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 guihai24/openskills --skill smart-fetchgit clone --depth 1 https://github.com/guihai24/openskillsWrote 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/guihai24/openskills/smart-fetch)<a href="https://agentmods.dev/skills/guihai24/openskills/smart-fetch"><img src="https://agentmods.dev/badge/skills/guihai24/openskills/smart-fetch.svg" alt="Measured on agentmods" 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 | $0.00075 | $0.00989 |
| Opus 5 | $0.00037 | $0.00495 |
| Sonnet 5 | $0.00015 | $0.00198 |
| Haiku 4.5 | $0.00007 | $0.00099 |
Grade A, and why
smart-fetch 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 7d 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.
| 1 | 推文 / X | URL 含 `x.com` 或 `twitter.com` | Jina + curl | What it actually says
smart-fetch — 智能网页抓取路由
拿到 URL，按场景自动选择最合适的工具，不试错，5 秒出结果。
路由规则（按优先级执行）
| 优先级 | 场景 | 判断条件 | 工具 |
|---|---|---|---|
| 1 | 推文 / X | URL 含 x.com 或 twitter.com |
Jina + curl |
| 2 | 文章 / 博客 / 文档 | 内容型页面（Medium、知乎、掘金、少数派、GitHub README、SubStack 等） | Jina + WebFetch |
| 3 | 关键词搜索 | 无具体 URL，需要发现信息 | WebSearch |
| 4 | 普通公开网页 | URL 已知，内容公开 | WebFetch |
| 5 | 需要原始 HTML | 需要 meta / JSON-LD / 结构化数据 | curl |
| 6 | 兜底 | 前几步返回空或错误 | curl + 浏览器 UA |
决策流程
- 拿到请求 — 明确目标：是 URL 还是关键词？要提取什么内容？
- 匹配路由 — 按上表优先级从高到低匹配场景，选第一个命中的工具
- 执行 — 调用对应工具
- 校验结果 — 返回内容是否有效？空内容 / 登录墙 / 报错 → 降级到下一个工具
- 全部失败 — 告知用户：该页面需要登录态或浏览器环境（CDP），建议使用 web-access skill
工具使用规范
Jina（首选预处理层）
将网页转为干净的 Markdown，大幅节省 token，适合正文提取。
调用方式：https://r.jina.ai/{原始完整URL}
示例：https://r.jina.ai/https://x.com/user/status/123
- 速率限制：20 RPM
- 适合：推文、文章、博客、文档、PDF
- 不适合：数据面板、商品列表、需要登录的内容
- 失败信号：返回 "Sign in" / "Log in" / 空内容 → 降级
使用 curl 调用 Jina：
curl -s "https://r.jina.ai/https://x.com/user/status/123" \
-H "Accept: text/plain" \
--max-time 30
使用 WebFetch 调用 Jina：
- url:
https://r.jina.ai/https://example.com/article - prompt: 描述要提取的内容
WebSearch
用于关键词搜索、发现信息来源。无具体 URL 时的第一选择。
WebFetch
已知 URL、内容公开时直接使用。由模型根据 prompt 提取内容，返回处理后结果。
curl
需要原始 HTML 或 Jina/WebFetch 均失败时使用。
curl -s "{URL}" \
-H "User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36" \
--max-time 30
站点经验
操作前先查 references/site-patterns.md，有命中站点则按已验证模式执行。
操作成功后，如发现新的有效模式或陷阱，主动更新 references/site-patterns.md。
边界说明
smart-fetch 覆盖零依赖的公开内容抓取。以下场景超出范围，建议使用 web-access skill：
- 需要登录态的内容（小红书、微信公众号、付费内容）
- 需要页面交互（点击、滚动、填表）
- 反爬强的平台（多次降级后仍失败）
- 需要 JS 渲染的动态页面
What ships with it
1 file 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.
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.
- 7d ago First seen · 94 lines · 75 tokens per session scan A 7a5a3194cd9d
smart-fetch is a skill published in the GitHub repository guihai24/openskills (2 stars, last pushed 2d ago), licensed MIT. It adds 75 tokens to every session and 989 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 2026-08-31.
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…