test

test is a skill for Claude Code, Codex from Crawlio-app/crawlio-browser. It costs 19 tokens per session (1,117 once invoked), scanned A, original, Apache-2.0.

A page-testing skill that checks accessibility, speed, security, search-engine readiness, and mobile support. Accessibility means making a page usable by people with disabilities; SEO means helping search engines understand it.

In plain words
What is it for?
Auditing a live page, extracting its quality data, checking assertions such as missing image descriptions, and returning findings with evidence and gaps.
Why use it?
It turns quality requirements into pass-or-fail findings and limits confidence when important data is missing.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/crawlio-app/crawlio-browser/test
Any agent
npx skills add Crawlio-app/crawlio-browser --skill test
Clone the repo
git clone --depth 1 https://github.com/Crawlio-app/crawlio-browser

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for test

README.md
[![agentmods](https://agentmods.dev/badge/skills/crawlio-app/crawlio-browser/test.svg)](https://agentmods.dev/skills/crawlio-app/crawlio-browser/test)
Your own site
<a href="https://agentmods.dev/skills/crawlio-app/crawlio-browser/test"><img src="https://agentmods.dev/badge/skills/crawlio-app/crawlio-browser/test.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,117 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00019 $0.01117
Opus 5 $0.00010 $0.00558
Sonnet 5 $0.00004 $0.00223
Haiku 4.5 $0.00002 $0.00112

Measured 3d ago against content hash ace913998890, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test 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 3d 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.

skills/test/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test — Quality Assertions

Run pass/fail assertions across accessibility, performance, security, SEO, and mobile readiness. Every assertion becomes a finding. Confidence auto-caps when data is missing.

When to Use

  • Auditing accessibility, performance, security, SEO, or mobile readiness
  • Running pass/fail assertions against quality thresholds

Protocol

  1. search for extraction commands: search("extract page accessibility")
  2. connect_tab to the target URL with { background: true }
  3. execute Code Mode: smart.extractPage() gathers all dimensions in one call
  4. Emit one smart.finding() per assertion — claim states pass or fail
  5. Return smart.findings() + page.gaps

Code Example

const page = await smart.extractPage();

// Accessibility
if (page.accessibility) {
  smart.finding({
    claim: page.accessibility.imagesWithoutAlt === 0
      ? "All images have alt text"
      : `${page.accessibility.imagesWithoutAlt} images missing alt text`,
    evidence: [`imagesWithoutAlt: ${page.accessibility.imagesWithoutAlt}`, `nodeCount: ${page.accessibility.nodeCount}`],
    sourceUrl: page.capture.url, confidence: "high",
    method: "extractPage", dimension: "accessibility"
  });
  smart.finding({
    claim: page.accessibility.landmarkCount > 0
      ? `${page.accessibility.landmarkCount} ARIA landmarks found`
      : "No ARIA landmarks — add banner, main, contentinfo",
    evidence: [`landmarkCount: ${page.accessibility.landmarkCount}`],
    sourceUrl: page.capture.url, confidence: "high",
    method: "extractPage", dimension: "accessibility"
  });
}

// Performance
if (page.performance) {
  const lcp = page.performance.webVitals?.lcp;
  const cls = page.performance.webVitals?.cls;
  smart.finding({
    claim: lcp && lcp < 2500 ? `LCP good (${lcp}ms)` : `LCP needs work (${lcp || "unknown"}ms)`,
    evidence: [`LCP: ${lcp}ms`, `CLS: ${cls}`, `thresholds: LCP<2500, CLS<0.1`],
    sourceUrl: page.capture.url, confidence: lcp ? "high" : "low",
    method: "extractPage", dimension: "performance"
  });
}

// Security
if (page.security) {
  smart.finding({
    claim: page.security.securityState === "secure"
      ? "TLS connection is secure" : `Security state: ${page.security.securityState || "unknown"}`,
    evidence: [`protocol: ${page.security.certificate?.protocol || "unknown"}`],
    sourceUrl: page.capture.url, confidence: "high",
    method: "extractPage", dimension: "security"
  });
}

// SEO
if (page.meta) {
  const m = page.meta;
  smart.finding({
    claim: m._title && m.description ? "Title + meta description present" : "SEO meta tags incomplete",
    evidence: [`title: ${m._title || "missing"} (${m._title?.length || 0} chars)`,
               `description: ${m.description || "missing"} (${m.description?.length || 0} chars)`],
    sourceUrl: page.capture.url, confidence: "high",
    method: "extractPage", dimension: "seo"
  });
}

// Mobile readiness
if (page.mobileReadiness) {
  smart.finding({
    claim: page.mobileReadiness.hasViewportMeta ? "Viewport meta tag present" : "Missing viewport meta",
    evidence: [`viewport: ${page.mobileReadiness.viewportContent || "none"}`],
    sourceUrl: page.capture.url, confidence: "high",
    method: "extractPage", dimension: "mobile-readiness"
  });
}

// Tech stack
const tech = await smart.detectTechnologies();
if (tech.technologies?.length) {
  smart.finding({
    claim: `${tech.technologies.length} technologies detected`,
    evidence: tech.technologies.map(t => t.name),
    sourceUrl: page.capture.url, confidence: "high",
    method: "detectTechnologies", dimension: "technology"
  });
}

return { findings: smart.findings(), gaps: page.gaps };

Read the full file on GitHub · 118 lines

Changes

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.

  1. 3d ago First seen · 118 lines · 19 tokens per session scan A ace913998890

Subscribe to this mod's changes

test is a skill published in the GitHub repository Crawlio-app/crawlio-browser (6 stars, last pushed 24d ago), licensed Apache-2.0. It adds 19 tokens to every session and 1,117 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.

Related

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"。.

zeshuochen/nekoro-browser · 102 tokens

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…

woniu9524/open-web-bridge · 143 tokens

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。.

LinVireo/browsertap-mcp · 53 tokens

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。.

LinVireo/browsertap-mcp · 84 tokens

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.

Nitjsefnie-Harness-Commons/daedalus · 51 tokens

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.

DevZonayed/Mochi · 50 tokens