Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/imjszhang/js-eyes/js-xiaohongshu-ops-skill)<a href="https://agentmods.dev/skills/imjszhang/js-eyes/js-xiaohongshu-ops-skill"><img src="https://agentmods.dev/badge/skills/imjszhang/js-eyes/js-xiaohongshu-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-xiaohongshu-ops-skill"><img src="https://agentmods.dev/badge/skills/imjszhang/js-eyes/js-xiaohongshu-ops-skill.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00043 | $0.05891 |
| Opus 5 | $0.00022 | $0.02946 |
| Sonnet 5 | $0.00009 | $0.01178 |
| Haiku 4.5 | $0.00004 | $0.00589 |
Grade A, and why
js-xiaohongshu-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 12d 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 — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
js-xiaohongshu-ops-skill
面向小红书内容读取的 skill。v2.1 起按 skills/js-x-ops-skill 的 PAGE_PROFILES + Bridges + Session 架构重构，支持笔记 / 搜索 / 用户 / 首页四个 profile，并按 v2.1 → v3.x 阶段渐进交付：
- v2.1（当前）：架构铺底，落
note-bridge与xhs_get_note/xhs_get_note_comments/xhs_session_state三个 READ 工具。 - v2.2：搜索域（
search-bridge+xhs_search_notes+ 4 个 INTERACTIVE 导航工具）。 - v2.3：用户域（
user-bridge+xhs_get_user/xhs_get_user_notes）。 - v3.0：监控子系统（accounts + searches 两类 target）。
- v3.x：限流 / 反爬 / visual-bridge-kit / cookie sanitize 治理。
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。
- 笔记公开内容可匿名读取；评论 API、部分用户页和风控后的页面要求浏览器已有登录态。本 Skill 提供 CLI 登录引导，但不向 AI 暴露登录操作。
安全分级
- READ：
xhs_get_note、xhs_get_note_comments、xhs_session_state（v2.1）。 - INTERACTIVE：
xhs_navigate_*（v2.2 起）。仅location.assign，不模拟点击、不改 DOM。 - DESTRUCTIVE：永不引入。本 skill 不提供发笔记 / 评论 / 点赞 / 收藏 / 关注。
READ 调度（readMode）
xhs_get_note 默认 readMode='auto'，与 X 取反：
auto：DOM 优先 → API 兜底（小红书 DOM 覆盖更广，feed JSON 不稳定）。dom：仅 DOM 抽取。api：仅 API（笔记详情 stub，主用于评论/调试）。
xhs_get_note_comments 默认 readMode='api'（基于 edith /api/sns/web/v2/comment/page，分页稳定）。
提供的 AI 工具（v3.0）
| 工具 | 类型 | 说明 |
|---|---|---|
xhs_get_note |
READ | 笔记详情 + 可选评论 |
xhs_get_note_comments |
READ | 评论分页（API 主路径） |
xhs_session_state |
READ | 登录态读取（cookie a1/web_session + DOM 昵称） |
xhs_search_notes |
READ | 搜索（频道 / 筛选 / 滚动；可 extractDetails 串行点开详情） |
xhs_get_user |
READ | 用户主页资料（昵称、签名、关注/粉丝/获赞） |
xhs_get_user_notes |
READ | 用户笔记列表（滚动分页） |
xhs_navigate_* |
INTERACTIVE | navigate-note / search / user / home（仅 location.assign） |
xhs_monitor_list_targets |
READ | 列出 monitor accounts + searches + channels |
xhs_monitor_get_status |
READ | daemon pid + 各 target lastCheck/notesCount |
xhs_monitor_add_target |
READ | 增加一个 user/search target（仅写 config，不发通知） |
xhs_monitor_remove_target |
READ | 删除一个 user/search target |
xhs_monitor_test_target |
READ | 单 target dry run（不写 state、不发通知） |
What ships with it
60 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-xhs.js 3.9 KB runs code
- bridges/common.js 18 KB runs code
- bridges/home-bridge.js 1.5 KB runs code
- bridges/note-bridge.js 13 KB runs code
- bridges/search-bridge.js 38 KB runs code
- bridges/user-bridge.js 8.8 KB runs code
- cli/index.js 18 KB runs code
- docs/dev/monitor-runbook.md 6.4 KB
- index.js 650 B runs code
- lib/api.js 4.0 KB runs code
- lib/bridgeAdapter.js 5.4 KB runs code
- lib/cliVisualFlags.js 849 B runs code
- lib/commands.js 15 KB runs code
- lib/config.js 3.8 KB runs code
- lib/monitor/config.js 8.8 KB runs code
- lib/monitor/daemon.js 5.4 KB runs code
- lib/monitor/dedup.js 1.8 KB runs code
- lib/monitor/dispatcher.js 9.6 KB runs code
- lib/monitor/fetchSearch.js 1.8 KB runs code
- lib/monitor/fetchUserNotes.js 1.5 KB runs code
- lib/monitor/format.js 4.0 KB runs code
- lib/monitor/logs.js 569 B runs code
- lib/monitor/notify.js 5.7 KB runs code
- lib/monitor/paths.js 2.5 KB runs code
- lib/monitor/runCheck.js 11 KB runs code
- lib/monitor/state.js 2.0 KB runs code
- lib/rateLimit/antiCrawlingStats.js 3.4 KB runs code
- lib/rateLimit/limiter.js 3.5 KB runs code
- lib/runContext.js 987 B runs code
- lib/runMonitor.js 9.5 KB runs code
- lib/runtimeConfig.js 939 B runs code
- lib/runTool.js 21 KB runs code
- lib/session.js 15 KB runs code
- lib/toolTargets.js 1.3 KB runs code
- lib/visualHint.js 9.2 KB runs code
- lib/xhsUtils.js 4.7 KB runs code
- lib/xiaohongshuUtils.js 12 KB runs code
- package.json 908 B
- scripts/_dev/diff-snapshot.js 3.3 KB runs code
- scripts/_dev/probe-comments.js 2.3 KB runs code
- scripts/_dev/probe-note.js 3.3 KB runs code
- scripts/_dev/probe-search.js 5.8 KB runs code
- scripts/_dev/probe-snapshot.js 3.9 KB runs code
- scripts/_dev/probe-token.js 3.0 KB runs code
- scripts/_dev/probe-user.js 3.5 KB runs code
- scripts/aggregate-note.js 9.3 KB runs code
- scripts/xhs-note.js 2.6 KB runs code
- skill.definition.js 17 KB runs code
- skill.entry.js 252 B runs code
- skill.manifest.json 16 KB
- tests/antiCrawlClassify.test.js 4.0 KB runs code
- tests/cliVisualFlags.test.js 3.0 KB runs code
- tests/config.test.js 2.6 KB runs code
- tests/contract.test.js 2.7 KB runs code
- tests/monitor.test.js 3.4 KB runs code
- tests/monitorSchemaV2.test.js 2.9 KB runs code
- tests/rateLimit.test.js 2.1 KB runs code
- tests/runTool.test.js 1.7 KB runs code
- tests/sanitize.test.js 3.0 KB runs code
- tests/search.test.js 5.9 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.
- 12d ago First seen · 334 lines · 43 tokens per session scan A 5cde2ad3fc93
js-xiaohongshu-ops-skill is a skill published in the GitHub repository imjszhang/js-eyes (43 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 5,891 once invoked, about $0.0002 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…