Borrowing it
Nothing to install: this file belongs to cabbage2000-lab/textbook-writer-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cabbage2000-lab/textbook-writer-skills/main/AGENTS.mdgit 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/instructions/cabbage2000-lab/textbook-writer-skills/agents-md)<a href="https://agentmods.dev/instructions/cabbage2000-lab/textbook-writer-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/cabbage2000-lab/textbook-writer-skills/agents-md.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 5.1 | $0.01192 | $0.01192 |
| Opus 5 | $0.00596 | $0.00596 |
| Sonnet 5 | $0.00238 | $0.00238 |
| Haiku 4.5 | $0.00119 | $0.00119 |
Grade A, and why
textbook-writer-skills AGENTS.md 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 8d 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
本文件是 Codex CLI 及其他读取 AGENTS.md 的宿主在本仓库中的项目级指令入口，作用与 CLAUDE.md 面向 Claude Code 平行——CLAUDE.md 面向"改 skill 时的工程约束"，本文件面向"如何在本仓库启动并运行这套 skill"。
它是未安装时的兜底路径：已按 README「快速开始」装了插件（codex plugin add textbook-writer@textbook-writer-skills）或把 skills/ 复制进宿主 skills 目录的，宿主会自行加载 5 个 skill，不必依赖本文件的路由表；在本仓库目录里直接开干、什么都没装时，按本文件走同样成立。
这是什么
本仓库是一套以 UbD 逆向设计为内核的教材写作 skill 组合（学科无关内核 + 可插拔学科档案，内置 stem、humanities、economics 三份）：1 个主 skill（textbook）编排 3 个子 skill，驱动"教学定位 → UbD 预期结果 gate → 章节树 gate → 逐章写作 → 审核定稿"五阶段流程；另有 1 个独立辅助 skill（textbook-init）负责动笔前的工作目录规划，不入调度链。5 个 skill 是一个整体组合，跨 skill 以相对路径互相引用，需整体使用，不得只启用其中一个而忽略其余。
触发路由：用户想做什么，就读哪个 SKILL.md
宿主未安装本套 skill 时不会自动加载它们的 frontmatter。收到以下意图时，直接读取对应文件并严格遵循其指令执行：
| 用户意图（触发词示例） | 读取并遵循 |
|---|---|
| 写教材 / 写一本…教材 / 编写课程讲义 / 系统教材 | skills/textbook/SKILL.md |
| 设计教材大纲 / 教材规划 / 课程体系设计 | skills/textbook-outline/SKILL.md |
| 写第 X 章 / 按大纲写这一章 | skills/textbook-chapter/SKILL.md |
| 出几道题 / 给这一章生成例题 | skills/textbook-exercises/SKILL.md |
| 初始化教材项目 / 创建或规划教材工作目录 | skills/textbook-init/SKILL.md |
跨 skill 调用桥接
各 SKILL.md 内部已写明"使用 Skill 工具调用对方 skill；若 Skill 工具不可用或未注册，直接读取对方 SKILL.md 并严格遵循其指令执行"的降级路径（例：skills/textbook/SKILL.md 第 42、56 行，skills/textbook-chapter/SKILL.md 第 33 行）。没有 Skill 工具的宿主天然命中这条降级分支：主 skill 调子 skill、子 skill 相互调用时，都直接读取被调用方的 SKILL.md 并遵循执行，无需任何额外适配。另一处同款降级是 textbook-outline、textbook-init 的一轮提问——宿主没有 AskUserQuestion 一类结构化提问工具时，降级为编号提问、等待文本回复，收集到的信息完全一致。
三条红线（细节以对应 SKILL.md / handoff-contract.md 为准，此处只提醒不重述）
- 双 gate 必须停：阶段 2（UbD 五件套）、阶段 3（章节树+梯度报告）必须等作者明确确认才能推进，任何"流程优化"都不得绕过或自动确认。
- 每题必验，不许假装：例题与习题的答案必须按所用学科档案第 2 节定义的手段实际核对后才能输出（
stem档案 = 真算复核）；确实验证不了的，必须明确标注⚠️ 需作者确认，绝不能在没有验证的情况下假装已验证。档案能定义"用什么方式验证"，不能定义"是否需要验证"。 - 状态单一写者：
.progress.json只由textbook（主 skill）读写，子 skill（textbook-outline、textbook-chapter、textbook-exercises）一律不碰这个文件。
契约、落盘布局、状态机的完整权威定义见 skills/textbook/references/handoff-contract.md；学科差异（题型集、验证手段、认知动词、章内段义）的收口处是 skills/textbook/references/subject-profile-spec.md，阶段 1 判定档案、逐章透传，内置三份：stem（答案可复算的学科）、humanities（答案取决于论证、但引文与史实可核查的学科）、economics（模型题可复算、统计数据须核对来源，两类在同一本书里交织）。
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.
- 8d ago First seen · 34 lines · 1,192 tokens per session scan A d27b3f82bc0b
textbook-writer-skills AGENTS.md is an instructions file published in the GitHub repository cabbage2000-lab/textbook-writer-skills (27 stars, last pushed 6d ago), licensed MIT. It adds 1,192 tokens to every session, about $0.0060 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.