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 skills add AmadeusITGroup/otter --skill a11y-page-checksgit 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/skills/amadeusitgroup/otter/a11y-page-checks)<a href="https://agentmods.dev/skills/amadeusitgroup/otter/a11y-page-checks"><img src="https://agentmods.dev/badge/skills/amadeusitgroup/otter/a11y-page-checks/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/skills/amadeusitgroup/otter/a11y-page-checks"><img src="https://agentmods.dev/badge/skills/amadeusitgroup/otter/a11y-page-checks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00036 | $0.00468 |
| Opus 5 | $0.00018 | $0.00234 |
| Sonnet 5 | $0.00007 | $0.00094 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
a11y-page-checks 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 11d 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.
What it actually says
Skill: Page-Level Accessibility Checks
Compliance Target
WCAG 2.1 AA for existing pages. WCAG 2.2 AA for newly created pages.
<hard_rules>
- Page title: each route has a meaningful and unique
<title>. - Heading hierarchy: heading levels must not skip ranks (e.g.
<h1>→<h3>is invalid). Each page must have exactly one<h1>. - Focus on route/view change: focus moves to the page heading or first interactive element when navigating to a new view. </hard_rules>
Axe test coverage — verify a full-page axe test exists for this route (follow [[a11y-axe-playwright]] for conventions). If none exists, record as a finding. Record: covered or missing — no axe test found.
Page title
Confirm the <title> is meaningful and unique for this route. Record: verified or findings.
Heading hierarchy
Confirm no heading levels are skipped and exactly one <h1> exists on the page. Record: verified or findings.
Focus on view change
Confirm the page heading or first interactive element receives focus when the route loads. Record: verified or n/a — no route change.
Emit evidence block
Never omit a bullet — record n/a — <reason> when a check does not apply.
## Page-Level Accessibility Evidence
- Axe test: <covered | missing>
- Page title: <verified | findings>
- Heading hierarchy: <verified | findings>
- Focus on view change: <verified | n/a — no route change>
References
<reporting_rules> Run all checks to completion before reporting. After all checks:
- If any findings exist and are not explicitly waived → emit a complete findings list, do NOT emit a passing evidence block. </reporting_rules>
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.
- 11d ago First seen · 57 lines · 36 tokens per session scan A d7870e85ea0c
a11y-page-checks is a skill published in the GitHub repository AmadeusITGroup/otter (58 stars, last pushed today), licensed BSD-3-Clause. It adds 36 tokens to every session and 468 once invoked, about $0.0002 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 skills, from other repositories
config-evals
Builds and maintains configuration-based evaluations on a workflow with the eval-config tool. Use when the user asks to set up, add, view, change, or remove an evaluation, score, grade, or judge a workflow's output, or measure answer quality against a test dataset. This is the only eval form Instance AI handles — it…
output-dev-eval-testing
Create offline evaluation tests for Output SDK workflows using @outputai/evals. Use when implementing test evaluators with verify(), creating dataset YAML files, building eval workflows, or running workflow tests via CLI.
output-eval-validate-judge
Validate LLM judges against human labels using TPR/TNR metrics and train/dev/test splits. Use after writing a judge prompt to verify it agrees with human judgment.
creating-online-evaluations
Author continuously-running online evaluations in PostHog AI observability, grounded in real failure modes you've identified. Use when the user wants evaluations that automatically score new generations or whole traces going forward — "create an eval to catch X", "continuously check that responses do Y", "turn these…
build-swiftui-interface
Use when a coding agent must design, scaffold, implement, or verify an iOS or macOS SwiftUI interface with Apple-platform state, accessibility, availability, testing, and Xcode evidence.
operate-ai-stack
Develop, test, and troubleshoot this generated AI or ML workload across its framework, model and embedding providers, retrieval stores, interfaces, training, serving, and observability layers. Use when changing prompts, tools, agents, RAG, MCP, inference, fine-tuning, evaluations, or provider integration.