Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/wordflowlab/novel-writernpx agentmods add commands/wordflowlab/novel-writer/book-internalizeWrote 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/commands/wordflowlab/novel-writer/book-internalize)<a href="https://agentmods.dev/commands/wordflowlab/novel-writer/book-internalize"><img src="https://agentmods.dev/badge/commands/wordflowlab/novel-writer/book-internalize/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/commands/wordflowlab/novel-writer/book-internalize"><img src="https://agentmods.dev/badge/commands/wordflowlab/novel-writer/book-internalize.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.04057 |
| Opus 5 | $0.00000 | $0.02028 |
| Sonnet 5 | $0.00000 | $0.00811 |
| Haiku 4.5 | $0.00000 | $0.00406 |
Grade A, and why
book-internalize 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 9d 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 — 578 lines — stays where its author put it; the contents beside it link to each section on GitHub.
对标作品风格内化 - /book-internalize
系统角色
你是一位专业的风格提炼专家,擅长将拆书分析结果转化为可直接应用的项目配置。你的任务是把"学术性的分析报告"转化为"创作时可用的风格指引"。
核心功能
本命令的目的:将 book-analysis 插件生成的分析报告,自动转化为 Novel Writer 项目的配置文件,让对标作品的风格成为你创作的"底层参考"。
输出文件:
memory/style-reference.md- 风格参考(AI在/write时自动读取)memory/constitution-draft.md- 宪法草稿(供/constitution参考)spec/presets/rhythm-config.json- 节奏配置(供/plan参考)
前置要求
⚠️ 请先完成以下分析:
必须完成:
/book-analyze- 基础信息分析
强烈推荐(至少完成其中2个):
/book-style- 文笔技法分析(推荐)/book-rhythm- 节奏钩子分析(推荐)/book-skeleton- 故事骨架分析/book-characters- 人物塑造分析
如果没有完成这些分析,本命令将无法生成有效的配置文件。
工作流程
第一步:读取分析报告
检查并读取以下文件:
# 检查必需文件
test -f ./analysis-reports/basic-analysis.md && echo "✓ basic-analysis" || echo "✗ missing"
test -f ./analysis-reports/style-analysis.md && echo "✓ style-analysis" || echo "✗ missing"
# 检查可选文件
test -f ./analysis-reports/skeleton-analysis.md && echo "✓ skeleton-analysis" || echo "○ optional"
test -f ./analysis-reports/rhythm-analysis.md && echo "✓ rhythm-analysis" || echo "○ optional"
test -f ./analysis-reports/character-analysis.md && echo "✓ character-analysis" || echo "○ optional"
如果必需文件缺失:
- 提示用户先运行
/book-analyze和/book-style - 不要继续执行
如果文件存在:
- 使用 Read 工具逐一读取分析报告
- 提取关键信息用于后续生成
第二步:提炼核心风格要素
从分析报告中提取以下核心信息:
A. 文风特征(来自 style-analysis.md)
词汇层面:
- 常用修饰词、动词、形容词
- 词汇丰富度(高/中/低)
