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-ch-audit)<a href="https://agentmods.dev/commands/zhiliyouxian/claude-novel-writer/nw-ch-audit"><img src="https://agentmods.dev/badge/commands/zhiliyouxian/claude-novel-writer/nw-ch-audit/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-ch-audit"><img src="https://agentmods.dev/badge/commands/zhiliyouxian/claude-novel-writer/nw-ch-audit.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 | $0.00025 | $0.03323 |
| Opus 5 | $0.00013 | $0.01662 |
| Sonnet 5 | $0.00005 | $0.00665 |
| Haiku 4.5 | $0.00003 | $0.00332 |
Grade A, and why
nw-ch-audit 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 — 402 lines — stays where its author put it; the contents beside it link to each section on GitHub.
批量章节审核命令
快捷批量审核多个章节的命令。
用法
/nw-ch-audit <章节范围或列表>
示例
# 审核第1-10章(连续范围)
/nw-ch-audit 1-10
# 审核指定章节(离散列表)
/nw-ch-audit 1,4,7
# 审核单章
/nw-ch-audit 5
# 审核后半部分
/nw-ch-audit 101-200
功能
此命令会:
- 解析参数: 支持范围(1-10)或列表(1,4,7)格式
- 调用Agent: 调用
chapter-auditorAgent执行审核 - 逐章评分: 从五个维度评估每章质量
- 生成报告: 输出详细审核报告到reviews目录
- 汇总建议: 提供优先级修改建议
执行流程
用户输入: /nw-ch-audit 1-10
↓
解析: 起始=1, 结束=10, 共10章
↓
【前置】调用 encoding-checker Skill:
扫描: productions/{project_id}/chapters/chapter-*.md
├─ 无乱码 → 继续审核
└─ 有乱码 → 自动修复 → 再次检查 → 循环直到无乱码 → 继续审核
↓
读取素材池融合风格(style-fusion.md):
├─ 目标句长: 15.6字
├─ 目标对话比例: 43%
└─ 目标爽点密度: 3.3/千字
↓
For each 章节 from 1 to 10:
├─ 读取 productions/{project_id}/chapters/chapter-{NNNN}.md
├─ 统计基础数据(字数/句长/对话比例)
├─ 分析爽点(关键词/密度/分布)
├─ 评估对话(自然度/性格/推动剧情)
├─ 检查钩子(类型/吸引力)
├─ 评估节奏(起承转合)
├─ 计算综合评分
└─ 显示进度: "已审核 {N}/10 章"
↓
全部完成后:
├─ 生成批次报告
├─ 汇总问题清单
├─ 计算平均分
└─ 提示修改建议
审核维度
1. 风格一致性 (权重20%)
检查内容:
- 平均句长与目标偏差
- 对话比例与目标偏差
- 叙事视角统一性
评分标准:
- 10分: 完全符合目标(偏差<5%)
- 8分: 基本符合(偏差5-10%)
- 6分: 有偏差(偏差10-20%)
- 4分: 偏差较大(偏差20-30%)
- 2分: 严重偏离(偏差>30%)
2. 爽点密度 (权重30%)
检查内容:
- 爽点关键词数量
- 爽点分布均匀度
- 爽点类型多样性
爽点关键词:
- 战斗类: 碾压、秒杀、轰飞、击败、完胜
- 突破类: 突破、晋级、进阶、凝聚、圆满
- 震惊类: 震惊、骇然、惊呆、不可思议、难以置信
- 暴露类: 原来、竟然、居然、没想到、真相
- 获得类: 得到、获得、发现、宝物、机缘
评分标准:
- 10分: 密度3.5-4.0/千字
- 8分: 密度3.0-3.4/千字
- 6分: 密度2.5-2.9/千字
- 4分: 密度2.0-2.4/千字
- 2分: 密度<2.0/千字
3. 对话质量 (权重20%)
检查内容:
- 对话自然度(口语化程度)
- 角色性格一致性
- 对话推动剧情
评分标准:
- 10分: 自然+性格一致+推动剧情
- 8分: 基本符合,1-2处小问题
- 6分: 有3-5处问题
- 4分: 问题较多,>5处
- 2分: 严重不符合角色性格
4. 章节钩子 (权重15%)
检查内容:
- 章末悬念设置
- 钩子类型分类
- 吸引力评估
钩子类型:
- 悬念型: "就在...时" (推荐占比40-45%)
- 冲突型: 杀意/冷笑/对峙 (推荐占比30-35%)
- 预告型: "他不知道" (推荐占比15%)
- 反转型: 意外发生 (推荐占比10%)
评分标准:
- 10分: 强悬念+多重吸引
- 8分: 有效悬念或冲突
- 6分: 普通结尾,有一定吸引
- 4分: 结尾平淡
- 2分: 无钩子
5. 节奏把控 (权重15%)
检查内容:
- 章节结构(起承转合)
- 张弛有度
- 段落衔接
评分标准:
- 10分: 起承转合完美
- 8分: 节奏合理
- 6分: 略有拖沓或仓促
- 4分: 节奏问题明显
- 2分: 节奏混乱
评分计算
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 · 402 lines · 0 tokens per session scan A 5b8d7942ab35
nw-ch-audit is a command published in the GitHub repository zhiliyouxian/claude-novel-writer (5 stars, last pushed 8mo ago), licensed MIT. It adds 25 tokens to every session and 3,323 once invoked, about $0.0001 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.