An accessibility checker for changed Compass user-interface code. It examines semantics, labels, keyboard and focus behavior, ARIA, contrast, motion, and related tests.

Use it when reviewing UI diffs, checking keyboard or screen-reader behavior, or investigating unreliable interaction tests.

It helps catch accessibility regressions introduced by a UI change without reviewing the entire site. It also connects findings to the changed code and suggests small fixes.

How KeepSoftwareSimple/compass-calendar configures Claude Code and Cod

Reuse

Borrowing it

Nothing to install: this file belongs to KeepSoftwareSimple/compass-calendar. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/KeepSoftwareSimple/compass-calendar/main/.agents/skills/a11y-audit/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/KeepSoftwareSimple/compass-calendar

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/keepsoftwaresimple/compass-calendar/a11y-audit/github.svg)](https://agentmods.dev/skills/keepsoftwaresimple/compass-calendar/a11y-audit)

Your own site

<a href="https://agentmods.dev/skills/keepsoftwaresimple/compass-calendar/a11y-audit"><img src="https://agentmods.dev/badge/skills/keepsoftwaresimple/compass-calendar/a11y-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/keepsoftwaresimple/compass-calendar/a11y-audit"><img src="https://agentmods.dev/badge/skills/keepsoftwaresimple/compass-calendar/a11y-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 759 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.

Model	Per session	Once invoked
Fable 5.1	$0.00058	$0.00759
Opus 5.5	$0.00023	$0.00304
Sonnet 5.5	$0.00012	$0.00152
Haiku 4.5	$0.00006	$0.00076

Measured yesterday against content hash d6e7da0e6e88, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

a11y-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 yesterday.

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/skills/a11y-audit/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When

UI diff review, accessibility audit, or flaky interaction tests.

Steps

Workflow, then Checklist, scoped to the diff.

Output

Minimal diff-scoped findings and proposed fixes.

Pass

Changed UI reviewed; no site-wide unrelated audit.

Anti-patterns

Do not expand into an unrelated site-wide audit. See anti-patterns.md.

Escalate

A WCAG judgment that needs a human, or a contrast issue that needs design.

Accessibility change audit

Audit the changed UI and its immediate context. Do not turn a diff review into an unrelated site-wide audit.

Workflow

Identify changed elements, interactions, states, and styles.
Exercise affected behavior with the browser tooling available to the current agent when static inspection cannot establish focus, keyboard, contrast, or motion behavior.
Run the checklist below.
Tie each finding to a changed line or behavior and propose the smallest durable fix.
Recommend role/name queries and user-driven tests.

Checklist

Semantics and names

Heading order and landmarks remain meaningful.
Interactive elements use native buttons, links, inputs, lists, and tables.
Inputs, icon controls, dialogs, and regions have accessible names.
Helper/error text is connected with aria-describedby when appropriate.

Keyboard and focus

Every interaction is keyboard reachable and operable.
Focus order follows DOM order; avoid positive tabIndex.
Dialogs, menus, and popovers place, contain, and return focus correctly.
Composite widgets implement the expected arrow, Home/End, Enter, Space, and Escape behavior.

ARIA and state

Use ARIA only where native semantics are insufficient.
aria-expanded, aria-selected, aria-pressed, aria-controls, and aria-activedescendant reflect actual state and relationships.
Hidden/disabled content is not accidentally focusable.
Live updates and errors are announced when users need them.

Visual behavior

Read the full file on GitHub · 109 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.

yesterday First seen · 109 lines · 58 tokens per session scan A d6e7da0e6e88

Subscribe to this mod's changes

a11y-audit is a skill published in the GitHub repository KeepSoftwareSimple/compass-calendar (226 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 759 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-07.

Design and UX E2E testing React Testing TypeScript calendar google google-calendar nodejs

a11y-audit next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
a11y-auditKeepSoftwareSimple/compass-calendar	Skill	226	today	MIT	A	58	Claude Code, Codex
merge-seedkriasoft/react-starter-kit	Skill	24k	6d ago	MIT	A	49	Claude Code, Codex
magic-uimagicuidesign/magicui	Skill	23k	3d ago	MIT	A	56	Claude Code, Codex
building-canvasesPostHog/posthog	Skill	41k	today	none	A	148	Claude Code, Codex
test-electron-appPostHog/posthog	Skill	41k	today	none	A	112	Claude Code
composing-grid-canvasesPostHog/posthog	Skill	41k	today	none	A	136	Claude Code, Codex
formatting-slack-messagesPostHog/posthog	Skill	41k	today	none	A	66	Claude Code, Codex

compass-calendar: Skill for Claude Code