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/koersliven/lore/lore-importnpx skills add koersliven/Lore --skill lore-importgit 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/skills/koersliven/lore/lore-import)<a href="https://agentmods.dev/skills/koersliven/lore/lore-import"><img src="https://agentmods.dev/badge/skills/koersliven/lore/lore-import.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 | $0.00015 | $0.01239 |
| Opus 5 | $0.00008 | $0.00620 |
| Sonnet 5 | $0.00003 | $0.00248 |
| Haiku 4.5 | $0.00002 | $0.00124 |
Grade A, and why
lore-import 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/import — 重型知识导入
对话知识密度有限。Lore 支持从文档、规范、手动输入导入高密度知识。
使用场景
| 场景 | 示例 |
|---|---|
| 架构设计文档 | 导入系统架构图、模块说明 |
| API 规范 | 导入接口文档、字段说明 |
| 业务规范 | 导入业务规则、流程说明 |
| 外部依赖说明 | 导入第三方系统对接文档 |
| 历史知识迁移 | 从旧文档系统迁移知识 |
使用方式
方式 1：文件导入
/import path/to/architecture.md
Agent 会：
- 读取文档内容
- 提取知识（DECISION/CONSTRAINT/ARCHITECTURE/EXTERNAL）
- 生成 increment 文件
- 标记来源为
[trigger: document]
方式 2：目录扫描
/import docs/
扫描目录下所有 .md 文件，批量导入知识。
方式 3：手动输入
/import
请输入知识内容（输入 END 结束）：
[DECISION] 订单服务使用 TDDL 分库分表
原因: 单表数据量超过 1 亿，需要水平扩展
分片键: order_id
分库数: 16
[CONSTRAINT] 订单表不能加唯一索引
原因: 并发写入场景会导致死锁
END
Agent 会解析并写入 increment。
方式 4：URL 导入
/import https://wiki.company.com/architecture
从 URL 获取内容并提取知识。
知识格式
导入的知识会标记不同的来源：
# 2026-04-24 import-architecture-doc
## Meta
- author: 文档作者 / 导入者
- timestamp: YYYY-MM-DD HH:MM:SS
- trigger: document / manual / url
- source: 文件路径 / URL
- confidence: high（文档通常经过审核）
## Decisions
...
## Constraints
...
## Architecture
...
## External Dependencies
...
文档解析规则
架构文档
识别以下模式：
- "系统架构" / "模块说明" → ARCHITECTURE
- "设计原因" / "为什么" → DECISION
- "不能" / "禁止" / "必须" → CONSTRAINT
- "依赖" / "调用" / "接口" → EXTERNAL
API 文档
识别以下模式：
- 接口定义 → ARCHITECTURE
- 字段说明 → EXTERNAL
- 限制条件 → CONSTRAINT
业务文档
识别以下模式：
- 业务规则 → CONSTRAINT
- 流程说明 → ARCHITECTURE
- 术语定义 → EXTERNAL
与对话知识的区别
| 维度 | 对话知识 | 文档知识 |
|---|---|---|
| 密度 | 低 | 高 |
| 结构 | 碎片化 | 完整 |
| 时效 | 实时 | 可能过期 |
| 验证 | 待验证 | 通常已审核 |
| 更新 | 自动 | 需重新导入 |
知识合并
文档导入的知识会与对话知识合并到同一个 snapshot：
snapshot.md
├── 对话知识（trigger: dialogue）
├── 文档知识（trigger: document）
└── 手动知识（trigger: manual）
冲突时：
- 文档知识优先级 > 对话知识（文档通常更权威）
- 标记
[CONFLICT]等待人工裁决
示例
导入架构文档
用户: /import docs/architecture.md
Agent:
正在解析 docs/architecture.md...
提取到以下知识：
- [ARCHITECTURE] 系统采用微服务架构，包含 5 个核心服务
- [DECISION] 选型 Spring Cloud 作为微服务框架
- [CONSTRAINT] 服务间调用必须走网关，禁止直连
- [EXTERNAL] 配置中心使用 Nacos
已写入 increment: 2026-04-24_import-architecture.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 · 200 lines · 15 tokens per session scan A 1e1a83f147f3
lore-import is a skill published in the GitHub repository koersliven/Lore (5 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 1,239 once invoked, about $0.0001 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 skills, from other repositories
repomix
Pack and analyze codebases into AI-friendly single files using Repomix. Use when the user wants to explore repositories, analyze code structure, find patterns, check token counts, or prepare codebase context for AI analysis. Supports both local directories and remote GitHub repositories.
skill-creator
Generate a new skill from a plain-language description — decides invocation control, arguments, and context cost, then scaffolds, validates, and tests it.
migrate-gemini
Migrate selected Gemini CLI instructions, commands, skills, hooks, and MCP configuration into this workspace with a dry run, review gates, and parity checks.
faf-expert
Expert in .faf (Foundational AI-context Format) files for persistent project context. Use when working with .faf files, project DNA, CLAUDE.md bi-sync, faf-cli commands, MCP server configuration, or AI-readiness scoring (0-100%). Updated for v2.8.0 Tool Visibility System.
avoid-ai-writing
Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Pairs with writing-voice for full voice alignment.
import
Import a self-contained NeatContext context bundle shared by another person, or reconcile a newer copy of a context already on this machine, leaving the source bundle unchanged. Use only when the user explicitly invokes this skill or asks to import a NeatContext bundle.