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 redfox-data/redfox-community-dsh --skill xiaohongshu-crawlergit clone --depth 1 https://github.com/redfox-data/redfox-community-dshWrote 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/redfox-data/redfox-community-dsh/xiaohongshu-crawler)<a href="https://agentmods.dev/skills/redfox-data/redfox-community-dsh/xiaohongshu-crawler"><img src="https://agentmods.dev/badge/skills/redfox-data/redfox-community-dsh/xiaohongshu-crawler/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/redfox-data/redfox-community-dsh/xiaohongshu-crawler"><img src="https://agentmods.dev/badge/skills/redfox-data/redfox-community-dsh/xiaohongshu-crawler.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 | $0.00108 | $0.03085 |
| Opus 5 | $0.00054 | $0.01543 |
| Sonnet 5 | $0.00022 | $0.00617 |
| Haiku 4.5 | $0.00011 | $0.00309 |
Grade A, and why
xiaohongshu-crawler 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 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.
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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
小红书作品爬取
📝 简介
根据关键词爬取小红书热门作品，支持按日期范围筛选和多种排序方式（相关性、最新、最热），返回笔记标题、作者、互动数据等，结果以结构化表格展示。
✨ 功能特性
| 功能模块 | 能力描述 | 核心价值 |
|---|---|---|
| 作品爬取 | 关键词搜索小红书作品 | 精准发现高热度内容 |
| 日期筛选 | 支持按日期范围筛选 | 定位特定时间段的热门内容 |
| 多种排序 | 相关性/最新/最热三种排序 | 灵活满足不同筛选需求 |
| 互动数据 | 返回收藏、分享、评论、点赞等 | 全面评估作品热度 |
| 报告导出 | CSV（Excel兼容）+ HTML可视化报告 | 本地离线查看与分享 |
🔑 鉴权
- 获取 API Key：前往 红狐hub
- 配置方式1：写入
~/.openclaw/openclaw.json→{ "env": { "REDFOX_API_KEY": "ak_xxxx..." } } - 配置方式2：终端执行
export REDFOX_API_KEY="ak_xxxx..."
⚙️ 工作流程
Step 1: 🔍 用户意图理解
从用户输入中提取以下参数：
| 参数 | 提取规则 | 默认值 |
|---|---|---|
| keyword | 用户提到的搜索关键词 | 空字符串 "" |
| startDate | 起始日期，解析为 YYYY-MM-DD |
30天前（脚本自动计算） |
| endDate | 结束日期，解析为 YYYY-MM-DD |
今天（脚本自动计算） |
| sortType | 排序方式，见下表 | "_0" |
sortType 枚举：
| 值 | 含义 | 触发词 |
|---|---|---|
_0 |
相关性排序（默认） | 默认排序、综合排序、相关 |
_2 |
最新（按发布时间排序） | 最新、 newest、按时间 |
_4 |
最热（按互动数排序） | 最热、最火、hottest、按热度 |
时间解析规则：
| 用户输入 | 解析方式 | 示例 |
|---|---|---|
| 绝对日期 | 解析为 YYYY-MM-DD |
6月1号 → 2026-06-01 |
| 相对日期 | 基于当前日期计算 | 最近7天 → start=7天前, end=今天 |
| 日期范围 | 分别解析为 startDate/endDate | 5月30日到6月2日 |
| 未提供时间 | 不传 --start-date/--end-date，脚本默认查最近30天 |
不传参数 |
Step 1.5: 🧠 关键词类型判断（⚠️ 调用脚本前必须执行）
核心规则：泛化词必须先询问再查询，具体词直接查询。
关键词分类：
| 类型 | 特征 | 处理方式 |
|---|---|---|
| 空关键词 | 用户未提供关键词（如「最近热门笔记」） | 直接查询全站热门，keyword 传 "" |
| 细分词 | 含具体场景/属性/人群修饰（如「减脂餐」「小个子穿搭」「生酮饮食」） | 直接调用脚本 |
| 泛化词 | 纯大类词，无修饰成分（如「美食」「穿搭」「美妆」） | 必须先推荐细分词，等待用户回复后再查询 |
泛化词处理流程（⚠️ 禁止直接调用脚本！）：
第一步：生成 10 个细分词推荐
生成原则：
- 词的大小适中，避免过细（查不到数据）或过泛
- 必须覆盖不同场景：趋势词、人群词、场景词、意图词各 2-3 个
输出示例：
我识别到「美食」是较大的分类，推荐以下细分方向： 家常菜、烘焙甜点、减脂餐、早餐、宵夜、地方菜系、懒人食谱、宝宝辅食、火锅、咖啡饮品 回复「拓展」将同时搜索这 10 个词，回复「不拓展」将继续搜索「美食」
第二步：等待用户回复（禁止在同一次对话中继续执行脚本）
- 用户回复「拓展」 → 调用脚本搜索 10 个细分词（逗号分隔）
- 用户回复「不拓展」 → 调用脚本搜索原关键词
Step 2: 📡 调用脚本
# 基础调用（仅关键词，日期默认最近30天，排序默认相关性）
python3 ~/.qoderwork/skills/xiaohongshu-crawler/scripts/crawl_xhs.py "<关键词>"
# 完整参数（仅传入非空的时间/排序参数）
python3 ~/.qoderwork/skills/xiaohongshu-crawler/scripts/crawl_xhs.py "<关键词>" --start-date <startDate> --end-date <endDate> --sort-type <_0|_2|_4>
What ships with it
5 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.
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 · 238 lines · 108 tokens per session scan A a7d005a7cf22
xiaohongshu-crawler is a skill published in the GitHub repository redfox-data/redfox-community-dsh (5 stars, last pushed today), licensed MIT. It adds 108 tokens to every session and 3,085 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
dsh-hooks-authoring
Instructions for writing and debugging dsh-hooks-plugin scripts, which run during tool or session events such as before a tool call or after it finishes. These scripts return JSON decisions such as allowing, asking about, or denying an action.
web-artifact-designer
A design workflow for producing self-contained HTML or SVG files that open directly in a browser. It covers visual work such as posters, infographics, landing pages, charts, banners, cards, and interface mockups.
dsh-web-pet-developer
Create a pet for the dsh-pet plugin and integrate it into the dsh web GUI — author a v2 pet.json manifest plus an 8-column x 9-row atlas per the Codex/hatch-pet contract (live2d pets, voice packs and status decorations included), drop it into the pet-center user directory or contribute it as a built-in asset under…
company-research-method
A documented process for researching a company using supplied files and selected public sources. It produces a company overview with business details, sourced financial figures, and stated risks.
dsh-plugin-guide
Use when developing, reviewing, packaging, debugging, or answering questions about DeepSeek Harness (DSH) plugins — the plugin-based agent harness on vendored Cordis. Applies the official plugin-development constraints (plugin contract, cordis.yml layers, services/events/effects, tool DSL, bundles/profiles) backed by…
delivery-proof
Delivery proof and the doublecheck report. Use when the work is done and the delivery must be proven — consolidate the spec, test timeline, review verdicts, and verification checks into a doublecheckreport, and only then claim completion.