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/koersliven/lore/claude-mdgit clone --depth 1 https://github.com/koersliven/LoreWrote 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/koersliven/lore/claude-md)<a href="https://agentmods.dev/instructions/koersliven/lore/claude-md"><img src="https://agentmods.dev/badge/instructions/koersliven/lore/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 | $0.01825 | $0.01825 |
| Opus 5 | $0.00912 | $0.00912 |
| Sonnet 5 | $0.00365 | $0.00365 |
| Haiku 4.5 | $0.00183 | $0.00183 |
Grade A, and why
Lore 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 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 — 188 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 code in this repository.
Project Overview
Lore — 管理代码中的 WHY。让隐性知识随代码一起传承的开源框架。
核心思想：知识通过 git 传播，和代码享受同等待遇。
AI Context 自动积累规则
This section is injected by Lore. It instructs the agent to automatically buffer knowledge during development and flush on trigger.
核心原则
记录代码本身无法告诉你的知识。
代码告诉你 HOW，但不知道：
- WHY — 为什么这样设计
- WHERE — 配置在哪里、谁在管
- WHICH — 多条路径选哪条
- FLOW — 端到端流程是什么
- WHO — 谁在用、谁在维护
知识识别规则（主动识别）
每次回复结束后，主动扫描对话内容，识别以下知识：
1. 外部依赖知识
触发信号：对话中提到外部系统、平台、服务
| 提到 | 应记录为 |
|---|---|
| Diamond / Nacos / Apollo | [EXTERNAL] 配置中心，控制 X 行为 |
| Tair / Redis / Memcached | [ARCHITECTURE] 缓存层，存储 X 数据 |
| HSF / Dubbo / gRPC | [ARCHITECTURE] RPC 调用，依赖 X 服务 |
| MetaQ / Kafka / RocketMQ | [ARCHITECTURE] 消息队列，X 流程解耦 |
| TDDL / ShardingSphere | [ARCHITECTURE] 分库分表，规则是 X |
| 外部 JAR / SDK | [EXTERNAL] 提供 X 能力，字段含义是 Y |
2. 配置来源知识
触发信号：对话中提到配置、开关、参数
| 提到 | 应记录为 |
|---|---|
| "这个配置在..." | [EXTERNAL] 配置位置和含义 |
| "改了这个会..." | [CONSTRAINT] 配置变更影响 |
| "这个开关控制..." | [DECISION] 开关设计原因 |
3. 数据流向知识
触发信号：对话中提到数据、存储、流转
| 提到 | 应记录为 |
|---|---|
| "数据在...里" | [ARCHITECTURE] 数据存储位置 |
| "这个表..." | [ARCHITECTURE] 表结构/分片规则 |
| "数据从...来" | [ARCHITECTURE] 数据流向 |
4. 业务概念知识
触发信号：对话中提到业务术语、规则、场景
| 提到 | 应记录为 |
|---|---|
| "这个业务是..." | [ARCHITECTURE] 业务场景描述 |
| "状态流转是..." | [ARCHITECTURE] 状态机/流程 |
| "规则是..." | [CONSTRAINT] 业务规则 |
5. 架构边界知识
触发信号：对话中提到服务、模块、调用关系
| 提到 | 应记录为 |
|---|---|
| "这个服务调用..." | [ARCHITECTURE] 服务依赖关系 |
| "这个模块负责..." | [ARCHITECTURE] 模块职责 |
| "不能直接调用..." | [CONSTRAINT] 架构约束 |
6. 决策原因知识
触发信号：对话中解释为什么
| 提到 | 应记录为 |
|---|---|
| "为什么选..." | [DECISION] 技术选型原因 |
| "这样设计是因为..." | [DECISION] 设计原因 |
| "之前出过..." | [CONSTRAINT] 历史事故约束 |
不记录什么
以下内容不需要记录，因为代码 diff 已经表达：
- 变量重命名、格式调整
- 纯粹的 bug fix（除非涉及架构）
- 明显的代码逻辑（函数名已说明）
- 临时调试代码
写入格式
识别到知识后，追加写入 .ai-context/buffer.md：
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 · 188 lines · 1,825 tokens per session scan A c77927c193e0
Lore CLAUDE.md is an instructions file published in the GitHub repository koersliven/Lore (5 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 1,825 tokens to every session, about $0.0091 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
cognirepo CLAUDE.md
Claude Code instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
aeon CLAUDE.md
Claude Code 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.
memory-mcp-1file AGENTS.md
Instructions for pomazanbohdan/memory-mcp-1file, covering ⛔ l0 invariants (never violate under any circumstance), detection heuristic, 🔀 phase transition routing (⛔ blocking), gate-0: phase identification & loading and 🧾 proof-of-load requirement (critical).