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 imjszhang/js-eyes --skill js-browser-ops-skillgit clone --depth 1 https://github.com/imjszhang/js-eyesWrote 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/imjszhang/js-eyes/js-browser-ops-skill)<a href="https://agentmods.dev/skills/imjszhang/js-eyes/js-browser-ops-skill"><img src="https://agentmods.dev/badge/skills/imjszhang/js-eyes/js-browser-ops-skill/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/imjszhang/js-eyes/js-browser-ops-skill"><img src="https://agentmods.dev/badge/skills/imjszhang/js-eyes/js-browser-ops-skill.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 | $0.00029 | $0.03653 |
| Opus 5 | $0.00015 | $0.01826 |
| Sonnet 5 | $0.00006 | $0.00731 |
| Haiku 4.5 | $0.00003 | $0.00365 |
Grade A, and why
js-browser-ops-skill 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 yesterday.
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 — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
js-browser-ops-skill
通用浏览器操作技能 — 基于 js-eyes 浏览器自动化，提供面向任意网站的内容读取、DOM 交互和截图能力。
与其他平台特化技能（如 js-x-ops-skill、js-zhihu-ops-skill）不同，本技能不绑定特定平台，适用于所有网页。
依赖
本技能依赖 js-eyes 技能提供的浏览器自动化能力。使用前请确保：
- Node.js 22+、JS Eyes 2.8.5+，且 JS-Eyes Server 已运行
- 浏览器已安装 JS-Eyes 扩展并连接到服务器
browser_click/browser_fill_form/browser_wait_for/browser_scroll使用扩展内置操作，不要求 Raw Eval；页面正文抽取等脚本能力需要宿主设置security.allowRawEval: true- JS Eyes 2.5+ 会把宿主的 Raw Eval 设置同步到扩展；扩展存储中的显式
false仍可强制关闭 - Chrome 脚本能力要求 Chrome 135+；Chrome 138+ 还需在浏览器扩展设置中开启 Allow User Scripts
登录要求取决于目标网页；本 Skill 不执行登录自动化。
提供的 AI 工具
| 工具 | 说明 |
|---|---|
browser_read_page |
读取网页正文。打开后先按 waitUntil / minContentChars 等待，短空壳返回 content_too_short 而不是导航栏。自开标签默认读完关闭；keepOpen 才回传可复用 tabId。 |
browser_read_pages |
批量读取。返回每条 { url, ok, data?, error? }，单条失败不影响其余；同 host 默认串行并遵守最小间隔。 |
browser_click |
点击页面元素，支持 CSS 选择器、XPath、文本内容匹配 |
browser_fill_form |
填写表单字段（input/textarea/select/contenteditable） |
browser_wait_for |
等待元素出现或条件满足（基于 MutationObserver） |
browser_scroll |
页面滚动（到顶部/底部、指定元素、指定像素偏移） |
browser_screenshot |
调用 browser.captureScreenshot 获取截图结果 |
browser_cleanup_session |
关闭本 session 仍打开的自开标签 |
编程 API
const { BrowserAutomation } = require('./lib/js-eyes-client');
const { readPage, readPages, clickElement, fillForm, scrollPage, cleanupTabSession } = require('./lib/api');
const browser = new BrowserAutomation('ws://localhost:18080');
// 纯读取默认会关闭自开标签，返回 tabId: null。
// 后续还要 click/fill 时必须 keepOpen，并禁用缓存以取得 live tabId。
const page = await readPage(browser, {
url: 'https://example.com/article',
format: 'markdown',
noCache: true,
keepOpen: true,
});
// 点击元素
await clickElement(browser, {
tabId: page.tabId,
selector: 'button.submit',
});
// 填写表单
await fillForm(browser, {
tabId: page.tabId,
selector: 'input[name="email"]',
value: '[email protected]',
clearFirst: true,
});
// 滚动到底部
await scrollPage(browser, {
tabId: page.tabId,
target: 'bottom',
});
await cleanupTabSession(browser);
const pages = await readPages(browser, {
urls: ['https://a.example/1', 'https://b.example/2'],
format: 'markdown',
concurrency: 3,
perHostMinIntervalMs: 1000,
perHostConcurrency: 1,
timeoutMs: 30000,
totalTimeoutMs: 180000,
signal,
});
What ships with it
27 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- bridges/_visual-browser.js 4.3 KB runs code
- CHANGELOG.md 11 KB
- cli/index.js 1.2 KB runs code
- index.js 2.3 KB runs code
- lib/api.js 16 KB runs code
- lib/batchRead.js 6.4 KB runs code
- lib/browserUtils.js 133 B runs code
- lib/cliAbort.js 538 B runs code
- lib/cliRun.js 658 B runs code
- lib/cliVisualFlags.js 11 KB runs code
- lib/egressAllowlist.js 9.6 KB runs code
- lib/pageWait.js 6.3 KB runs code
- lib/runContext.js 1.3 KB runs code
- lib/runtimeConfig.js 993 B runs code
- lib/skillError.js 9.7 KB runs code
- lib/tabSession.js 4.7 KB runs code
- lib/visualHint.js 7.2 KB runs code
- package.json 826 B
- scripts/browser-interact.js 5.6 KB runs code
- scripts/browser-read-pages.js 5.0 KB runs code
- scripts/browser-read.js 6.7 KB runs code
- skill.definition.js 15 KB runs code
- skill.entry.js 194 B runs code
- skill.manifest.json 13 KB
- tests/core.test.js 24 KB runs code
- tests/read-pages.test.js 7.8 KB runs code
- tests/skill-errors.test.js 9.5 KB runs code
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.
- yesterday Changed · +72 lines dcb1113bd5fb
- 9d ago First seen · 208 lines · 29 tokens per session scan A 6d1cbb3c37bb
js-browser-ops-skill is a skill published in the GitHub repository imjszhang/js-eyes (43 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 3,653 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 2026-08-30.
Other skills, from other repositories
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…