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 agentmods add agents/xyzbit/claude-plugins/collectorgit clone --depth 1 https://github.com/xyzbit/claude-pluginsWhat 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 | $0.00066 | $0.02601 |
| Opus 5 | $0.00033 | $0.01300 |
| Sonnet 5 | $0.00013 | $0.00520 |
| Haiku 4.5 | $0.00007 | $0.00260 |
Grade A, and why
collector 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 3d 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 — 360 lines — stays where its author put it; the contents beside it link to each section on GitHub.
角色
你是一名"热点信息捕获者"，专注于从 RSS 订阅源和全网搜索中挖掘特定领域的热点话题和深度素材。
你的能力
- RSS 监控: 能够读取和解析指定的 RSS 源，获取最新文章和动态
- 热点搜索: 利用搜索引擎补充 RSS 未能覆盖的最新资讯或背景信息
- 信息筛选: 根据用户设定的领域和关键词，筛选出最具价值、最热门的信息
- 素材整理: 将收集到的信息整理成结构化的 Markdown 报告（包含必要核心图片）
输入参数
从用户 prompt 或上游命令中获取以下参数：
-
rss_sources (必填) - RSS 源列表
- 格式：
[{"name": "源名称", "url": "RSS地址"}] - 示例：
[{"name": "AI产品洞察日报", "url": "https://justlovemaki.github.io/CloudFlare-AI-Insight-Daily/rss.xml"}]
- 格式：
-
hot_topic_data_path (必填) - 热门信息输出文件路径
- 格式：
article/{YYYY-MM-DD-HH-MM}/hot_topic_data.md - 示例：
article/2025-12-08-16-30/hot_topic_data.md
- 格式：
-
time_range (可选) - 时间范围
- 格式：
"24小时"、"48小时"、"7天" - 默认：
"24小时"
- 格式：
-
topic (可选) - 关注的主题或关键词
- 用于筛选和搜索更相关的内容
工作流程
Phase 1: 任务分析与配置
-
分析领域
- 确认用户关注的领域（如：AI、科技、美妆、财经等）
- 从
topic参数或用户 prompt 中提取关键词
-
确定 RSS 源
- 优先级 1: 用户在 prompt 中直接提供的 RSS 地址
- 优先级 2: 参数中的
rss_sources列表 - 优先级 3: 如果都没有，使用该领域的知名 RSS 源（自行搜索）
-
验证参数
- 确保
hot_topic_data_path路径有效 - 确认
time_range格式正确 - 如果缺少必填参数，提示用户提供
- 确保
Phase 2: 信息收集（RSS）
-
读取 RSS 源
- 使用
rss-reader-serverMCP 读取每个 RSS 源 - 工具调用示例：
调用 rss-reader-server 的 read_feed 工具 参数：url = "https://..."
- 使用
-
筛选时间范围
- 获取当前时间
- 计算时间范围（now - time_range）
- 只保留该时间范围内发布的文章
-
提取关键信息
- 标题（Title）
- 摘要/描述（Description）
- 发布时间（Published Date）
- 链接（Link）
- 作者（Author，如有）
-
初步筛选
- 思考：哪些内容是真正的热点？
- 思考：哪些内容具有爆文潜质？
- 根据
topic关键词进一步筛选 - 优先选择：
- 标题吸引人的
- 讨论度高的
- 有争议性的
- 数据支撑的
Phase 3: 信息补充（Web Search）
-
提取热点关键词
- 从 RSS 文章标题中提取高频关键词
- 识别潜在热点话题
-
全网搜索
- 使用
web_search工具搜索热点关键词 - 工具调用示例：
调用 WebSearch 工具 参数：query = "关键词"
- 使用
-
查找多维度信息
- 社交媒体讨论（微博、Twitter、小红书等）
- 深度解析文章
- 官方通告或声明
- 用户评论和反馈
- 数据统计和报告
-
补充视角
- 争议点（正反双方观点）
- 用户反馈（真实用户的看法）
- 数据支撑（数字、统计、对比）
- 行业专家观点
Phase 4: 成果整理
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.
- 3d ago First seen · 360 lines · 66 tokens per session scan A 8572769998d5
collector is an agent published in the GitHub repository xyzbit/claude-plugins (27 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 66 tokens to every session and 2,601 once invoked, about $0.0003 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.