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 skills add cabbage2000-lab/textbook-writer-skills --skill textbook-exercisesgit clone --depth 1 https://github.com/cabbage2000-lab/textbook-writer-skillsWrote 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/cabbage2000-lab/textbook-writer-skills/textbook-exercises)<a href="https://agentmods.dev/skills/cabbage2000-lab/textbook-writer-skills/textbook-exercises"><img src="https://agentmods.dev/badge/skills/cabbage2000-lab/textbook-writer-skills/textbook-exercises/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cabbage2000-lab/textbook-writer-skills/textbook-exercises"><img src="https://agentmods.dev/badge/skills/cabbage2000-lab/textbook-writer-skills/textbook-exercises.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00151 | $0.01747 |
| Opus 5 | $0.00076 | $0.00873 |
| Sonnet 5 | $0.00030 | $0.00349 |
| Haiku 4.5 | $0.00015 | $0.00175 |
Grade A, and why
textbook-exercises 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 7d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
textbook-exercises
生成三类题（示范例题/引导练习/独立习题），每道题带 Bloom 层级标注，每道题的答案都经过验证才输出。学科无关的设计与验证纪律见 references/exercise-design.md；本次出题的题型集与每型的验证手段取自输入契约 学科档案 指定的档案第 2 节（规格与索引见 ../textbook/references/subject-profile-spec.md）。
何时不触发
- 题型在所用档案第 2 节里没有对应验证手段的（如
stem档案下的文科论述题、案例分析题）——按 exercise-design.md 第 7 节反模式 5 处理：改出档案内最接近的题型（stem档案下改概念辨析题）并在输出中说明替换 - 组卷/试卷排版（本 skill 只产题目内容）
- 与教材无关的一般性问答
两种调用模式
- 被 textbook-chapter 调用（常规）：输入 = 契约
{章上下文, 题目计划, 术语表, 学科档案}（字段定义见 ../textbook/references/handoff-contract.md 第 2 节）。按题目计划逐条生成，不多不少。 - 独立触发：一轮问清
{主题, 读者水平, 三类题各要几道, 期望 Bloom 层级分布}（用户已说明的不重复问）；按主题自行判定学科档案（索引见 subject-profile-spec.md 第 5 节，找不到匹配项按该文档第 7 节处理：说明将按最接近的档案处理并指出差异），并在输出开头说明用了哪份档案；术语自拟并保持内部一致；编号中的章号默认取 1，用户指定章号则从之。
生成流程（每道题走完 1–4 才算完成一道）
-
设计题面：题型从档案第 2 节的题型集里选（表外的题型不出，见"何时不触发"），支撑纪律按 references/exercise-design.md 第 4 节，具体教学动作按档案第 4 节；对照题目计划的主题与 Bloom 层级，层级判定标准查 ../textbook-outline/references/bloom-levels.md 第 4 节（同题多问取最高层，歧义就低不就高；六层对照标尺在档案第 3 节）。
-
同步写完整解答：示范例题 = 逐步推导每步一行理由；引导练习 = 提示阶梯（提示 1 方向 → 提示 2 关键步骤）+ 完整解答；独立习题 = 参考答案或含关键中间结果的解题路径。禁止先攒题后补答案。
-
验证（红线，不可省略）：到档案第 2 节查该题型的「验证手段」列，照它执行；执行不了时照同一行的「无法验证时的降级」列处理，不自行发明第三种做法。两条与学科无关的硬纪律：
- 验证必须走与解答不同的路径——沿同一条路径重走一遍，重复的是同一个错误，等于没验证；
- 档案里每型的「验证手段」列都非空，即没有任何题型可以跳过验证（spec 第 2 节）。
-
处理验证结果：核对一致 → 标
✅ 已验证（<方式>）；不一致 → 修题或修解答后重新验证；连续 2 次验证失败 → 弃题换题。手段与降级路径都走不通（如开放性探究题）→ 标⚠️ 需作者确认（<原因>），绝不假装已验证。
输出
- 按契约逐题给出
{编号, 类型, 题干, 解答或提示, Bloom层级, 验证状态}； - 正文格式遵循 exercise-design.md 第 6 节（编号规则
例 N-M/习题 N-M，引导练习计入"例"序列加后缀），文体附加条款按档案第 4 节； - 验证过程逐题附上（放在该题"验证"行后的代码块中，每题都要有）：能用代码复算的，附这道题自己的、复制即可运行的代码——不写"多题共用一个外部脚本 + 逐题只附调用命令"，因为章文件里没有安放共享脚本的位置，脚本落在章外读者就复核不了；靠核验依据完成的附核验记录（详见 exercise-design.md 第 3 节末）；
- 术语用词严格对照传入的术语表；独立触发时保持自拟术语的内部一致。
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago Changed · +4 lines · +30 tokens per session dfb57f4464a4
- 11d ago First seen · 45 lines · 121 tokens per session scan A 98c053124391
textbook-exercises is a skill published in the GitHub repository cabbage2000-lab/textbook-writer-skills (27 stars, last pushed 8d ago), licensed MIT. It adds 151 tokens to every session and 1,747 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
understand-explain
Use when you need a deep-dive explanation of a specific file, function, or module in the codebase.
baoyu-comic
A tool for creating original educational comics that explain knowledge or ideas through multiple illustrated panels. It supports different art styles and tones and can create several comics in one batch.
skill-creation-walkthrough
Step-by-step guide for creating your own Claude Skills, from deciding whether a skill is the right tool to writing the SKILL.md file, structuring reference material, and making it trigger reliably. Use when you want to package a workflow, framework, or repeated task into a reusable Skill, when an existing skill is not…
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.
master-debate
A skill for running an adversarial, multi-round debate between two Buddhist teachers. It is designed for questions where the teachers argue from different positions.
master-atisha
A reference-based assistant for Atisha and the Kadam school, an early Tibetan Buddhist tradition. It explains the staged path to awakening and can answer in Atisha’s historical teaching style.