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-release)<a href="https://agentmods.dev/commands/zhiliyouxian/claude-novel-writer/nw-release"><img src="https://agentmods.dev/badge/commands/zhiliyouxian/claude-novel-writer/nw-release/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-release"><img src="https://agentmods.dev/badge/commands/zhiliyouxian/claude-novel-writer/nw-release.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 | $0.00016 | $0.03952 |
| Opus 5 | $0.00008 | $0.01976 |
| Sonnet 5 | $0.00003 | $0.00790 |
| Haiku 4.5 | $0.00002 | $0.00395 |
Grade A, and why
nw-release 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 — 561 lines — stays where its author put it; the contents beside it link to each section on GitHub.
发布导出命令
执行者:
release-manageragent本命令由 release-manager agent 执行，该 agent 会：
- 进行发布前检查（书名、章节状态、完整性）
- 根据格式调用相应 Skill（audiobook-optimizer、format-exporter 等）
- 传递正确的参数并协调执行
将创作内容导出为多种发布格式。
用法
/nw-release <格式>
格式说明
| 格式 | 输出 | 说明 |
|---|---|---|
tts |
releases/{project_id}/tts/scripts/ |
语音文本（去换行、优化朗读） |
txt |
releases/{project_id}/text/full.txt |
完整合集（单文件） |
md |
releases/{project_id}/markdown/ |
发布版 Markdown（去 yml 头） |
audio |
releases/{project_id}/tts/audio/ |
有声书音频 + 字幕 |
video-char |
releases/{project_id}/video/prompts/characters/ |
角色视觉提示词 |
video-prep |
releases/{project_id}/video/storyboard/ + prompts/scenes/ |
分镜 + 场景提示词 |
video-assemble |
releases/{project_id}/video/output/ |
拼接最终视频 |
all |
以上全部（不含 video） |
示例
# 导出语音朗读文本
/nw-release tts
# 导出完整合集
/nw-release txt
# 导出发布版 Markdown
/nw-release md
# 导出所有格式
/nw-release all
# 生成有声书音频 + 字幕
/nw-release audio
# === 视频发布 ===
# 生成角色视觉提示词
/nw-release video-char
# 生成分镜脚本和场景提示词
/nw-release video-prep
# 拼接最终视频（需先放置图片）
/nw-release video-assemble
也可以通过自然语言触发，如：
- "导出有声书文本"
- "生成语音版本"
- "合成音频" → 会生成 tts/scripts + audio + subtitles
- "制作视频" → 启动完整视频发布流程
- "生成角色参考图提示词"
- "生成分镜脚本"
支持的导出格式
1. TXT纯文本 (txt)
文件: releases/{project_id}/text/full.txt
特点:
- 所有章节合并为单文件
- 移除YAML frontmatter
- 移除Markdown标记
- 统一中文标点
- 章节间空行分隔
示例输出:
第1章 {章节标题1}
{起始城镇}，{主角家族}。
"{主角}哥哥，这是我给你带的糕点。"{女主}提着食盒，轻声说道。
...
第2章 {章节标题2}
...
2. 带目录TXT (txt-toc)
文件: releases/{project_id}/text/full-with-toc.txt
特点:
- 文件开头包含目录
- 目录包含章节名和字数
- 便于快速定位
示例输出:
【目录】
第1章 {章节标题1} (3,200字)
第2章 {章节标题2} (3,150字)
第3章 {章节标题3} (2,980字)
...
总字数: 93,000字
总章节: 30章
═══════════════════════════════
第1章 {章节标题1}
{起始城镇}，{主角家族}。
...
3. 分章TXT (txt-chapters)
目录: releases/{project_id}/text/chapters/
特点:
- 每章单独文件
- 文件名:
0001_{章节标题}.txt - 便于分章上传
4. 起点中文网格式 (qidian)
目录: releases/{project_id}/platforms/qidian/
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 · 561 lines · 0 tokens per session scan A 2f5b7b25aa07
nw-release is a command published in the GitHub repository zhiliyouxian/claude-novel-writer (5 stars, last pushed 8mo ago), licensed MIT. It adds 16 tokens to every session and 3,952 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.
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.