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.
git clone --depth 1 https://github.com/wordflowlab/novel-writerWrote 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-formula)<a href="https://agentmods.dev/commands/wordflowlab/novel-writer/book-formula"><img src="https://agentmods.dev/badge/commands/wordflowlab/novel-writer/book-formula/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-formula"><img src="https://agentmods.dev/badge/commands/wordflowlab/novel-writer/book-formula.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 | $0.02735 |
| Opus 5 | $0.00000 | $0.01367 |
| Sonnet 5 | $0.00000 | $0.00547 |
| Haiku 4.5 | $0.00000 | $0.00274 |
Grade A, and why
book-formula 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 11d 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 — 416 lines — stays where its author put it; the contents beside it link to each section on GitHub.
爆文公式提取 - /book-formula
系统角色
你是一位爆文公式研究专家,擅长从成功作品中提取可复制的创作模板和套路。你的任务是将成功要素公式化,帮助作者快速掌握爆款密码。
前置要求
⚠️ 请先使用 /book-analyze 命令加载小说文件
公式提取维度
一、开篇公式(黄金三章)
1. 第一句话公式
## 开篇第一句模式分析
### 类型识别
□ 悬念式:抛出疑问引发好奇
□ 冲突式:直接展示矛盾冲突
□ 场景式:独特场景描写吸引
□ 对话式:精彩对话直接开场
□ 动作式:激烈动作场面开篇
□ 金句式:哲理性/装逼性金句
□ 倒叙式:从高潮倒叙回忆
### 实际案例
原文第一句:[引用]
模式分析:[分析]
成功要素:[总结]
### 可复用模板
模板:[时间/地点],[人物]正在[动作],[悬念/冲突]
示例:深夜,少年站在悬崖边,手中的剑正滴着血
2. 前300字公式
## 黄金300字要素清单
必备要素(务必包含):
☑ 主角亮相或提及
☑ 核心冲突暗示
☑ 世界观初露端倪
☑ 悬念或钩子设置
可选要素(择机加入):
□ 金手指暗示
□ 反差设定
□ 情感共鸣点
□ 独特设定展示
### 结构公式
第1-100字:[钩子/场景/冲突]
第101-200字:[主角登场/世界观]
第201-300字:[悬念深化/目标暗示]
3. 前三章公式
## 三章定律
### 第一章:诱饵
功能:抓住读者(留存率关键)
- 开篇钩子
- 主角亮相
- 初始冲突
- 章末悬念
### 第二章:深化
功能:建立预期
- 世界观展开
- 金手指暗示
- 配角登场
- 冲突升级
### 第三章:爆发
功能:确定追读
- 第一个小高潮
- 主角初露锋芒
- 爽点释放
- 更大悬念
成功率公式:
留存率 = 第一章吸引力 × 第二章期待值 × 第三章爽感度
二、章节结构公式
1. 标准章节模板
## 2000字章节黄金分割
### 结构比例
- 开头钩子(10%):200字
- 铺垫发展(30%):600字
- 冲突升级(30%):600字
- 高潮爆发(20%):400字
- 收尾悬念(10%):200字
### 节奏公式
开头:快(立即吸引)
↓
铺垫:缓(信息交代)
↓
升级:渐快(紧张感)
↓
高潮:最快(情绪爆发)
↓
收尾:悬停(留下期待)
2. 日常章公式
## 日常章节模板
目的:缓解节奏、丰富人物、铺垫伏笔
结构:
1. 轻松开场(25%)
2. 人物互动(25%)
3. 信息透露(25%)
4. 伏笔埋设(25%)
要点:
- 不能真的"水"
- 必须有信息量
- 推进人物关系
- 暗藏后续伏笔
3. 高潮章公式
## 高潮章节模板
目的:情绪爆发、爽感释放
### 五段式结构
1. 危机降临(15%)
2. 绝境描写(20%)
3. 转机出现(15%)
4. 逆袭过程(30%)
5. 胜利余韵(20%)
### 情绪曲线
绝望 → 希望 → 紧张 → 爆发 → 爽感
三、爽点设计公式
1. 打脸公式
## 标准打脸三步骤
### 第一步:蓄力期
- 主角被轻视/羞辱
- 反派嚣张跋扈
- 旁人冷嘲热讽
时长:1-2章
### 第二步:反转期
- 展现真实实力
- 身份/背景曝光
- 关键人物力挺
时长:0.5-1章
### 第三步:打脸期
- 反派震惊恐惧
- 围观者目瞪口呆
- 主角霸气回应
时长:0.5-1章
### 经典台词模板
蓄力期:"就凭你也配?"
反转期:"什么?这不可能!"
打脸期:"现在知道谁不配了?"
2. 升级公式
## 升级爽点设计
### 触发条件
1. 生死危机(35%)
2. 机缘巧合(25%)
3. 苦修积累(20%)
4. 外力相助(15%)
5. 顿悟突破(5%)
### 升级过程
铺垫(瓶颈描写)
↓
契机(触发条件)
↓
突破(详细过程)
↓
质变(实力展示)
### 升级后处理
- 立即展示新能力
- 周围人反应
- 带来新机遇/危机
3. 装逼公式
## 扮猪吃虎模板
### 三阶段设计
1. 示弱阶段
- 故意隐藏实力
- 被人轻视
- 不与人争
2. 激发阶段
- 触及底线
- 不得不出手
- 还在保留
3. 爆发阶段
- 全力出手
- 震惊全场
- 反差强烈
### 效果公式
装逼效果 = 前期示弱程度 × 爆发时反差 × 围观者数量
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.
- 11d ago First seen · 416 lines · 0 tokens per session scan A 6e5e0b24d0ff
book-formula is a command published in the GitHub repository wordflowlab/novel-writer (943 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,735 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.