/Next.js, UI/UX Psychology, Accessibility, and Tailwind v4. Specializes in high-performance, bespoke interfaces.
angular-implementor
Implements Angular / TypeScript fixes and features in compliance with all materialized angular rules and pilot-angular skills. Takes an angular-reviewer finding (rule/skill ID + file:line) or a feature request, applies minimal targeted edits, verifies with tsc/ng build, and hands back a summary formatted for re-review…
pn-frontend-developer
Specialist: UI components, layout, a11y, and visual design for React, Astro, Next.js, or vanilla HTML/CSS/JS. Invoke directly for focused frontend work or let pn-build route to it.