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-modularizenpx skills add koersliven/Lore --skill lore-modularizegit 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-modularize)<a href="https://agentmods.dev/skills/koersliven/lore/lore-modularize"><img src="https://agentmods.dev/badge/skills/koersliven/lore/lore-modularize.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 | $0.00015 | $0.01028 |
| Opus 5 | $0.00008 | $0.00514 |
| Sonnet 5 | $0.00003 | $0.00206 |
| Haiku 4.5 | $0.00002 | $0.00103 |
Grade A, and why
lore-modularize 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/modularize — Auto Module Discovery & Knowledge Partition
全自动模块发现与知识分区。不需要用户确认,代码结构即定义。
When to Trigger
/lore-evolvedetects nomodules/directory but has accumulated knowledge with file references- User explicitly invokes this skill
Purpose
扫描代码目录结构,自动识别模块边界,将现有知识按 affected_files 路径归类到对应模块。零干预,猜错了后续对话会自动修正。
Process
Step 1: Check Prerequisites
- If
.ai-context/modules/already exists → exit silently (already modular) - If
snapshot.mddoes not exist → exit silently (nothing to partition)
Step 2: Discover Modules from Code Structure
扫描项目目录结构,识别独立模块。判定标准:
一个目录包含以下任一即视为模块:
- Controller/Route/Handler 类文件
- 独立的服务入口或 API 定义
- 独立的数据模型定义
模块命名规则:
- 直接使用目录名(
src/order/→order) - 同一模块可能分散在多个子目录 → 以父目录为准
排除规则:
test/,__tests__/,spec/,fixtures/— 测试目录不是模块shared/,common/,util/,helpers/— 共享工具不是模块- 只有单文件且无入口点的目录不是模块
Step 3: Classify Knowledge by Module
读取 snapshot.md 和所有 increments,对每条知识:
- 提取
affected_files和关联文件路径 - 路径匹配:文件路径包含哪个模块目录 → 归到该模块
- 多模块匹配:涉及多个模块 → 同时归到各模块,记录交叉引用
- 零匹配:路径不匹配任何模块 → 归到全局知识
- 无法提取路径:纯业务知识 → 归到全局
Step 4: Create Module Structure
.ai-context/modules/
├── _index.md # 模块注册表
├── {{module-name}}/
│ ├── knowledge.md # 模块知识(L1+L3)
│ ├── specs/ # prescriptive 层(L0,由 /lore-spec 管理)
│ │ └── index.md # Spec 目录索引
│ ├── increments/ # 模块增量
│ ├── progress.md # 模块进度
│ └── cross-refs.md # 跨模块依赖
Step 5: Write Module Specs Index
对每个模块,创建 specs/index.md:
# Specs: {{module-name}}
> Managed by /lore-spec. Do not edit manually.
## Specs
| Spec | Type | Status | Created |
|------|------|--------|---------|
## Status Legend
- **draft**: 正在设计
- **proposed**: 已提出,待评审
- **approved**: 已批准,可以实现
- **implemented**: 已实现,知识已提取
- **superseded**: 已废弃
Step 6: Write Module Knowledge Files
对每个模块,使用 templates/module-knowledge.md 模板创建 knowledge.md:
- 从 snapshot 中提取该模块相关的知识条目
- 保持原有证据溯源(author/timestamp/confidence/source)
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 · 134 lines · 15 tokens per session scan A 0c60a8913a83
lore-modularize 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 1,028 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
trpc
Skill "trpc" from neverinfamous/memory-journal-mcp, covering trpc guidelines, 1. routers and procedures, 2. context and middleware and 3. client integration.
faf-context
Use FAF project context tools on this server — init, score, sync, discover; claim equals wire.
journal-optimizer
Guided database pruning and optimization workflows for memory-journal-mcp. Uses importance scores, relationship density, and entry metadata to identify low-value entries for safe soft-deletion. Includes dry-run previews, backup gates, and revert guidance. Use when the user says "clean up the database", "optimize…
wrap
Session-end retrospective. Produces a dated retro file, appends to a cross-session tooling journal, and reconciles NEXTSESSION.md so the next session can resume cleanly. Invoke as /wrap when ending a session, or /wrap -q for the local repo work only (NEXTSESSION.md + CLAUDE.md, no retro or journal).
personal-context
Interview the user to build or update a reusable "about me" context file for AI tools — who they are, their role and background, how they work, and how they want AI to help. Use when the user says "build my personal context", "create my about-me context", "set up my AI context", "update my personal context", or wants…
refresh-context
Review and refresh an existing personal-context.md or company-context.md — check what has gone stale, fill gaps against the current template, and update the file. Use when the user says "refresh my context", "review my context", "is my context still up to date", "my context is stale", or after a change in role, offer…