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-initgit 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-init)<a href="https://agentmods.dev/skills/cabbage2000-lab/textbook-writer-skills/textbook-init"><img src="https://agentmods.dev/badge/skills/cabbage2000-lab/textbook-writer-skills/textbook-init/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-init"><img src="https://agentmods.dev/badge/skills/cabbage2000-lab/textbook-writer-skills/textbook-init.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 | $0.00155 | $0.01650 |
| Opus 5.5 | $0.00062 | $0.00660 |
| Sonnet 5.5 | $0.00031 | $0.00330 |
| Haiku 4.5 | $0.00015 | $0.00165 |
Grade A, and why
textbook-init 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
textbook-init
动笔前的工作目录规划师：一轮提问弄清作者要写一本还是多本、放在哪里、要不要版本管理，呈现目录方案等确认后创建目录骨架（可含 git 仓库与 README 工作说明），最后把作者交给 textbook 主流程开写。教材项目内部的文件构成以 ../textbook/references/handoff-contract.md（下称"契约文档"）第 3 节为唯一权威定义，本 skill 只引用不重复定义。
何时不触发
- 已有教材项目要续写（目录里有
.progress.json）——直接用 textbook，它会按状态文件定位续点； - 作者直接开写、不关心目录规划——textbook 启动时自会询问一次并默认
./<教材名>/，无需先走本 skill； - 整理与教材写作无关的目录——本 skill 只服务教材项目的开局。
与流水线的关系
本 skill 只独立触发：不被 textbook 调度，不进五阶段契约链，产出是"就绪的空工作目录 + 启动指引"。
流水线文件一律不建不改：.progress.json（主 skill 是唯一写者，这是项目红线）、00-前言.md（阶段 5 派生生成）、00-教材设计.md（textbook-outline 写入）、NN-<章标题>.md（逐章生成）、98-参考答案.md（逐章追加）、99-表现性任务.md（阶段 5 派生生成）、术语表.md（主 skill 追加维护）。动机：主 skill 的重入判定靠"这些文件存不存在、内容有没有"定位续点（契约文档第 4 节），预建空文件会让它把全新项目误判成半成品；空壳文件混进交付物也违背"交付即可用"的底线。本 skill 创建的只有目录本身、.gitignore 和 README 工作说明——均在契约之外。
工作流
第 1 步：一轮提问
用 AskUserQuestion 一轮收集四项（触发语已说明的项不再问）：
- 教材名：如《线性代数入门》——将成为项目目录名；
- 规划范围：a) 只写这一本 b) 未来还会写多本（追加：工作区名，默认"教材工作区"）；
- 位置：项目/工作区建在哪个目录下，默认当前目录
./； - git 版本管理：默认要（教材写作周期以周计，版本保护值回票价）；作者明确不要则跳过。
若当前环境没有 AskUserQuestion 工具，降级为编号提问并等待文本回复：
请回答以下问题（回复格式如 "1 线性代数入门 2b 教材工作区 3 ./ 4 要"）：
1. 教材名？
2. 规划范围？ a) 只写这一本 b) 未来还会写多本（请给工作区名，默认"教材工作区"）
3. 建在哪个目录下？（默认当前目录 ./）
4. 要 git 版本管理吗？（默认要）
按语义宽松解析回复，只就有歧义的一项追问。
第 2 步：方案呈现与确认
按 references/workspace-layout.md 第 1、2 节的布局规则组装方案，完整呈现后停下：
- 目录树预览：含流水线随后会生成的文件，逐项注明"由 textbook 流水线创建"——让作者看到最终形态，同时不误以为本 skill 会建它们；
- 关键选择及理由：单本还是工作区分层、git 建在哪一层、
.gitignore为什么不忽略.progress.json； - 停点格式沿用契约文档第 5 节：
⏸ 等待确认：工作目录方案（回复"确认"开始创建，或直接提出修改）
作者提出修改 → 更新方案后重新完整呈现再等确认，循环直到明确确认；"确认，但把位置改一下"这类混合答复按修改分支处理（修改优先于确认，判定语义同契约文档第 5 节）。确认前不创建任何东西。
第 3 步：创建与交接
- 建目录：按确认的方案
mkdir -p； - git 判重：在目标位置检查是否已处于某个 git 仓库内（方法见 references/workspace-layout.md 第 3 节）——已在，则跳过 git init 并向作者说明原因；
- git 初始化（作者要 git 且未命中判重）：git init + 写
.gitignore+ 首次提交，层级与内容规范见 references/workspace-layout.md 第 3、4 节； - README 工作说明：按 references/workspace-layout.md 第 5 节模板实例化——所有字段填当前项目的真实值，写完通读确认没有残留尖括号或待填空白；
- 打印成果与下一步指引：
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 1cc4030f2f48
- 1mo ago Changed · +4 lines · +13 tokens per session 4ba39b4cdbd5
- 1mo ago First seen · 76 lines · 142 tokens per session scan A 0e86b969ebbc
textbook-init is a skill published in the GitHub repository cabbage2000-lab/textbook-writer-skills (38 stars, last pushed 8d ago), licensed MIT. It adds 155 tokens to every session and 1,650 once invoked, about $0.0006 per session on Opus 5.5. 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
diffler
Generate and deliver a graded comprehension quiz from the current Git branch diff, either in the local terminal or through Google Forms. Use when a user asks to prove, test, or verify understanding of branch changes, a feature branch, or a pull request.
uru-thesis-reviewer
Continuous-feedback reviewer for URU (Universidad Rafael Urdaneta) theses. Emits ordered .md diff files (- old / + new) the author applies manually — never edits the .docx. Covers substance, structure, prose, citations vs NORMASURU2020. Tracks issues across sessions via stable IDs and carry-forward. Use when the user…
study-artifact-builder
Build a single-file interactive HTML artifact to study a paper's pipeline or dataset until it can be defended from memory — source pinning, paper-versus-code separation, per-component explanation (mechanics, real example, measured on the data, non-obvious details), ablation toggles, SVG diagram, numeric audit. Use…
uru-thesis-architect
Interview-first drafter for URU (Universidad Rafael Urdaneta) thesis (TEG) chapters — writes one section at a time toward the evaluation rubric the jury grades against, Spanish output, URU chapter order (I. Problema → V. Propuesta), never fabricates data. Complements uru-thesis-reviewer. Use when drafting or iterating…
uru-thesis-defense-architect
Design URU-style thesis defense presentation specs — fixed institutional slide structure (portada, problema, objetivos, antecedentes, variables, metodología, resultados, conclusiones), Spanish-only content, logo placement rules (large centered cover, small top-left from slide 2). Outputs one .md slide-by-slide spec.…
design-patterns
Skeptical design-patterns reference catalog for modern Go and Python — keeps repository, adapter, strategy, decorator, observer, builder; flags the rest as anti-patterns. Consultative, not active: consult before introducing a pattern in code-design-refactor or improve-codebase-architecture, or when pushing back on a…