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 | $0.03709 |
| Opus 5.5 | $0.00012 | $0.01484 |
| Sonnet 5.5 | $0.00006 | $0.00742 |
| Haiku 4.5 | $0.00003 | $0.00371 |
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 1mo 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 — 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。需要人完成登录或 2FA 时，使用宿主的 browser_wait_for_user（扩展 popup 继续，或 js-eyes browser resume）。
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，或 page.state 的 ref |
browser_fill_form |
填写表单字段（input/textarea/select/contenteditable）；可用 ref 或 secretRef |
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 14 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.
- 1mo ago Changed a17e2428c6bf
- 2mo ago Changed · +72 lines dcb1113bd5fb
- 2mo 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 (45 stars, last pushed 2d ago), licensed MIT. It adds 29 tokens to every session and 3,709 once invoked, about $0.0001 per session on Opus 5.5. 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.
js-browser-ops-skill compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| js-browser-ops-skillimjszhang/js-eyes | Skill | 45 | 2d ago | MIT | A | 29 | Claude Code, Codex |
| interactive-loginyc-software/qm | Skill | 16k | yesterday | MIT | A | 46 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |
| azure-messaging-webpubsub-javamicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 43 | Claude Code |
| cua-driverdavidondrej/skills | Skill | 4.3k | 3d ago | MIT | A | 68 | Claude Code, Codex |
| open-design-browsercompozy/compozy | Skill | 2.8k | yesterday | MIT | A | 56 | Claude Code, Codex |
| southwestborski/travel-hacking-toolkit | Skill | 895 | yesterday | MIT | A | 40 | Claude Code |