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/comparenpx skills add Crawlio-app/crawlio-browser --skill comparegit 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/compare)<a href="https://agentmods.dev/skills/crawlio-app/crawlio-browser/compare"><img src="https://agentmods.dev/badge/skills/crawlio-app/crawlio-browser/compare.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 | $0.00022 | $0.00949 |
| Opus 5 | $0.00011 | $0.00475 |
| Sonnet 5 | $0.00004 | $0.00190 |
| Haiku 4.5 | $0.00002 | $0.00095 |
Grade A, and why
compare 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compare
Side-by-side comparison of two websites across 11 typed dimensions. One call captures both sites and returns a scaffold with per-dimension comparability. Produces one finding per dimension.
When to Use
- Compare two competing sites (framework, performance, security)
- Audit staging vs production
- Benchmark a site against a competitor across all 11 dimensions
- Identify gaps where one site excels and the other falls short
The 11 Dimensions
framework, performance, security, seo, accessibility, error-surface, third-party-load, architecture, content-delivery, mobile-readiness, data-structure.
Protocol
Acquire -> Normalize -> Analyze with Evidence Mode.
1. Connect
connect_tab({ url: "https://site-a.com", background: true })
comparePages handles navigation to both sites internally.
2. Acquire + Normalize
const comparison = await smart.comparePages(
"https://site-a.com",
"https://site-b.com"
);
// comparison.siteA / siteB — full PageEvidence (capture, performance, security, etc.)
// comparison.scaffold.dimensions[] — 11 objects: { name, comparable, siteA.type/value, siteB.type/value }
// comparison.scaffold.sharedFields / missingFields
// comparison.siteA.gaps[] / siteB.gaps[] — what failed per site
3. Analyze — produce findings
Walk the scaffold. One finding per dimension.
for (const dim of comparison.scaffold.dimensions) {
if (!dim.comparable) {
smart.finding({
claim: `${dim.name}: not comparable — data missing`,
evidence: [`siteA: ${dim.siteA.type}`, `siteB: ${dim.siteB.type}`],
sourceUrl: comparison.siteA.capture?.url || "unknown",
confidence: "low", method: "comparePages", dimension: dim.name
});
continue;
}
smart.finding({
claim: `${dim.name}: both sites present — ready for comparison`,
evidence: [
`siteA (${dim.siteA.type}): ${JSON.stringify(dim.siteA.value)}`,
`siteB (${dim.siteB.type}): ${JSON.stringify(dim.siteB.value)}`
],
sourceUrl: comparison.siteA.capture?.url || "unknown",
confidence: "high", method: "comparePages", dimension: dim.name
});
}
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 · 110 lines · 22 tokens per session scan A 2baf461ba4a7
compare is a skill published in the GitHub repository Crawlio-app/crawlio-browser (6 stars, last pushed 25d ago), licensed Apache-2.0. It adds 22 tokens to every session and 949 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"。.
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。.
changing-daedalus
Use when changing anything in this repository - before running its suites, adding a tracked file, growing a size-baselined module, writing a regression test, judging a CI failure, or filing, claiming and labelling an issue.
browser
Use this skill when the user says browser, /browser, test in Chrome, inspect a webpage, verify a localhost app, capture screenshots, check console/network errors, run browser QA, or automate browser flows with the Mochi browser MCP.