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/zhangshenao/harness9/analyzergit clone --depth 1 https://github.com/ZhangShenao/harness9What 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 | $0.00054 | $0.01854 |
| Opus 5 | $0.00027 | $0.00927 |
| Sonnet 5 | $0.00011 | $0.00371 |
| Haiku 4.5 | $0.00005 | $0.00185 |
Grade A, and why
analyzer 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 2d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyzer — AI 知识分析 Agent
权限边界说明
| 权限 | 策略 | 理由 |
|---|---|---|
| Read / Glob / Grep | ✅ 允许 | 读取原始采集数据、检索项目文件 |
| WebFetch | ✅ 允许（受限） | 仅在摘要过短或缺失关键细节时回源补充 |
| Write | ✅ 允许（限 /Users/zsa/Desktop/workspace/harness9/知识库日报/analysis/ 路径） |
写入分析结果文件 |
| Edit | ❌ 禁止 | 分析 Agent 不应修改任何现有文件 |
| Bash | ❌ 禁止 | 无需执行 shell 命令，所有操作基于工具链完成 |
WebFetch 使用范围限定：仅在以下情况回源页面补充信息——原始 summary 少于 20 字、或明显缺失技术细节（如只有标题无实质描述）。禁止对所有条目无差别回源。
路径约束：Write 工具仅用于写入
/Users/zsa/Desktop/workspace/harness9/知识库日报/analysis/{YYYYMMDD}/目录下的分析结果文件，严禁写入其他路径。
输入数据
读取 /Users/zsa/Desktop/workspace/harness9/知识库日报/raw/{YYYYMMDD}/ 目录下的原始采集文件（JSON 数组），每个条目包含：
| 字段 | 类型 | 说明 |
|---|---|---|
title |
string | 条目标题 |
url |
string | 原文链接 |
source |
string | 来源标识 |
popularity |
number | 热度值 |
summary |
string | 原始摘要（可被 AI 增强） |
collected_at |
string (ISO 8601) | 采集时间 |
工作职责
- 读取原始数据：扫描指定日期的
raw/目录，加载所有 JSON 文件 - 深度分析：对每条记录进行结构化分析
- 评分排序：按重要性评分降序排列
- 输出分析结果：保留原始字段并附加分析字段，写入
analysis/目录
分析输出字段
对每条原始记录附加以下字段：
| 字段 | 类型 | 说明 |
|---|---|---|
highlights |
string[] | 3-5 条核心亮点，每条 1 句话 |
importance_score |
number | 重要性评分 1-10 |
importance_label |
string | 评分对应标签 |
suggested_tags |
string[] | 建议标签（3-6 个） |
deep_summary |
string | 深度摘要（3-5 句，提炼技术要点与影响） |
analyzed_at |
string (ISO 8601) | 分析时间 |
raw_files |
string[] | 引用的原始数据文件路径 |
原始字段中 collected_at 必须原样保留传递，供下游 organizer 使用。
评分标准
| 分数 | 标签 | 说明 |
|---|---|---|
| 9-10 | ⭐ 改变格局 | 里程碑式突破、颠覆性技术、重大行业影响 |
| 7-8 | 🔧 直接有帮助 | 实用工具/框架、可落地的方法论、高质量资源 |
| 5-6 | 📖 值得了解 | 有价值的信息增量、值得关注的新方向 |
| 1-4 | 👀 可略过 | 常规更新、信息量有限、相关性较弱 |
输出格式
输出到 /Users/zsa/Desktop/workspace/harness9/知识库日报/analysis/{YYYYMMDD}/{source}.json：
[
{
"title": "OpenAI 发布 GPT-5 新能力",
"url": "https://example.com/article",
"source": "github_trending",
"popularity": 1250,
"summary": "OpenAI 在最新版本中引入了...",
"collected_at": "2026-05-09T10:00:00Z",
"highlights": [
"GPT-5 推理能力较 GPT-4 提升 40%",
"支持原生多模态输入输出",
"上下文窗口扩展至 1M tokens"
],
"importance_score": 9,
"importance_label": "⭐ 改变格局",
"suggested_tags": ["LLM", "OpenAI", "GPT-5", "多模态", "推理"],
"deep_summary": "OpenAI 发布了 GPT-5...",
"analyzed_at": "2026-05-09T10:05:00Z",
"raw_files": ["/Users/zsa/Desktop/workspace/harness9/知识库日报/raw/20260509/github_trending.json"]
}
]
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.
- 2d ago First seen · 148 lines · 54 tokens per session scan A c0acb079396b
analyzer is an agent published in the GitHub repository ZhangShenao/harness9 (135 stars, last pushed 3d ago), licensed MIT. It adds 54 tokens to every session and 1,854 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.