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.
npx agentmods add commands/wordflowlab/novel-writer/specifygit 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/specify)<a href="https://agentmods.dev/commands/wordflowlab/novel-writer/specify"><img src="https://agentmods.dev/badge/commands/wordflowlab/novel-writer/specify.svg" alt="Measured on agentmods" 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 | $0.00011 | $0.01710 |
| Opus 5 | $0.00005 | $0.00855 |
| Sonnet 5 | $0.00002 | $0.00342 |
| Haiku 4.5 | $0.00001 | $0.00171 |
Grade A, and why
specify 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 6d 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
用户输入描述了他们想要创作的故事。基于这个描述，创建一个完整的故事规格文档。
用户输入： $ARGUMENTS
目标
像产品规格书（PRD）一样定义故事，明确"要创造什么"而非"如何创造"。输出带有 [需要澄清] 标记的规格，为后续澄清步骤留出空间。
执行步骤
1. 初始化故事规格
运行 {SCRIPT} 获取路径信息：
- 解析 JSON 获取
STORY_NAME和SPEC_PATH - 如果是新故事，创建规格文件
- 如果已存在，准备更新
2. 检查宪法合规性
如果存在 memory/novel-constitution.md：
- 加载宪法原则
- 确保规格符合宪法价值观
- 在规格中引用相关原则
3. 创建故事规格文档
使用以下结构创建规格：
# 故事规格书
## 元数据
- 故事名称：[名称]
- 版本：1.0.0
- 创建日期：[YYYY-MM-DD]
- 状态：草案
- 作者：[作者名]
## 一、故事概要
### 一句话故事（电梯演讲）
[30字以内描述故事核心]
### 故事简介（100-200字）
[扩展描述，包含主要冲突和结局暗示]
### 核心主题
- 主题：[如"成长"、"救赎"、"复仇"]
- 深层含义：[想要表达什么]
- 情感内核：[希望读者感受到什么]
## 二、目标定位
### 目标读者画像
- 年龄段：[需要澄清：具体年龄范围]
- 性别倾向：[需要澄清：男性向/女性向/通用]
- 阅读层次：[需要澄清：入门/进阶/资深]
- 类型偏好：[玄幻/都市/历史等]
- 阅读场景：[碎片时间/深度阅读]
### 市场定位
- 类型标签：[主标签] + [副标签]
- 竞品分析：类似[作品1]的[特点] + [作品2]的[特点]
- 差异化：[需要澄清：核心卖点是什么]
## 三、成功标准
### 量化指标
- 目标字数：[需要澄清：3万/10万/50万]
- 更新频率：[需要澄清：日更/周更/月更]
- 完成时间：[预计时长]
- 商业目标：[如适用]
### 质量标准
- 逻辑一致性：[必须/应该]无明显漏洞
- 人物丰满度：主角有[X]个层次，配角有[Y]个层次
- 情节紧凑度：[需要澄清：每章都有冲突/允许过渡章节]
- 文字水准：[需要澄清：通俗易懂/文学性/专业性]
### 读者反馈指标
- 目标评分：[如适用]
- 互动率：[评论/收藏比例]
- 完读率：[期望的读者完成度]
## 四、核心需求
### 必须包含（P0）
1. [核心情节元素1]
2. [核心人物关系]
3. [核心冲突设定]
4. [必要的世界观元素]
### 应该包含（P1）
1. [增强体验的元素]
2. [深化主题的内容]
3. [丰富人物的支线]
### 可以包含（P2）
1. [锦上添花的内容]
2. [可选的支线]
3. [额外的彩蛋]
## 五、约束条件
### 内容红线
- 绝对禁止：[如违法内容]
- 需要避免：[如敏感话题]
- 谨慎处理：[需要澄清：如何处理情感关系]
### 创作约束
- 知识限制：[需要澄清：是否需要专业知识]
- 时间限制：[完成期限]
- 资源限制：[如需要的参考资料]
### 技术约束
- 发布平台：[需要澄清：网文平台/出版/自媒体]
- 格式要求：[章节长度等]
- 更新要求：[固定时间等]
## 六、风险评估
### 创作风险
- 写作难度：[需要澄清：挑战在哪里]
- 灵感枯竭：[如何应对]
- 逻辑漏洞：[复杂度评估]
### 市场风险
- 同质化：[如何差异化]
- 读者接受度：[需要澄清：创新是否过度]
- 时效性：[题材是否会过时]
## 七、核心决策点 [需要澄清]
以下关键决策需要在 `/clarify` 阶段明确：
1. [决策1：如主角性格是热血还是冷静]
2. [决策2：如结局是开放还是圆满]
3. [决策3：如叙事是单线还是多线]
4. [决策4：如节奏是快速还是缓慢]
5. [决策5：如风格是轻松还是严肃]
## 八、验证清单
- [ ] 故事概要清晰明确
- [ ] 目标读者定义准确
- [ ] 成功标准可衡量
- [ ] 核心需求已列出
- [ ] 约束条件已识别
- [ ] 风险已评估
- [ ] 关键决策点已标记
## 附录：参考资料
### 灵感来源
- [来源1]
- [来源2]
### 参考作品
- [作品1]：参考其[特点]
- [作品2]：参考其[特点]
### 补充说明
[其他需要说明的内容]
4. 标记需要澄清的点
在规格中标记所有需要进一步澄清的决策点：
- 使用
[需要澄清：具体问题]格式 - 确保标记 5-10 个关键决策点
- 这些将在
/clarify步骤中处理
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.
- 6d ago First seen · 209 lines · 11 tokens per session scan A d2b352db5d0c
specify is a command published in the GitHub repository wordflowlab/novel-writer (939 stars, last pushed 10mo ago), licensed MIT. It adds 11 tokens to every session and 1,710 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 2026-08-30.
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.