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 instructions/dev-lou/pixelpilot/uiux-audit-automationgit clone --depth 1 https://github.com/dev-lou/PixelPilotWrote 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/instructions/dev-lou/pixelpilot/uiux-audit-automation)<a href="https://agentmods.dev/instructions/dev-lou/pixelpilot/uiux-audit-automation"><img src="https://agentmods.dev/badge/instructions/dev-lou/pixelpilot/uiux-audit-automation.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 | $0.02169 | $0.02169 |
| Opus 5 | $0.01085 | $0.01085 |
| Sonnet 5 | $0.00434 | $0.00434 |
| Haiku 4.5 | $0.00217 | $0.00217 |
Grade A, and why
PixelPilot uiux-audit-automation.instructions.md 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI/UX Audit Automation 2026
Navigate → inject axe-core → scan → report → fix. Produces a structured WCAG 2.1 AA + 3.0 violation report for any live URL or local dev server page.
PREREQUISITES
# Required MCP: Chrome DevTools (or Puppeteer MCP)
# Confirm it is active before running any step:
# - Tool: browser_navigate, browser_evaluate, browser_screenshot
# axe-core CDN (injected at runtime — no install needed):
AXE_CDN = "https://cdnjs.cloudflare.com/ajax/libs/axe-core/4.9.1/axe.min.js"
STEP 1 — NAVIGATE TO TARGET
// Via Chrome DevTools MCP tool: browser_navigate
await browser_navigate({ url: TARGET_URL });
// Wait for network idle — important for SPAs
await browser_evaluate({ script: `
await new Promise(resolve => {
if (document.readyState === 'complete') return resolve();
window.addEventListener('load', resolve);
});
await new Promise(r => setTimeout(r, 500)); // extra tick for hydration
` });
For local dev servers, use http://localhost:PORT/PATH.
For SPAs, navigate to the specific route — not just /.
STEP 2 — INJECT AXE-CORE
await browser_evaluate({ script: `
// Inject axe-core from CDN
const script = document.createElement('script');
script.src = '${AXE_CDN}';
document.head.appendChild(script);
await new Promise((res, rej) => {
script.onload = res;
script.onerror = () => rej(new Error('axe-core failed to load'));
});
console.log('axe-core loaded:', typeof axe !== 'undefined');
` });
STEP 3 — RUN THE SCAN
const results = await browser_evaluate({ script: `
// Run full axe scan with WCAG 2.1 AA + 2.2 tags
const results = await axe.run(document, {
runOnly: {
type: 'tag',
values: ['wcag2a', 'wcag2aa', 'wcag21a', 'wcag21aa', 'wcag22aa', 'best-practice']
},
resultTypes: ['violations', 'incomplete'],
});
// Summarise for output
return {
url: location.href,
timestamp: new Date().toISOString(),
violations: results.violations.map(v => ({
id: v.id,
impact: v.impact, // critical | serious | moderate | minor
description: v.description,
help: v.help,
helpUrl: v.helpUrl,
wcag: v.tags.filter(t => t.startsWith('wcag')),
nodes: v.nodes.map(n => ({
html: n.html.slice(0, 200),
summary: n.failureSummary,
target: n.target,
})),
})),
incomplete: results.incomplete.length,
passes: results.passes.length,
};
` });
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.
- 4d ago First seen · 321 lines · 2,169 tokens per session scan A c77f06325727
PixelPilot uiux-audit-automation.instructions.md is an instructions file published in the GitHub repository dev-lou/PixelPilot (2 stars, last pushed 5mo ago), licensed MIT. It adds 2,169 tokens to every session, about $0.0108 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 2026-08-31.
Other instructions, from other repositories
ui-ux-design-pro-skill CLAUDE.md
Instructions for saifyxpro/ui-ux-design-pro-skill, covering project overview, cli commands, full design system generation (markdown output), search across all databases (sub-50ms) and audit ui code quality.
UIX CLAUDE.md
Instructions for Deepractice/UIX, covering uix project rules, design system: lucid ui, colors, forbidden and preferred patterns.
wonder-blocks CLAUDE.md
Claude Code instructions for Khan/wonder-blocks, covering wonder blocks design system, technology stack, coding conventions, file & export naming and typescript.
melta-ui AGENTS.md
Instructions for tsubotax/melta-ui, covering melta ui — ai エージェント作業ガイド, アーキテクチャ概要, 最初に読むファイル, 読み込みモード and 作業ルール.
Design-Learn CLAUDE.md
Instructions for GalaxyXieyu/Design-Learn, covering claude.md, todo, quick start, server and vscode extension.
html2style copilot-instructions.md
Copilot instructions for jackguihx-alt/html2style: When working on website style extraction, transfer, or reconstruction in this repository, read SKILL.md and use the portable CLI or MCP tools. Do not depend on a vendor-specific browser plugin. For style work, keep deterministic style-profile.json separate from…