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/zhiliyouxian/claude-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/zhiliyouxian/claude-novel-writer/nw-bp-plan)<a href="https://agentmods.dev/commands/zhiliyouxian/claude-novel-writer/nw-bp-plan"><img src="https://agentmods.dev/badge/commands/zhiliyouxian/claude-novel-writer/nw-bp-plan/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/zhiliyouxian/claude-novel-writer/nw-bp-plan"><img src="https://agentmods.dev/badge/commands/zhiliyouxian/claude-novel-writer/nw-bp-plan.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 | $0.00044 | $0.04767 |
| Opus 5 | $0.00022 | $0.02384 |
| Sonnet 5 | $0.00009 | $0.00953 |
| Haiku 4.5 | $0.00004 | $0.00477 |
Grade A, and why
nw-bp-plan 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 12d 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 — 513 lines — stays where its author put it; the contents beside it link to each section on GitHub.
蓝图生成命令
生成小说蓝图，包括选题方案、世界观、角色档案和章节大纲。
核心理念：融合麦基戏剧理论（控制思想、五大转折点、场景极性）与网文技法（爽点、钩子、境界曲线）。
执行此命令后进入蓝图阶段，后续对话可直接讨论蓝图修改，无需重复输入命令。
阶段职责分工
| 阶段 | 职责 | 产出 |
|---|---|---|
| 蓝图阶段 | 详细规划 | 世界观、角色、大纲、戏剧结构 |
| 创作阶段 | 展开润色 | 根据蓝图展开内容，润色文字 |
- 蓝图阶段：完成所有规划工作，包括情节设计、角色塑造、冲突设置、戏剧结构
- 创作阶段：根据蓝图展开具体内容，负责文字润色、节奏把控、细节填充
蓝图越详细，创作越顺畅。创作阶段不应大幅修改情节走向。
灵活模式
规模灵活
支持任意规模的小说创作：
| 规模 | 章节数 | 适用场景 |
|---|---|---|
| 单章 | 1章 | 短篇故事、番外 |
| 短篇 | 3-10章 | 短篇小说、试写 |
| 中篇 | 20-50章 | 中篇连载 |
| 长篇 | 100-300章 | 标准网文 |
| 超长篇 | 500+章 | 无限连载 |
不限制章节数：用户可自由指定，系统自动适配卷划分和节奏。
渐进式策划
支持「边策划边创作」的工作流：
策划第一卷 → 创作第一卷 → 策划第二卷 → 创作第二卷 → ...
无需一次性完成全部蓝图，可以：
- 先生成总览（世界观、角色、大纲框架）
- 细化当前卷 → 创作当前卷
- 根据创作情况调整后续卷的规划
- 重复以上过程
自然语言引导
如果信息不完整，通过对话澄清：
用户: "我想写个修仙小说"
Claude: 好的，为了生成更合适的蓝图，我有几个问题：
1. 规模打算多大？
- 短篇（10章左右）
- 中篇（50章左右）
- 长篇（200章以上）
- 无限连载（边写边规划）
2. 主角有什么特别的金手指或设定吗？
3. 希望是什么风格？
- 爽文快节奏
- 剧情流
- 轻松搞笑
- ...
用法
/nw-bp-plan [pool_name] <类型> <流派>
示例
# 基于素材池生成蓝图
/nw-bp-plan xuanhuan_1 玄幻 废柴流
# 不使用素材池，直接生成
/nw-bp-plan 玄幻 系统流
# 指定更多关键词
/nw-bp-plan 都市 重生 复仇
# 英文关键词也支持
/nw-bp-plan fantasy hero's-journey
参数说明
| 参数 | 必填 | 说明 |
|---|---|---|
| pool_name | 可选 | 素材池名称，用于参考风格 |
| 类型 | 必填 | 题材类型（玄幻/仙侠/都市/科幻等） |
| 流派 | 必填 | 流派关键词（废柴流/系统流/重生等） |
| --id | 可选 | 自定义 project_id（默认自动生成） |
project_id 自动生成
详细规范见
specs/project-naming.md
命名格式
{主题材前缀}_{序号}
主题材映射
| 关键词 | 前缀 | 示例 |
|---|---|---|
| 玄幻/异世界/领主 | xuanhuan |
xuanhuan_001 |
| 仙侠/修仙/洪荒 | xianxia |
xianxia_001 |
| 都市/重生/职场 | dushi |
dushi_001 |
| 科幻/末世/星际 | kehuang |
kehuang_001 |
| 历史/穿越/架空 | lishi |
lishi_001 |
| 游戏/网游/电竞 | youxi |
youxi_001 |
| 奇幻/魔法/西幻 | qihuan |
qihuan_001 |
| 悬疑/推理/灵异 | xuanyi |
xuanyi_001 |
| 轻小说/校园/日常 | qingxiaoshuo |
qingxiaoshuo_001 |
自动生成规则
输入: /nw-bp-plan 都市 重生流
系统处理:
1. 识别主题材: 都市 → dushi
2. 扫描已有项目: blueprints/dushi_001/, blueprints/dushi_002/
3. 生成新ID: dushi_003
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.
- 12d ago First seen · 513 lines · 0 tokens per session scan A cf207e520408
nw-bp-plan is a command published in the GitHub repository zhiliyouxian/claude-novel-writer (5 stars, last pushed 8mo ago), licensed MIT. It adds 44 tokens to every session and 4,767 once invoked, about $0.0002 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 2026-08-31.
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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.