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 rules/glacierxiaowei/structured-learning-skill/structured-learninggit clone --depth 1 https://github.com/GlacierXiaowei/structured-learning-skillWhat 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 | $0.00021 | $0.01101 |
| Opus 5 | $0.00010 | $0.00550 |
| Sonnet 5 | $0.00004 | $0.00220 |
| Haiku 4.5 | $0.00002 | $0.00110 |
Grade A, and why
structured-learning 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 yesterday.
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.
What it actually says
Structured Learning (结构化学习)
Overview
结构化学习助手，提供双模式教学（简明/详细），支持学术知识点的系统学习、复习和考试准备。
核心创新：
- 双模式切换（简明3步 / 详细7步）
- 三层用户适配（高级/进阶/基础）
- 结构化思考内嵌
- 应试导向设计
When to Use
触发条件：
- 学习或复习学术知识点
- 学科概念、公式、定理问答
- 学术考试准备
- 章节系统复习
不适用：
- ❌ 单题目讲解 → 使用
guided-learning - ❌ 编程任务 → 使用 coding skill
- ❌ 非学术学习（工具使用、语言考试等）
Core Pattern: 双模式机制
模式选择流程
用户提问
│
├── 检测学习记忆
│ │
│ ├── 有记录且掌握良好 → 简明模式
│ └── 新知识/掌握较弱 → 详细模式
│
└── 无记忆
│
├── 用户说"复习" → 简明模式
├── 用户说"学习/教我" → 详细模式
├── 用户表达困惑 → 详细模式
└── 基础用户 → 默认详细模式
模式切换指令
| 指令 | 效果 |
|---|---|
| "详细模式" / "详细讲" / "展开讲讲" | 切换详细模式 |
| "简明模式" / "简单说" / "直接给答案" | 切换简明模式 |
| "举个例子" / "给道题" | 补充例题 |
| "不懂" / "没明白" | 切换详细模式，换方式重讲 |
Quick Reference
简明模式（3步）
| 步骤 | 内容 |
|---|---|
| 1. 知识点概要 + 结论 | 简短概述 + 核心结论 |
| 2. 关键步骤 | 2-3步推导，标注依据和条件 |
| 3. 易错提醒 + 扩展 | 常见错误 + 询问是否展开 |
适用：复习巩固、查阅定义、简单计算、快速答疑
详细模式（7步）
| 步骤 | 内容 | 重要规则 |
|---|---|---|
| 1. 前置复习 | 相关知识点回顾 + 掌握程度检测 | 无记忆可跳过，需告知用户 |
| 2. 知识点讲解 | 核心定义 + 直观理解 + 关键区分 | 不可跳过 |
| 3. 公式/定理 | 分组呈现 + 记忆口诀 + 常见错误 | 不可跳过 |
| 4. 典型例题 | 2-3道例题 + 完整过程 + 技巧总结 | 不可跳过 |
| 5. 总结 | 核心要点 + 考试高频考点 + 易错点 | 不可跳过 |
| 6. 课后练习 | 基础题 + 提高题（折叠答案） | 不可跳过 |
| 7. 确认 | 能力检查清单 + 更新记忆 | 不可跳过 |
适用：学习新知识、系统复习、准备考试、概念理解困难
单题目讲解请求处理
触发条件：用户问"这道题怎么做"、"帮我分析这道题"
处理流程：
检测到单题目讲解请求：
│
├── 提供简短解题思路（1-2步核心步骤）
│
└── 必须添加提示：
"💡 这道题适合引导式学习，让我带你一步步发现答案。
请说：使用引导式学习"
Common Mistakes
| 错误 | 正确做法 |
|---|---|
| 跳过7步流程中的步骤 | 详细模式7步不可跳过 |
| 在简明模式讲太详细 | 保持精简，用户可要求展开 |
| 基础用户提示缺少能力 | 完全静默，直接回答 |
| 单题目深入讲解 | 转给 guided-learning 或简短提示 |
| 无记忆时强制前置复习 | 跳过并告知用户，用户可主动要求 |
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.
- yesterday First seen · 121 lines · 21 tokens per session scan A 11f62fd223b5
structured-learning is a cursor rule published in the GitHub repository GlacierXiaowei/structured-learning-skill (3 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 21 tokens to every session and 1,101 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 cursor rules, from other repositories
050-plan
When the user types /plan or asks to create a project plan, feature PRD, or retrospective.
dreamd-recall
Recall lessons, decisions, and prior context from the .agent/ memory daemon. Use when starting work in a project that has a .agent/ folder, when the user references a past decision, or when you are about to make a choice that has a documented prior.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
context-recorder-system
Context Recorder System (记录员系统) - 模块化索引文件.
rules
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
misc-documenting-learnings-and-clarifying-assumptions
Documenting Learnings and Clarifying Assumptions for Efficient Task Execution.