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 instructions/lululu811/init-knowledge-base/agents-mdgit 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/instructions/lululu811/init-knowledge-base/agents-md)<a href="https://agentmods.dev/instructions/lululu811/init-knowledge-base/agents-md"><img src="https://agentmods.dev/badge/instructions/lululu811/init-knowledge-base/agents-md.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 | $0.04036 | $0.04036 |
| Opus 5 | $0.02018 | $0.02018 |
| Sonnet 5 | $0.00807 | $0.00807 |
| Haiku 4.5 | $0.00404 | $0.00404 |
Grade A, and why
init-knowledge-base AGENTS.md 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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — init-knowledge-base
本文件供 AI Coding Agent 阅读。项目语言为简体中文。
项目概述
init-knowledge-base 是一个 Kimi Code CLI Project Skill,用于一键初始化标准化的 Obsidian 知识库(Vault)项目骨架。
- 灵感来源:Andrej Karpathy 的 LLM Wiki 规范
- 核心理念:将碎片化信息编译成结构化、高度相互链接的知识网络
- 使用场景:用户在 Kimi Code CLI 中输入
/init-vault <名称>或自然语言"新建知识库"时,Skill 将_templates/下的所有模板文件复制到目标目录,生成完整的 Obsidian Vault 结构
注意:本项目本身不是传统软件项目,没有 package.json、pyproject.toml、Cargo.toml 等构建配置文件,也没有编译或打包步骤。它是一个纯模板与配置仓库,依赖 Markdown、CSS、JSON 和 Kimi Code CLI 的 Skill 系统运行。
技术栈与运行时架构
| 层级 | 技术 | 说明 |
|---|---|---|
| AI 运行时 | Kimi Code CLI | Skill 的加载与执行环境 |
| 知识库客户端 | Obsidian(桌面端) | 用户主要的阅读与编辑界面 |
| 数据查询 | Dataview(Obsidian 社区插件) | wiki/index.md 动态仪表盘依赖此插件 |
| 模板引擎 | Templater(Obsidian 社区插件) | templates/ 目录下的 4 个模板由其解析 |
| 样式 | CSS Snippets | .obsidian/snippets/ 下的 3 个 CSS 文件 |
| 版本控制 | Git | 仅追踪配置与内容,排除插件二进制文件 |
运行时架构
用户通过 Kimi Code CLI 触发 /init-vault
↓
CLI 读取本项目的 SKILL.md
↓
按 SKILL.md 定义的"生成流水线",将 _templates/ 复制到用户指定目录
↓
生成的 Vault 包含:Obsidian 配置 + CSS 样式 + 模板 + 5 个 Agent Skills
↓
用户在 Obsidian 中打开 Vault,使用 /ingest、/query、/lint、/canvas 命令与 AI 交互
目录结构与模块划分
项目根目录/
├── SKILL.md # Skill 定义与生成流水线(Kimi Code CLI 入口)
├── README.md # 面向人类用户的项目说明
├── LICENSE # MIT 许可证
├── AGENTS.md # 本文件
└── _templates/ # 所有模板文件,初始化时复制到目标项目
├── README.md # 生成的 Vault 的 README(含 {vault_name} 占位符)
├── CLAUDE.md # Agent 行为契约与规范(原样复制)
├── OBSIDIAN_SETUP.md # Obsidian 配置指南(原样复制)
├── .gitignore # 忽略规则(原样复制)
├── .obsidian/ # Obsidian 统一配置
│ ├── app.json # 编辑器设置(新文件位置、附件路径、显示选项等)
│ ├── appearance.json # 外观 + 启用的 CSS 片段清单
│ ├── core-plugins.json # 核心插件开关列表
│ ├── community-plugins.json # 推荐社区插件列表(dataview, templater 等)
│ └── snippets/ # CSS 样式片段
│ ├── wiki-reading.css # 阅读排版优化
│ ├── wiki-callouts.css # Callout 语义化颜色 + 左侧边条
│ └── wiki-components.css # 双链、外部链接、标签、图片、代码块增强
├── templates/ # Templater 模板文件夹
│ ├── entity.md # 实体模板(人物、公司、工具、产品)
│ ├── concept.md # 概念模板(框架、方法论)
│ ├── source.md # 来源摘要模板
│ └── synthesis.md # 综合分析模板
├── wiki/ # 知识编译输出层骨架
│ ├── index.md # Dataview 动态仪表盘(全局内容字典)
│ ├── log.md # 操作日志(Append-only)
│ └── mocs/ # 主题地图(Map of Contents)
│ ├── README.md # MOC 创建指南与 Dataview 查询模板
│ ├── MOC-技术.md # 技术领域 MOC
│ ├── MOC-商业.md # 商业领域 MOC
│ ├── MOC-人物.md # 人物与机构 MOC
│ └── MOC-待整理.md # 草稿与待分类 MOC
└── .claude/ # Agent Skills
└── skills/
├── ingest/SKILL.md # 将 raw/ 资料编译到 wiki/
├── query/SKILL.md # 在知识库中搜索与回答
├── lint/SKILL.md # 检查死链、孤儿页面、逻辑冲突
├── obsidian-markdown/SKILL.md # Obsidian Markdown 语法规范
└── json-canvas/SKILL.md # Canvas 可视化与知识图谱
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 · 290 lines · 4,036 tokens per session scan A 18606988b5f2
init-knowledge-base AGENTS.md is an instructions file published in the GitHub repository lululu811/init-knowledge-base (23 stars, last pushed 19d ago), licensed MIT. It adds 4,036 tokens to every session, about $0.0202 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 instructions, from other repositories
google-automation-mcp GEMINI.md
Instructions for sam-ent/google-automation-mcp, covering apps script mcp, available tools, authentication, bound scripts and triggers.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).