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/crawlio-app/crawlio-browser/clonenpx skills add Crawlio-app/crawlio-browser --skill clonegit clone --depth 1 https://github.com/Crawlio-app/crawlio-browserWrote 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/crawlio-app/crawlio-browser/clone)<a href="https://agentmods.dev/skills/crawlio-app/crawlio-browser/clone"><img src="https://agentmods.dev/badge/skills/crawlio-app/crawlio-browser/clone.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 | $0.00021 | $0.00962 |
| Opus 5 | $0.00010 | $0.00481 |
| Sonnet 5 | $0.00004 | $0.00192 |
| Haiku 4.5 | $0.00002 | $0.00096 |
Grade A, and why
clone 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clone — Design System Extraction
Capture the visual DNA of a page: design tokens, typography scale, spacing system, component patterns, and CSS framework.
When to Use
- Reproducing or referencing another site's design system
- Extracting CSS custom properties and design tokens
- Identifying typography, color palette, spacing conventions
- Determining what CSS framework or UI library is in use
Protocol
- search for the right commands:
search("design tokens extract CSS")orsearch("detect technologies") - connect_tab to the target URL with
{ background: true }(or use an already-connected owned tab) - execute Code Mode with smart.* methods to extract evidence
- Emit one
smart.finding()per design dimension discovered - Return
smart.findings()as the final output
Code Example
const page = await smart.extractPage();
const tech = await smart.detectTechnologies();
// Extract CSS custom properties (design tokens)
const tokens = await smart.evaluate(`(() => {
const styles = getComputedStyle(document.documentElement);
const props = {};
for (const name of [...document.styleSheets].flatMap(s => {
try { return [...s.cssRules] } catch { return [] }
}).filter(r => r.style).flatMap(r => [...r.style]).filter(p => p.startsWith('--'))) {
props[name] = styles.getPropertyValue(name).trim();
}
return { count: Object.keys(props).length, sample: Object.entries(props).slice(0, 20) };
})()`);
smart.finding({
claim: `Site uses ${tokens.result.count} CSS custom properties`,
evidence: tokens.result.sample.map(([k, v]) => `${k}: ${v}`),
sourceUrl: page.capture.url,
confidence: "high",
method: "evaluate + extractPage",
dimension: "design-system"
});
// Typography — detect_fonts returns an object, not a bare array
const detectedFonts = Array.isArray(page.fonts?.fonts) ? page.fonts.fonts : [];
if (detectedFonts.length) {
smart.finding({
claim: `${detectedFonts.length} font faces detected`,
evidence: detectedFonts.map(f => `${f.family} ${f.weight} (${f.status})`),
sourceUrl: page.capture.url,
confidence: "high",
method: "extractPage",
dimension: "typography"
});
}
// Framework / UI library
const frameworks = tech.technologies?.map(t => t.name) || [];
if (frameworks.length) {
smart.finding({
claim: `Detected CSS/UI frameworks: ${frameworks.join(", ")}`,
evidence: frameworks,
sourceUrl: page.capture.url,
confidence: "high",
method: "detectTechnologies",
dimension: "technology"
});
}
// Repeating UI patterns (tables / grids)
const tables = await smart.detectTables();
if (tables.length) {
smart.finding({
claim: `${tables.length} repeating UI patterns detected`,
evidence: tables.map(t => `${t.selector}: ${t.rowCount} rows, ${Math.round(t.confidence * 100)}% confidence (${t.strategy})`),
sourceUrl: page.capture.url,
confidence: "high",
method: "detectTables",
dimension: "layout"
});
}
// Visual reference
await smart.scrollCapture();
return { findings: smart.findings(), fonts: page.fonts, tech: frameworks };
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 · 113 lines · 21 tokens per session scan A e76f4e33526a
clone is a skill published in the GitHub repository Crawlio-app/crawlio-browser (6 stars, last pushed 25d ago), licensed Apache-2.0. It adds 21 tokens to every session and 962 once invoked, about $0.0001 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 skills, from other repositories
nekoro-browser
浏览器自动化——打开网页、搜索、点击、截图、执行 JS、填表、上传文件、处理对话框。通过 Chrome 扩展的 chrome.debugger API 操控用户日常浏览器,保留登录态,不开调试端口。触发词:"浏览器"、"打开网页"、"搜索"、"截图"、"点击"、"填表"、"上传文件"、"自动化操作"。.
wcag22-a11y-audit
WCAG 2.2 Accessibility Audit skill that systematically evaluates web pages against 8 core Success Criteria (1.1.1, 1.4.3, 1.4.11, 2.1.1, 2.1.2, 2.4.3, 2.4.7, 4.1.2) using accessibility tree inspection and visual analysis. Use this skill when you need to perform accessibility testing/auditing on a live webpage.
ux-audit-walkthrough
Minimalist UX/Interaction Audit Expert that deconstructs complex interactions through cognitive load and operational efficiency lenses. Use this skill when you need to perform a UX walkthrough audit on a Figma prototype or web interface, evaluating usability based on principles like fewer clicks, less UI elements, no…
owb
Open Web Bridge (OWB) — drive the user's own real browser with the owb command. Read pages behind their existing logins, gather and cross-check information, fill forms, walk multi-step flows, debug their site, audit responsive/accessibility behavior, and capture or reverse-engineer network traffic. Use this whenever…
browsertap-default
浏览器自动化默认入口。任何打开网页、填表、点击、截图、抓取或复用已登录 Chrome/Edge 的任务,优先使用 browsertap-mcp (BTAP) MCP 工具。.
browsertap-bridge-recovery
恢复 browsertap-mcp (BTAP) 的 CDP 桥连。触发:桥断了 / MCP 浏览器工具挂住 / getsetupstatus 转圈 / listtabs 拿不到 tab / Unknown command: downloads。分层排错:netstat → /link curl → listtabs,别把 MCP 层挂当成桥断。.