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-zhihu-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-zhihu-ops-skill)<a href="https://agentmods.dev/skills/imjszhang/js-eyes/js-zhihu-ops-skill"><img src="https://agentmods.dev/badge/skills/imjszhang/js-eyes/js-zhihu-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-zhihu-ops-skill"><img src="https://agentmods.dev/badge/skills/imjszhang/js-eyes/js-zhihu-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 | $0.00023 | $0.02396 |
| Opus 5 | $0.00012 | $0.01198 |
| Sonnet 5 | $0.00005 | $0.00479 |
| Haiku 4.5 | $0.00002 | $0.00240 |
Grade A, and why
js-zhihu-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 11d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
js-zhihu-ops-skill
面向知乎内容读取的 skill。v3.0 起按 PAGE_PROFILES + Bridges + Session 架构升级，支持回答、专栏、问题、搜索、用户、首页多个 profile，并保留 JS_ZHIHU_DISABLE_BRIDGE=1 旧脚本 fallback。
浏览器兼容性与登录
- 要求 Node.js 22+、JS Eyes 2.8.5+、已连接的浏览器扩展与运行中的 Server。
- 页面 bridge 需要宿主设置
security.allowRawEval: true；JS Eyes 2.5+ 会同步到扩展，扩展侧显式false仍可强制关闭。 - Chrome 要求 135+；Chrome 138+ 还需开启浏览器控制的 Allow User Scripts。
- 公开内容通常可匿名读取；搜索、连续分页或触发登录墙后的页面依赖浏览器已有登录态。本 Skill 不执行登录自动化。
安全分级
- READ：
zhihu_get_answer、zhihu_get_article、zhihu_session_state、zhihu_get_question_answers、zhihu_search、zhihu_get_user、zhihu_get_user_answers、zhihu_get_user_articles。 - INTERACTIVE：
zhihu_navigate_*。仅location.assign导航，不模拟点击、不改 DOM。 - DESTRUCTIVE：不引入。本文档不提供回答发布、评论、点赞、收藏、关注等能力。
提供的 AI 工具
| 工具 | 类型 | 说明 |
|---|---|---|
zhihu_get_answer |
READ | 读取知乎回答详情 |
zhihu_get_article |
READ | 读取知乎专栏详情 |
zhihu_session_state |
READ | 读取登录态、cookie 标记、登录墙/验证码状态 |
zhihu_get_question_answers |
READ | 读取问题页标题、描述和回答摘要列表 |
zhihu_search |
READ | 读取搜索结果 |
zhihu_get_user |
READ | 读取用户主页资料 |
zhihu_get_user_answers |
READ | 读取用户回答列表摘要 |
zhihu_get_user_articles |
READ | 读取用户文章列表摘要 |
zhihu_navigate_* |
INTERACTIVE | answer / article / question / search / user / home 导航 |
zhihu_monitor_* |
READ | list/status/add/remove/test 监控配置工具 |
CLI
node skills/js-zhihu-ops-skill/index.js answer "https://www.zhihu.com/question/1/answer/2" --pretty
node skills/js-zhihu-ops-skill/index.js article "https://zhuanlan.zhihu.com/p/123456" --pretty
node skills/js-zhihu-ops-skill/index.js session-state --pretty
node skills/js-zhihu-ops-skill/index.js doctor --pretty
node skills/js-zhihu-ops-skill/index.js records --last 5 --pretty
node skills/js-zhihu-ops-skill/index.js question-answers "https://www.zhihu.com/question/1" --limit 10 --max-pages 2 --pretty
node skills/js-zhihu-ops-skill/index.js search "大模型" --limit 10 --max-pages 2 --pretty
node skills/js-zhihu-ops-skill/index.js user "people-slug" --pretty
node skills/js-zhihu-ops-skill/index.js monitor init --pretty
node skills/js-zhihu-ops-skill/index.js monitor add search "大模型" --limit 10 --pretty
What ships with it
43 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-zhihu.js 2.3 KB runs code
- bridges/answer-bridge.js 1.4 KB runs code
- bridges/article-bridge.js 1.3 KB runs code
- bridges/common.js 16 KB runs code
- bridges/home-bridge.js 673 B runs code
- bridges/question-bridge.js 1.4 KB runs code
- bridges/search-bridge.js 1.3 KB runs code
- bridges/user-bridge.js 2.1 KB runs code
- cli/index.js 11 KB runs code
- index.js 387 B runs code
- lib/api.js 6.3 KB runs code
- lib/commands.js 14 KB runs code
- lib/config.js 4.0 KB runs code
- lib/monitor/config.js 3.1 KB runs code
- lib/monitor/dispatcher.js 3.8 KB runs code
- lib/monitor/paths.js 428 B runs code
- lib/rateLimit/limiter.js 1.5 KB runs code
- lib/runContext.js 728 B runs code
- lib/runMonitor.js 6.7 KB runs code
- lib/runtimeConfig.js 939 B runs code
- lib/runTool.js 19 KB runs code
- lib/session.js 12 KB runs code
- lib/toolTargets.js 1.9 KB runs code
- lib/visualHint.js 3.8 KB runs code
- lib/wsAuth.js 979 B runs code
- lib/zhihuUtils.js 8.3 KB runs code
- package.json 1.2 KB
- scripts/_dev/smoke-browser.js 13 KB runs code
- scripts/_dev/smoke-browser.samples.json 613 B
- scripts/zhihu-answer.js 2.3 KB runs code
- scripts/zhihu-article.js 2.3 KB runs code
- skill.definition.js 18 KB runs code
- skill.entry.js 194 B runs code
- skill.manifest.json 17 KB
- tests/commands.test.js 2.0 KB runs code
- tests/contract.test.js 1.5 KB runs code
- tests/monitor.test.js 1.5 KB runs code
- tests/runTool.test.js 1.8 KB runs code
- tests/session.test.js 832 B runs code
- tests/smokeBrowser.test.js 4.6 KB runs code
- tests/targets.test.js 1.1 KB runs code
- tests/wsAuth.test.js 852 B runs code
- tests/zhihuUtils.test.js 1.7 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.
- 11d ago First seen · 164 lines · 23 tokens per session scan A 34ddfbf7a217
js-zhihu-ops-skill is a skill published in the GitHub repository imjszhang/js-eyes (43 stars, last pushed 3d ago), licensed MIT. It adds 23 tokens to every session and 2,396 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
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…
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.
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…