AIPex is an open-source browser automation agent that operates inside the browser a user already uses, controlling pages, tabs, and other browser functions locally. It is intended for people who want browser automation without migrating to another browser, with agents connecting through MCP, skills, or its browser command-line interface. The catalogue skills and instructions extend or operate AIPex's local browser runtime.
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 AIPexStudio/AIPex --skill wcag22-a11y-auditgit clone --depth 1 https://github.com/AIPexStudio/AIPexWrote 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/aipexstudio/aipex/wcag22-a11y-audit)<a href="https://agentmods.dev/skills/aipexstudio/aipex/wcag22-a11y-audit"><img src="https://agentmods.dev/badge/skills/aipexstudio/aipex/wcag22-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.
<a href="https://agentmods.dev/skills/aipexstudio/aipex/wcag22-a11y-audit"><img src="https://agentmods.dev/badge/skills/aipexstudio/aipex/wcag22-a11y-audit.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 | $0.00111 | $0.04526 |
| Opus 5.5 | $0.00044 | $0.01810 |
| Sonnet 5.5 | $0.00022 | $0.00905 |
| Haiku 4.5 | $0.00011 | $0.00453 |
Grade A, and why
wcag22-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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- wcag22-a11y-audit — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 635 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WCAG 2.2 Accessibility Audit Skill
When to Use This Skill
Use this skill when the user wants to:
- Perform accessibility testing or auditing on a live webpage
- Evaluate a page against WCAG 2.2 Success Criteria
- Identify accessibility barriers for keyboard and screen reader users
- Generate a structured accessibility audit report with evidence
Tool Usage Strategy (IMPORTANT)
This skill uses a hybrid approach combining structured accessibility tree analysis and visual inspection.
Priority Order
-
PRIMARY: Accessibility Tree (search_elements)
- Use
search_elements(tabId, query)to retrieve structured accessibility information - This provides
role,name,value,checked,expanded,disabled,focused, etc. - Best for: 1.1.1, 2.1.1, 4.1.2 and element identification for other SCs
- Use
-
SECONDARY: Visual Analysis (Screenshot + LLM)
- Use
capture_screenshot(sendToLLM=true)for visual inspection - Essential for: 1.4.3, 1.4.11, 2.4.7 (contrast and focus visibility)
- Insert
[[screenshot:N]]placeholders in the report for evidence
- Use
-
KEYBOARD INTERACTION: computer tool
- Use
computer(action='key', text='Tab')for keyboard navigation testing - Essential for: 2.1.1, 2.1.2, 2.4.3, 2.4.7
- Capture screenshots at key moments to document focus path
- Use
Workflow for Each Test
1. Identify scope (page/component/flow)
2. Collect evidence via search_elements and/or screenshot
3. Apply SC-specific judgment rules
4. Record Pass/Fail with evidence references
5. Provide actionable fix recommendations
Threat Context & Privacy Notes
IMPORTANT: This audit may capture sensitive information.
- Screenshots and accessibility tree dumps may contain: account names, order details, personal data, auth tokens, internal URLs.
- DO NOT include raw sensitive data in the final report.
- If a screenshot contains PII, note this and recommend masking before sharing.
- Contrast/visual judgments are estimates—always recommend verification with dedicated tools (e.g., WebAIM Contrast Checker, axe DevTools).
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.
- 1mo ago First seen · 635 lines · 111 tokens per session scan A 452975a8866b
wcag22-a11y-audit is a skill published in the GitHub repository AIPexStudio/AIPex (1,274 stars, last pushed 2mo ago), licensed MIT. It adds 111 tokens to every session and 4,526 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
clone
Capture a site's design system — colors, typography, spacing, layout, components — as structured findings.
dogfood
Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -…
electron
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include…
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers hosted cloud browsers for AI agents: the browser-use Python library (Browser(usecloud=True)), Playwright, Puppeteer or any CDP client.
x402
Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — "just use it" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing…
cloud
Documentation reference for using Browser Use Cloud — the hosted API and SDK for browser automation. Use this skill whenever the user needs help with the Cloud REST API (v2, v3, or v4), browser-use-sdk (Python or TypeScript), X-Browser-Use-API-Key authentication, cloud sessions, browser profiles, profile sync, CDP…