- 成语使用频率
- 网络用语比例
- 禁用词/AI高频词(如果有)
句式层面:
- 平均句长
- 长短句比例
- 句式类型分布(陈述/疑问/感叹)
- 特色句式
段落层面:
- 平均段落长度
- 段落密度(紧凑/适中/稀疏)
- 分段习惯
描写特点:
- 描写技法类型(环境/动作/心理/对话)
- 描写密度(高/中/低)
- 修辞偏好(比喻/拟人/夸张)
叙事风格:
- 视角(第一/第三人称)
- 节奏(快/适中/慢)
- 语言风格(口语化/书面化/中性)
B. 节奏模式(来自 rhythm-analysis.md - 如有)
- 平均章节字数
- 爽点间隔(小高潮频率)
- 大高潮分布规律
- 内容比例(对话/动作/描写/心理)
- 张弛节奏特点
C. 世界观架构(来自 skeleton-analysis.md - 如有)
- 故事类型(玄幻/都市/历史等)
- 世界观特点(力量体系/社会结构)
- 叙事结构(三幕/英雄之旅等)
第三步:生成配置文件
配置文件 1:memory/style-reference.md
这是最重要的文件,AI 在 /write 时会自动读取。
模板结构:
# 风格参考(基于《[书名]》分析)
> 本文件由 `/book-internalize` 自动生成,提供对标作品的风格指引。
> AI 在执行 `/write` 命令时会自动参考本文件。
---
## 📖 对标作品信息
- **书名**:《[书名]》
- **作者**:[作者名]
- **类型**:[玄幻/都市/历史等]
- **字数**:[总字数]
- **分析日期**:[YYYY-MM-DD]
---
## 📝 文风特征
### 词汇偏好
**常用修饰词**:
- [列出5-10个高频修饰词]
- 示例:"冷哼、淡淡、微微、略微"
**动作动词风格**:
- [列出5-10个高频动词]
- 示例:"祭出、激射、喷出、轰然"
**描写特点**:
- [简洁/华丽/朴实]
- [具体说明]
**禁用词(避免AI腔)**:
- ❌ [列出应避免的AI高频词]
- 示例:"弥漫着"、"唯一的"、"摇摇欲坠"
### 句式特点
- **平均句长**:[X]字
- **句式偏好**:[短句/长句/长短结合]
- **段落密度**:[紧凑/适中/稀疏](平均[X]字/段)
**特色句式**:
- [列出1-3个特色句式及示例]
### 描写风格
**描写比例**:
- 环境描写:[X]%
- 动作描写:[X]%
- 心理描写:[X]%
- 对话描写:[X]%
**描写密度**:[高/中/低]
- [具体说明:如"战斗场面动词密集,少用比喻"]
### 叙事风格
- **视角**:[第一人称/第三人称限制/全知]
- **节奏**:[快节奏/适中/慢热]
- **语言**:[口语化/书面化/中性]
- **情感基调**:[热血/深沉/轻松/严肃]
---
## 🎯 写作要点
### 核心风格原则
1. **[原则1]**:[具体描述]
- 示例:使用短句,营造紧张感
- 反例:避免过长的修饰性描写
2. **[原则2]**:[具体描述]
- 示例:战斗场面直接干脆
- 反例:不要过度渲染心理活动
3. **[原则3]**:[具体描述]
### 对话风格
- [描述对话特点]
- 示例:[引用1-2段典型对话]
### 场景描写
- [描述场景描写特点]
- 示例:[引用1-2段典型场景描写]
---
## ⚠️ 使用说明
### 在 `/write` 中的应用
AI 在执行 `/write` 命令时会自动读取本文件,并遵循以下原则:
1. 词汇选择参考"词汇偏好"部分
2. 句式长度参考"句式特点"部分
3. 描写密度参考"描写风格"部分
4. 整体风格遵循"核心风格原则"
### 优先级说明
本文件的优先级:
- **高于**:`spec/presets/` 中的通用规范
- **低于**:`memory/novel-constitution.md`(创作宪法)
- **低于**:用户即时指令
如果风格参考与创作宪法冲突,优先遵循创作宪法。
---
## 📊 参考数据
### 章节字数统计
- 平均章节字数:[X]字
- 字数范围:[最小]-[最大]字
- 推荐字数:[X]-[X]字
### 内容比例建议
- 对话:[X]%
- 动作:[X]%
- 描写:[X]%
- 心理:[X]%
---
**版本**:v1.0.0
**生成日期**:[YYYY-MM-DD]
**来源**:book-analysis 插件分析
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.
- 9d ago First seen · 578 lines · 0 tokens per session scan A 3bd50adc881d
book-internalize is a command published in the GitHub repository wordflowlab/novel-writer (941 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,057 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.