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/deepnpx skills add guoqiaoZhou/study-with-claude-code --skill deepgit 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/deep)<a href="https://agentmods.dev/skills/guoqiaozhou/study-with-claude-code/deep"><img src="https://agentmods.dev/badge/skills/guoqiaozhou/study-with-claude-code/deep.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 | $0.00073 | $0.01069 |
| Opus 5 | $0.00036 | $0.00535 |
| Sonnet 5 | $0.00015 | $0.00214 |
| Haiku 4.5 | $0.00007 | $0.00107 |
Grade A, and why
swcc-deep 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.
What it actually says
swcc · deep — 概念深挖拓展
把一个概念横向拓宽:跨领域连接、类比、技术对比、延伸问题。这是"拓宽 + 沉淀",不是测试,不影响掌握度。
开始前先读数据契约:
${CLAUDE_PLUGIN_ROOT}/skills/_shared/data-contract.md(参考资料读取、deep-notes 目录)。本技能只新增deep-notes/笔记,不改 progress/tree。
参数:$ARGUMENTS —— topic(默认 activeTopic)+ concept(要深挖的概念,必填)。没给 concept 就问用户要挖哪个。
核心原则
- 拓宽,不考核。 目的是打开视野、建立联系,不打分、不记薄弱点、不动 progress。
- 可选联网,但离线可用是底线。 默认尝试用
WebSearch/WebFetch拉跨领域/最新材料;联网失败就回落到自身知识 + 已挂资料,绝不因断网报错。 - 沉淀成笔记。 结果写入
deep-notes/<concept-slug>.md,让深挖积累成知识资产。 - 基于已有锚点。 先看该概念在 knowledge-system.md 里的定位,再向外扩展,别脱离主题乱发散。
流程
1. 定位概念
- 在
knowledge-tree.md/knowledge-system.md里找到该 concept 所属节点与已有内容(挂了资料按数据契约第八节读相关章节)。找不到精确匹配 → 跟用户确认要挖的是哪个。 - 读全局
learner-profile.md(若存在),据其中讲解偏好调整深挖的讲法/类比风格——只调风格,不放松"四段都要有实质内容"的要求。见 data-contract 第十四节。
2. (可选)联网补料
- 尝试
WebSearch/WebFetch找该概念在其他领域的应用、最新进展、经典对比。 - 失败/不可用 → 跳过,用自身知识 + 已挂资料继续。在笔记里标注是否用了联网。
3. 生成深挖内容(四段)
- 🌐 跨领域连接:这个概念/机制在别的技术领域(或别学科)里有什么对应、相似或迁移?
- 🏠 类比:用一个直观的现实类比解释它的核心思想。
- 🔄 技术对比:与同类替代方案/相邻概念横向比较,讲清设计哲学差异。
- ❓ 延伸问题:抛出几个开放问题,引导进一步思考(可作为以后 mock/go 的难题来源)。
4. 沉淀到 deep-notes
- 写
$HOME/.study-with-cc/topics/<slug>/deep-notes/<concept-slug>.md(concept-slug = 概念的小写 kebab-case)。已存在则追加一段带日期的新内容,不覆盖旧笔记。
# 深挖:<concept>
(节点:<节点路径> <date +%F> 来源:<自身知识 / 联网 / 资料>)
## 🌐 跨领域连接
…
## 🏠 类比
…
## 🔄 技术对比
…
## ❓ 延伸问题
1. …
5. 输出摘要
🔍 已深挖:<topic> / <concept>
跨领域 <n> 条 | 对比 <m> 条 | 延伸问题 <k> 个 来源:<自身 / 联网>
📁 笔记:~/.study-with-cc/topics/<slug>/deep-notes/<concept-slug>.md
质量基准
- 四段都围绕该概念、有实质内容,不空泛发散。
- 联网不可用时正常产出(用自身知识),并如实标注来源。
- 只写了 deep-notes/ 笔记,progress/tree 未动。
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 · 72 lines · 73 tokens per session scan A d4a3340d99f7
swcc-deep is a skill published in the GitHub repository guoqiaoZhou/study-with-claude-code (2 stars, last pushed 2mo ago), licensed MIT. It adds 73 tokens to every session and 1,069 once invoked, about $0.0004 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.