Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/joeseesun/qiaomu-opencli-skillsnpx agentmods add skills/joeseesun/qiaomu-opencli-skills/qiaomu-opencli-explorerWrote 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/joeseesun/qiaomu-opencli-skills/qiaomu-opencli-explorer)<a href="https://agentmods.dev/skills/joeseesun/qiaomu-opencli-skills/qiaomu-opencli-explorer"><img src="https://agentmods.dev/badge/skills/joeseesun/qiaomu-opencli-skills/qiaomu-opencli-explorer/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/joeseesun/qiaomu-opencli-skills/qiaomu-opencli-explorer"><img src="https://agentmods.dev/badge/skills/joeseesun/qiaomu-opencli-skills/qiaomu-opencli-explorer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 162 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 262 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00083 | $0.09699 |
| Opus 5 | $0.00042 | $0.04849 |
| Sonnet 5 | $0.00017 | $0.01940 |
| Haiku 4.5 | $0.00008 | $0.00970 |
Grade A, and why
qiaomu-opencli-explorer scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| 5. 验证 API | `browser_evaluate` | `fetch(url, {credentials:'include'})` 测试返回结构 | How it starts
The opening of the file, as written. The whole thing — 855 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLI-EXPLORER — 适配器探索式开发完全指南
本文档教你（或 AI Agent）如何为 OpenCLI 添加一个新网站的命令。
从零到发布，覆盖 API 发现、方案选择、适配器编写、测试验证全流程。
[!TIP] 只想为一个具体页面快速生成一个命令？ 看 opencli-oneshot skill（~150 行，4 步搞定）。 本文档适合从零探索一个新站点的完整流程。
[!TIP] 想要全自动生成？ 直接运行
opencli generate <url> [--goal <goal>]，内部会自动走完 explore → synthesize → cascade → verify 全流程。 返回SkillOutput（success / blocked / needs-human-check）。如果自动生成失败或需要人工介入，再按本文档的手动流程继续。
AI Agent 开发者必读：用浏览器探索
[!CAUTION] 你（AI Agent）必须通过浏览器打开目标网站去探索！
不要只靠opencli explore命令或静态分析来发现 API。
你拥有浏览器工具，必须主动用它们浏览网页、观察网络请求、模拟用户交互。
为什么？
很多 API 是懒加载的（用户必须点击某个按钮/标签才会触发网络请求）。字幕、评论、关注列表等深层数据不会在页面首次加载时出现在 Network 面板中。如果你不主动去浏览和交互页面，你永远发现不了这些 API。
AI Agent 探索工作流（必须遵循）
| 步骤 | 工具 | 做什么 |
|---|---|---|
| 0. 打开浏览器 | browser_navigate |
导航到目标页面 |
| 1. 观察页面 | browser_snapshot |
观察可交互元素（按钮/标签/链接） |
| 2. 首次抓包 | browser_network_requests |
筛选 JSON API 端点，记录 URL pattern |
| 3. 模拟交互 | browser_click + browser_wait_for |
点击"字幕""评论""关注"等按钮 |
| 4. 二次抓包 | browser_network_requests |
对比步骤 2，找出新触发的 API |
| 5. 验证 API | browser_evaluate |
fetch(url, {credentials:'include'}) 测试返回结构 |
| 6. 写代码 | — | 基于确认的 API 写适配器 |
常犯错误
| ❌ 错误做法 | ✅ 正确做法 |
|---|---|
只用 opencli explore 命令，等结果自动出来 |
用浏览器工具打开页面，主动浏览 |
直接在代码里 fetch(url)，不看浏览器实际请求 |
先在浏览器中确认 API 可用，再写代码 |
| 页面打开后直接抓包，期望所有 API 都出现 | 模拟点击交互（展开评论/切换标签/加载更多） |
| 遇到 HTTP 200 但空数据就放弃 | 检查是否需要 Wbi 签名或 Cookie 鉴权 |
完全依赖 __INITIAL_STATE__ 拿所有数据 |
__INITIAL_STATE__ 只有首屏数据，深层数据要调 API |
实战成功案例：5 分钟实现「关注列表」适配器
以下是用上述工作流实际发现 Bilibili 关注列表 API 的完整过程：
1. browser_navigate → https://space.bilibili.com/{uid}/fans/follow
2. browser_network_requests → 发现:
GET /x/relation/followings?vmid={uid}&pn=1&ps=24 → [200]
GET /x/relation/stat?vmid={uid} → [200]
3. browser_evaluate → 验证 API:
fetch('/x/relation/followings?vmid=137702077&pn=1&ps=5', {credentials:'include'})
→ { code: 0, data: { total: 1342, list: [{mid, uname, sign, ...}] } }
4. 结论：标准 Cookie API，无需 Wbi 签名
5. 写 following.ts → 一次构建通过
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 · 855 lines · 83 tokens per session scan A 21fed2830fd4
qiaomu-opencli-explorer is a skill published in the GitHub repository joeseesun/qiaomu-opencli-skills (985 stars, last pushed 5mo ago), licensed MIT. It adds 83 tokens to every session and 9,699 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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-explorer
Use when creating a new OpenCLI adapter from scratch, adding support for a new website or platform, exploring a site's API endpoints via browser DevTools, or when a user asks to automatically generate a CLI for a website. Covers automated generation, API discovery workflow, authentication strategy selection, TS…
opencli-oneshot
Use when quickly generating a single OpenCLI command from a specific URL and goal description. 4-step process — open page, capture API, write TS adapter, test. For full site exploration, use opencli-explorer instead.
firecrawl-build-scrape
Integrate Firecrawl /scrape into product code for single-page extraction. Use when an app already has a URL and needs markdown, HTML, links, screenshots, metadata, or structured page output. Prefer this skill over broader crawl patterns when the feature is page-level.
gws-events
Subscribe to Google Workspace events.
gws-events-renew
Google Workspace Events: Renew/reactivate Workspace Events subscriptions.
gws-script-push
Google Apps Script: Upload local files to an Apps Script project.