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 skills/community-access/accessibility-agents/playwright-scannernpx skills add Community-Access/accessibility-agents --skill playwright-scannergit clone --depth 1 https://github.com/Community-Access/accessibility-agentsWrote 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/community-access/accessibility-agents/playwright-scanner)<a href="https://agentmods.dev/skills/community-access/accessibility-agents/playwright-scanner"><img src="https://agentmods.dev/badge/skills/community-access/accessibility-agents/playwright-scanner.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 | $0.00046 | $0.00405 |
| Opus 5 | $0.00023 | $0.00202 |
| Sonnet 5 | $0.00009 | $0.00081 |
| Haiku 4.5 | $0.00005 | $0.00040 |
Grade A, and why
playwright-scanner 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 2d 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
Playwright Scanner
You are a behavioral accessibility scanner agent. You are a read-only agent -- you never edit source files, configuration, or documentation. You are invoked internally by web-accessibility-wizard to run live browser-based accessibility tests.
Knowledge domains: Playwright Testing, Web Severity Scoring
Capabilities
1. Full Behavioral Scan
When invoked with a URL and scan profile, execute the following tests in order:
- Keyboard Flow Mapping -- Record the complete Tab sequence, detect keyboard traps, and identify unreachable interactive elements.
- Dynamic State Scanning -- Click triggers (accordions, menus, modals, tabs) and run axe-core against each revealed state.
- Responsive Viewport Scanning -- Test at widths [320, 768, 1024, 1440] to detect reflow failures, horizontal scroll, and undersized touch targets.
- Rendered Contrast Verification -- Extract computed foreground/background colors and calculate contrast ratios after full CSS cascade resolution.
- Accessibility Tree Snapshot -- Capture the browser's accessibility tree for landmark/heading/role/name verification.
Authoritative Sources
- WCAG 2.2 Specification — https://www.w3.org/TR/WCAG22/
- axe-core Rules — https://github.com/dequelabs/axe-core/tree/develop/lib/rules
- Playwright Accessibility — https://playwright.dev/docs/accessibility-testing
- @axe-core/playwright — https://github.com/dequelabs/axe-core-npm/tree/develop/packages/playwright
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.
- 2d ago First seen · 34 lines · 46 tokens per session scan A 1077d93a696e
playwright-scanner is a skill published in the GitHub repository Community-Access/accessibility-agents (405 stars, last pushed 24d ago), licensed MIT. It adds 46 tokens to every session and 405 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 2026-09-03.
Other skills, from other repositories
Accessibility Auditor
Comprehensive WCAG 2.1 AA compliance testing combining automated axe-core scans with manual keyboard navigation, screen reader compatibility, and focus management verification.
accessibility
Accessibility patterns for WCAG 2.2 compliance, keyboard focus management, React Aria component patterns, cognitive inclusion, native HTML-first philosophy, and user preference honoring. Use when implementing screen reader support, keyboard navigation, ARIA patterns, focus traps, accessible component libraries…
accessibility
Use when making a web UI conform to WCAG 2.2 Level AA — axe-core or Lighthouse a11y violations, keyboard operability, focus management, ARIA roles/names/live regions, contrast, tap-target size. NOT palette or visual intent (that is design), NOT test-runner setup (that is testing-web), NOT LCP/page-speed (that is…
zero-visual-delta-handoff
Disziplin für visuell unsichtbare Refactorings und Komponenten-Migrationen – null geänderte Snapshot-Bilder gegen den Base-Branch als hartes Akzeptanzkriterium, mit lokaler deterministischer Prüfpipeline, Pixel-/DOM-Analyse und Companion-Plan als Handoff über Sessions. Trigger: "zero visual delta", "visuell…
a11y-audit
Runs automated accessibility scans with axe-core, pa11y, Lighthouse, or eslint-plugin-jsx-a11y. Interprets results, prioritizes violations, and generates fix recommendations. Use when asked to audit, scan, or check accessibility of a page, component, or codebase.
css-a11y
Guides CSS patterns that affect accessibility — focus indicators, forced-colors mode, prefers-reduced-motion, prefers-contrast, color-only information avoidance, and target sizing. Auto-invokes when writing CSS for interactive elements, animations, transitions, media queries, or custom focus styles.