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 skills/lululu811/init-knowledge-base/ingestnpx skills add lululu811/init-knowledge-base --skill ingestgit clone --depth 1 https://github.com/lululu811/init-knowledge-baseWrote 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/lululu811/init-knowledge-base/ingest)<a href="https://agentmods.dev/skills/lululu811/init-knowledge-base/ingest"><img src="https://agentmods.dev/badge/skills/lululu811/init-knowledge-base/ingest.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 | $0.00092 | $0.02837 |
| Opus 5 | $0.00046 | $0.01418 |
| Sonnet 5 | $0.00018 | $0.00567 |
| Haiku 4.5 | $0.00009 | $0.00284 |
Grade A, and why
ingest 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 5d 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 — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ingest 技能
核心工作流:Inbox & Archive
你正在维护一个 LLM Wiki(Obsidian 知识库)。raw/ 目录是"待处理收件箱",wiki/ 是"编译输出层"。
目录结构约定:
raw/01-articles/— 网页剪藏的 Markdown 文章raw/02-papers/— 论文和 PDF 文献raw/03-transcripts/— 视频转录文案raw/04-meeting_notes/— 会议/课堂笔记raw/09-archive/— 已处理文件的归档目录,禁止读取wiki/sources/— 资料摘要wiki/entities/— 实体(人物、公司、工具、产品)wiki/concepts/— 概念(框架、方法论、理论)wiki/syntheses/— 综合分析报告
状态追踪机制(增量 Ingest)
系统通过 .claude/ingest-state.json 追踪处理状态,避免重复编译:
{
"version": 1,
"last_full_scan": "2026-05-01T10:00:00",
"files": {
"raw/01-articles/xxx.md": {
"hash": "a3f2c1d4",
"status": "archived",
"ingested_at": "2026-05-01T10:30:00",
"outputs": [
"wiki/sources/摘要-xxx.md",
"wiki/concepts/YYY.md",
"wiki/entities/ZZZ.md"
]
}
}
}
状态规则
| 状态 | 含义 | 处理方式 |
|---|---|---|
pending |
从未处理过 | 完整编译 |
modified |
文件内容有变更(哈希不同) | 重新编译,更新关联页面 |
archived |
已处理且源文件未变更 | 跳过 |
failed |
上次处理失败 | 重新尝试 |
哈希计算
对文件内容计算简单哈希(如 MD5 或 SHA-256),用于检测变更。
触发逻辑
- 用户执行
/ingest:扫描raw/所有子目录(排除09-archive/),找出待处理文件。 - 用户执行
/ingest <path>:仅处理指定文件。 - 用户执行
/ingest <url>:URL 摄入模式(见下方"URL 摄入"章节)。 - 隐式触发:用户说"把这个资料摄入知识库"、"导入这篇文章"时,自动执行 ingest。
URL 摄入模式
当 /ingest 的参数以 http:// 或 https:// 开头时,触发 URL 摄入流程:
步骤 0:网页抓取与存储
- 抓取网页内容:使用 WebFetch 或等效工具获取 URL 指向的页面内容,提取正文文本
- 转换为 Markdown:将 HTML 内容转换为 Markdown 格式,保留标题层级、链接、图片引用
- 生成本地文件名:从 URL 提取域名和页面标题,生成 kebab-case 文件名
- 格式:
{域名}-{页面slug}.md - 示例:
https://example.com/article/transformer-explained→example-com-transformer-explained.md
- 格式:
- 存储到 raw/:将转换后的 Markdown 保存到
raw/01-articles/目录 - 在文件头部添加元信息:
--- source_url: <原始URL> fetched_at: YYYY-MM-DDTHH:MM:SS --- # <页面标题> <正文内容> - 进入正常编译流水线:从步骤 1 开始处理该文件
注意:URL 摄入模式下,步骤 7(归档)仍然执行,源文件移动到
raw/09-archive/。 如果抓取失败(网络错误、页面不存在),向用户报告失败原因,不创建任何文件。
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.
- 5d ago First seen · 295 lines · 92 tokens per session scan A 74654c103624
ingest is a skill published in the GitHub repository lululu811/init-knowledge-base (23 stars, last pushed 21d ago), licensed MIT. It adds 92 tokens to every session and 2,837 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 2026-08-30.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
baoyu-youtube-transcript
Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面"…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
gog-slides
Google Slides operations through gog.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…