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/guoqiaozhou/study-with-claude-code/plannpx skills add guoqiaoZhou/study-with-claude-code --skill plangit clone --depth 1 https://github.com/guoqiaoZhou/study-with-claude-codeWrote 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/guoqiaozhou/study-with-claude-code/plan)<a href="https://agentmods.dev/skills/guoqiaozhou/study-with-claude-code/plan"><img src="https://agentmods.dev/badge/skills/guoqiaozhou/study-with-claude-code/plan.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 | $0.00068 | $0.04839 |
| Opus 5 | $0.00034 | $0.02420 |
| Sonnet 5 | $0.00014 | $0.00968 |
| Haiku 4.5 | $0.00007 | $0.00484 |
Grade A, and why
swcc-plan 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
swcc · plan — 生成 / 更新专题 roadmap 与教学教案
为一个技术专题搭建（或增量更新）roadmap 级知识树与递进式教学教案。质量标杆是「阶段 → 子主题（带核心问题 + 本章考察点）→ 可考核的叶子节点」的骨架，加上每个叶子节点「背景 → 本质问题 → 核心机制 → 进阶」的教案密度。
动手前先读三份契约:
${CLAUDE_PLUGIN_ROOT}/skills/_shared/data-contract.md—— 目录布局、节点路径 key、各文件格式、参考资料读取策略、合并/更新语义、旧格式兼容与迁移规则。${CLAUDE_PLUGIN_ROOT}/skills/_shared/review-rubric.md—— 强制评审的 4 个维度、各 level 深度校准、缺口格式。 所有数据写到$HOME/.study-with-cc/。
参数:$ARGUMENTS —— 第一个词是 topic（必填），可选 level（p6/p7/p8/p9，默认 p7），可选 --update / --regenerate。
核心原则（贯穿全程，在门控处会复述）
- 先自己想透，再看书。 永远先用自身领域知识构建完整大纲，再用参考资料锚定/补充。绝不因为挂了书就把范围缩到书的目录——书是锚点，不是天花板。
- 深度优先于条目数。 每个叶子节点都要能回答「是什么 + 为什么这样设计 + 取舍/边界」，不是列名词。宁可少而透，不要多而空。
- 质量由流程保证，不靠用户判断。 生成后必须派评审子智能体查漏补缺并据反馈补全——这是强制环节，不问用户「够不够」。
- 结构可演进，进度不可丢。 更新已存在专题时，默认增量合并，用户已学的进度一律保留。
- 不编来源。 没挂资料就老实靠自身理解，不要假称「依据某书」。
- 大文件分块写,永不一次性整文件输出。 knowledge-system.md 等大产物按 data-contract 第十二节分块追加 + TodoWrite 跟踪,否则会超时。
- roadmap 与教案分离。
knowledge-tree.md是 roadmap（骨架 + 每章核心问题/考察点），knowledge-system.md是递进式教案（背景/本质问题/核心机制/进阶）。
subagent 纪律（起草子智能体与评审子智能体共用）
plan 执行过程中会派两类子智能体：阶段 7 的起草子智能体（逐子主题生成教案文本）和阶段 8 的4 维评审子智能体。二者必须遵守以下纪律，主对话 also 默认不在 plan 执行中调用 WebSearch/WebFetch。
- 工具权限 —— 禁止联网。 subagent 严禁调用 WebSearch、WebFetch 以及任何其他联网工具；只能使用 Read 读取输入上下文中已提供的文件、Bash 进行纯本地处理、Agent 返回结果。主对话在
plan执行期间也默认不调用 WebSearch/WebFetch。 - 输入来源 —— 只读既定材料。 subagent 只能基于以下素材工作：现有 teaching plans / knowledge tree / knowledge-system.md、本轮对话历史、模型内部领域知识、用户在阶段 3 提供的参考资料路径。禁止主动检索外部网页、文档、博客、论文或在线课程。
- 输出契约。
- 起草子智能体：只返回其被分配子主题下的 markdown 教案文本（背景/本质问题/核心机制/进阶四段），不返回 frontmatter、不写文件、不输出额外说明。
- 评审子智能体：严格按
review-rubric.md第四节gaps[]JSON 结构返回缺口；除 JSON 外不要解释性文字。
- 失败回退。
- 起草子智能体失败/超时 → 由阶段 7 现有规则处理（不阻塞其他子主题，登记进 TodoWrite 后由主体补写）。
- 评审子智能体失败/超时 → 由阶段 8 现有规则处理（等待其余维度；若全部失败，本轮按空 gaps 处理并继续，摘要提示「评审暂不可用」）。
执行流程
| 阶段 | 名称 | 目的 |
|---|---|---|
| 1 | 解析参数 | 取 topic / level / 模式标记 |
| 2 | 存在性检查 & 路由 | 新建 or 更新（增量合并 / 重建） |
| 3 | 询问参考资料 | 收集 PDF/文档/目录的绝对路径 |
| 4 | 独立构建专家大纲 | 先不看书，凭领域知识列全大纲 |
| 5 | 挂载资料并锚定补充 | 用书映射/补充/纠错，标注来源 |
| 6 | 生成 roadmap（knowledge-tree.md） | 含 ## 子主题下的核心问题 + 本章考察点 + 嵌套 checkbox |
| 7 | 生成教学教案（knowledge-system.md） | 每个叶子节点按 背景/本质问题/核心机制/进阶 四段组织 |
| 8 | 强制 subagent 4 维评审 + 补全 | 并行评审 → 合并缺口 → 补全 → 循环 |
| 9 | 写 5 文件 + 自检 | 落盘并 ls 验证缺一不可 |
| 10 | 输出摘要 | 含评审补了哪些缺口 |
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 · 195 lines · 68 tokens per session scan A d847bbfce167
swcc-plan is a skill published in the GitHub repository guoqiaoZhou/study-with-claude-code (2 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 4,839 once invoked, about $0.0003 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
textbook-distillation
Turn a textbook or long-form source into a self-paced learning track: intake the material, build a chapter map, draft a lesson plan, then generate self-contained HTML lecture notes in a style the human specifies (layout, palette, emphasis), each lesson carrying worked examples, exercises, and checkpoint questions.…
researchers-historical
Researches archives, contemporary accounts, and timeline reconstruction. Use when the album subject involves historical events that need primary source verification.
Interview Prep Generator
Generate STAR stories, practice questions, and talking points from resume.
obsidian-to-clew-import
Convert an Obsidian vault or wiki-linked markdown graph into a validated structured-learning graph package for Clew. Use when the user wants to inspect a vault, preview whether it imports cleanly, preserve explicit relation markers, choose only the few import settings that matter, and produce a fail-closed package…
interview-simulator
Simulate role-specific mock interviews, score each answer, and provide concrete feedback and model responses for interview preparation.
Automation Interview Prep
Prepare for SDET and automation interviews round by round, covering coding screens, framework design, API testing tasks, scenario questions, and STAR stories built from real testing work.