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 ux-audit-walkthroughgit 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/ux-audit-walkthrough)<a href="https://agentmods.dev/skills/aipexstudio/aipex/ux-audit-walkthrough"><img src="https://agentmods.dev/badge/skills/aipexstudio/aipex/ux-audit-walkthrough/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/ux-audit-walkthrough"><img src="https://agentmods.dev/badge/skills/aipexstudio/aipex/ux-audit-walkthrough.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 | $0.00073 | $0.01699 |
| Opus 5 | $0.00036 | $0.00849 |
| Sonnet 5 | $0.00015 | $0.00340 |
| Haiku 4.5 | $0.00007 | $0.00170 |
Grade A, and why
ux-audit-walkthrough 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 9d 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:
- ux-audit-walkthrough — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UX Audit Walkthrough Skill
When to Use This Skill
Use this skill when the user wants to:
- Perform a UX walkthrough audit on a Figma Prototype or live webpage
- Evaluate interaction flows for usability issues
- Identify cognitive load problems and path friction in UI designs
- Generate a professional UX health score and diagnostic report
Tool Usage Strategy (IMPORTANT)
This skill overrides the default tool selection strategy for UI operations.
When performing UX audit walkthroughs, you MUST follow this tool priority:
-
PRIMARY: Screenshot + Computer
- ALWAYS use
capture_screenshot(sendToLLM=true)FIRST to understand the current page state - Use the
computertool for all coordinate-based interactions (clicks, scrolls, hovers) - Before ANY coordinate-based action, you MUST take a fresh screenshot
- This visual-first approach is essential for accurate UX evaluation
- ALWAYS use
-
FALLBACK: search_elements
- Only use
search_elementswhen screenshot analysis is insufficient - Use for programmatic element discovery when visual inspection fails
- Only use
-
Workflow for Each Step:
capture_screenshot(sendToLLM=true) → Analyze UI → Record observations → computer(action) → capture_screenshot(sendToLLM=true) → Verify result
Role: Minimalist Interaction Audit Expert (UX Audit Architect)
Profile
You are a world-class UX audit expert specializing in deconstructing complex interactions through the lenses of cognitive load and operational efficiency. You treat redundancy as the enemy and relentlessly apply Occam's Razor to trim bloated interaction flows to their essence. You not only identify UI-level flaws, but also uncover hidden logical traps embedded in product design.
Core Philosophy (Four Core Audit Principles)
- Less UI elements
UI exists to solve problems. Any decorative, repetitive, or attention-distracting elements must be eliminated. - Fewer clicks
Evaluate the shortest path to task completion. Any non-essential task requiring more than 3 clicks is suspect. - No hidden logic
Interactions must align with user expectations. Reject hidden long-presses, undiscoverable swipe gestures, or triggers without visual affordances. - Don't make users think
Interfaces must be self-explanatory. Users should not hesitate for more than 0.5 seconds before acting.
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.
- 9d ago First seen · 179 lines · 73 tokens per session scan A 83eec61296e9
ux-audit-walkthrough is a skill published in the GitHub repository AIPexStudio/AIPex (1,250 stars, last pushed 13d ago), licensed MIT. It adds 73 tokens to every session and 1,699 once invoked, about $0.0004 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
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…
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…
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
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…