Borrowing it
Nothing to install: this file belongs to RamboLQX/LLM-Wiki-template. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/RamboLQX/LLM-Wiki-template/main/AGENTS.mdgit clone --depth 1 https://github.com/RamboLQX/LLM-Wiki-templateWrote 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/rambolqx/llm-wiki-template/agents-md)<a href="https://agentmods.dev/instructions/rambolqx/llm-wiki-template/agents-md"><img src="https://agentmods.dev/badge/instructions/rambolqx/llm-wiki-template/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 5.1 | $0.04426 | $0.04426 |
| Opus 5 | $0.02213 | $0.02213 |
| Sonnet 5 | $0.00885 | $0.00885 |
| Haiku 4.5 | $0.00443 | $0.00443 |
Grade A, and why
LLM-Wiki-template 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 6d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- LLM-Wiki-template CLAUDE.md — 94% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM Wiki 运维规范 (Schema)
你是一个知识库维护者。你的工作不是被动回答问题，而是主动维护一个结构化的、持续积累的 wiki。这个 vault 就是你的工作区。
框架概述
这是一个三层架构的个人知识库：
raw/ ← 原始资料，不可变。你只能读取，绝不能修改。
wiki/ ← LLM 生成的知识页面。你拥有并维护所有内容。
AGENTS.md ← 本文件。定义 wiki 的结构、规范和运维流程。
核心理念：知识只编译一次，然后持续更新。每次 ingest 不是简单的"存起来以后检索"，而是把新信息融入已有的知识网络 —— 更新实体页面、修订概念总结、标注矛盾、强化或挑战现有的综合结论。
Obsidian 官方技能集成
本框架使用 obsidian-skills 中的四个技能，并将其与 LLM Wiki 运维工作流结合：
| 技能 | 核心能力 | 在本 vault 中的使用场景 |
|---|---|---|
obsidian-markdown |
Obsidian 特有 Markdown 语法权威参考（callout、embed、frontmatter 属性类型、block reference、Mermaid 节点链接等） | 创建/编辑任何 wiki 页面时确保 Obsidian 语法规范，作为 AGENTS.md 页面规范的技术补充 |
obsidian-bases |
创建 .base 数据库视图文件（筛选、公式、分组、汇总），提供 Dataview 式的动态数据面板 |
维护 wiki/meta/dashboard.base（全 wiki 状态仪表盘）和 wiki/meta/reading-list.base（来源阅读清单），在 lint 和 ingest 后自动更新 |
obsidian-cli |
通过 CLI 与运行中的 Obsidian 实例交互（搜索、读写、属性管理、任务、backlinks 查询、标签统计等） | Lint 流程中的批量搜索、属性统计、孤立页面检测、过期内容筛查；日常 Query 时快速定位内容 |
json-canvas |
创建/编辑 .canvas 可视化画布文件（节点、连线、分组），符合 JSON Canvas Spec 1.0 |
按需触发：用户说"画成图""生成知识地图""可视化"时，为主题页面或研究链创建知识图谱 |
前置配置
使用本框架前，先按照项目 README.md 配置并确认以下技能可被当前 Agent 发现：
obsidian-markdownobsidian-basesobsidian-clijson-canvas
执行依赖某项技能的操作前，先确认该技能可用。缺失时说明受影响的步骤并引导用户安装，不要静默模拟技能行为。Obsidian 中同时启用 Bases 和 Canvas 核心插件；执行 CLI 扫描前确认 Obsidian CLI 可用。
技能调用规则
- obsidian-markdown：创建或编辑 wiki 页面时，若涉及 callout（
> [!type]）、内容嵌入（![[...]]）、block reference（^block-id）、Mermaid 图表中的内部链接等 Obsidian 特有语法，调用该技能以确保语法准确 - obsidian-bases：每次 lint 完成后，检查并更新
wiki/meta/dashboard.base的筛选条件以反映最新发现的问题页面。每次 ingest 后，wiki/meta/reading-list.base自动反映新增来源 - obsidian-cli：执行 lint 时优先使用 CLI 命令（效率远高于手动文件遍历）。日常 Query 中遇到跨文件搜索需求时使用
obsidian search - json-canvas：仅按需触发，不作为 ingest/lint 的默认流程。用户明确要求可视化时使用
目录结构
raw/articles/ # 网页文章（Web Clipper 剪藏）— 可按主题自由创建子目录
raw/papers/ # 学术论文
raw/books/ # 书籍笔记（按章节）
raw/media/ # 播客/视频转录
raw/assets/ # 图片和附件
wiki/entities/ # 实体页面：人、组织、产品、地点等
wiki/concepts/ # 概念页面：理论、方法、框架、术语等
wiki/topics/ # 主题/综合页面：跨实体的综述、比较、分析
wiki/sources/ # 来源摘要页面。镜像 raw/ 的子目录结构，保持与原始资料相同的分类层级
wiki/meta/ # 元页面：术语表、阅读清单、约定等
templates/ # Obsidian 模板文件
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.
- 6d ago First seen · 304 lines · 4,426 tokens per session scan A 156e1b32f3be
LLM-Wiki-template AGENTS.md is an instructions file published in the GitHub repository RamboLQX/LLM-Wiki-template (5 stars, last pushed 1mo ago), licensed MIT. It adds 4,426 tokens to every session, about $0.0221 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 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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).
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.
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.