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/gatelynch/llm-knowledge-base/claude-mdgit clone --depth 1 https://github.com/gatelynch/llm-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/gatelynch/llm-knowledge-base/claude-md)<a href="https://agentmods.dev/instructions/gatelynch/llm-knowledge-base/claude-md"><img src="https://agentmods.dev/badge/instructions/gatelynch/llm-knowledge-base/claude-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 | $0.02283 | $0.02283 |
| Opus 5 | $0.01141 | $0.01141 |
| Sonnet 5 | $0.00457 | $0.00457 |
| Haiku 4.5 | $0.00228 | $0.00228 |
Grade A, and why
llm-knowledge-base CLAUDE.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 4d 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with this repository.
關於使用者
[YOUR_BIO — 用 1-2 句話描述你是誰、你關心什麼]
互動原則
- 使用 [YOUR_LANGUAGE] 跟我對話，請叫我「[YOUR_NAME]」
- 第一性原理：從最根本的角度分析問題，不預設答案
- 提問優先：需求不夠清楚時，主動提問直到沒有疑問，才開始執行
- 直接指出錯誤：尊重事實比照顧感受重要。使用者犯錯時立刻說明，不因感受迴避，這是強硬規則
- 在對任務採取行動之前先告訴我你的計畫。等我允許之後才開始執行
寫作風格
Vault 概覽
這是一個個人知識管理 Vault，內容以 [YOUR_DOMAIN] 為核心，以 Obsidian 管理，內容以 [YOUR_LANGUAGE] 為主。
最後設置日期：[DATE]
知識庫架構（raw / wiki / brainstorming / artifacts）
基於 Karpathy 的 LLM Knowledge Base 工作流，把原始資料、編譯產物、思考探索、成品四層分開。
vault/
├── raw/ # 原始資料，只進不改（不管誰寫的，未經編譯加工）
│ ├── articles/ # 文章剪藏（origin: external）
│ ├── books/ # 書籍筆記（origin: external）
│ ├── podcasts/ # 播客轉錄（origin: external）
│ ├── papers/ # 學術論文（origin: external）
│ ├── notes/ # 隨手靈感筆記（origin: self）
│ │ └── social/ # 社群平台匯入（facebook/ 等，origin: self）
│ └── projects/ # 專案相關原始資料（origin: self）
│
├── wiki/ # 編譯產物，由 LLM 維護，不手動改
│ ├── indexes/ # All-Sources.md, All-Concepts.md
│ ├── concepts/ # 概念條目（交叉引用）
│ ├── summaries/ # 逐篇摘要
│ └── log.md # 操作紀錄（compile、query、health-check）
│
├── brainstorming/ # 思考與探索
│ ├── chat/ # 問答沉澱（每次複雜提問的結果）
│ └── health/ # /health-check 產出的知識庫品質報告
│
├── artifacts/ # 個人成品與對外產出（origin: self）
│ └── projects/ # 進行中的專案
│ # 依領域自訂子資料夾，如：文章/、教學記錄/、書稿/、簡報/ 等
│
└── attachments/ # 圖片、PDF 等附件
編譯規範
摘要結構（wiki/summaries/）
外部來源（raw/ → wiki/summaries/）
---
origin: external
source: "[[YYYYMMDD 標題]]"
compiled: YYYY-MM-DD
tags: [標籤1, 標籤2]
---
# 核心結論
# 關鍵證據
# 疑點
# 術語
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.
- 4d ago First seen · 223 lines · 2,283 tokens per session scan A 266205eb4eda
llm-knowledge-base CLAUDE.md is an instructions file published in the GitHub repository gatelynch/llm-knowledge-base (328 stars, last pushed 5mo ago), licensed MIT. It adds 2,283 tokens to every session, about $0.0114 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
vespertide AGENTS.md
AGENTS.md instructions for dev-five-git/vespertide, covering vespertide knowledge base, structure, where to look, data flow and conventions.
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.