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/clarify)<a href="https://agentmods.dev/commands/wordflowlab/novel-writer/clarify"><img src="https://agentmods.dev/badge/commands/wordflowlab/novel-writer/clarify.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 | $0.00022 | $0.01666 |
| Opus 5 | $0.00011 | $0.00833 |
| Sonnet 5 | $0.00004 | $0.00333 |
| Haiku 4.5 | $0.00002 | $0.00167 |
Grade A, and why
clarify 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 8d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
用户输入可以直接提供或作为命令参数 - 你必须在继续之前考虑它(如果不为空)。
用户输入: $ARGUMENTS
目标
检测并减少故事大纲中的歧义或缺失的决策点,通过交互式问答收集澄清信息,并将结果记录在故事文件中。
注意:此澄清流程应在 /outline 之前运行并完成。如果用户明确表示跳过澄清(例如,探索性创作),可以继续,但必须警告下游返工风险会增加。
执行步骤
1. 初始化检查
运行 {SCRIPT} 获取当前故事路径:
- 解析 JSON 获取
STORY_PATH和STORY_NAME - 如果没有找到故事文件,提示用户先运行
/story创建故事大纲 - 加载故事文件内容进行分析
2. 结构化歧义扫描
对故事大纲进行全面扫描,评估每个类别的清晰度(清晰/部分清晰/缺失):
创作定位
- 目标读者群体(年龄段、性别倾向、阅读层次)
- 作品定位(商业爽文/严肃文学/类型小说)
- 预期规模(短篇3-5万/中篇10-20万/长篇50万+)
世界观设定
- 时代背景精确度(具体年份/朝代/架空程度)
- 世界规则(魔法体系/科技水平/社会制度)
- 地理范围(单一城市/多国/大陆/星际)
角色设计
- 主角成长曲线(废柴逆袭/天才型/稳扎稳打)
- 主角性格基调(热血/冷静/腹黑/圣母)
- 配角功能定位(推动剧情/情感支撑/对比反衬)
- 反派智商设定(降智反派/势均力敌/高维碾压)
叙事策略
- 视角选择(第一人称/第三人称限定/上帝视角)
- 时间线结构(线性叙事/倒叙插叙/多线并行)
- 叙事节奏(快节奏爽文/慢热铺垫/张弛有度)
情节核心
- 核心冲突类型(人vs人/人vs自然/人vs社会/人vs自我)
- 主线目标明确度(复仇/成长/拯救/探索)
- 结局倾向(大团圆/悲剧/开放式)
风格基调
- 文风选择(白话流畅/古风典雅/幽默诙谐/冷峻写实)
- 描写侧重(动作场面/心理描写/环境氛围/对话推进)
- 情感基调(热血激昂/压抑黑暗/温馨治愈/虐心催泪)
创作约束
- 敏感内容处理(violence程度/情感尺度)
- 价值观导向(正能量/现实主义/批判性)
- 更新计划(日更/周更/月更)
对每个"部分清晰"或"缺失"的类别生成候选问题,除非:
- 澄清不会实质影响创作方向
- 信息更适合在章节规划阶段确定
3. 生成优先问题队列
内部生成最多5个优先澄清问题,应用以下约束:
- 整个会话最多5个问题
- 每个问题必须可以通过以下方式之一回答:
- 多选题(2-5个互斥选项)
- 简答题(限制5个词以内)
- 只包含对创作方向有实质影响的问题
- 确保类别覆盖平衡,优先高影响领域
- 如果超过5个类别需要澄清,选择(影响力×不确定性)最高的5个
4. 顺序问答循环
一次展示一个问题
多选题格式:
| 选项 | 说明 |
|------|------|
| A | 选项A的详细说明 |
| B | 选项B的详细说明 |
| C | 选项C的详细说明 |
简答题格式:
请简要回答(5个词以内):_______
处理用户回答
- 验证答案有效性
- 如有歧义,请求快速澄清
- 记录答案并继续下一个问题
停止条件
- 所有关键歧义已解决
- 用户示意完成("好了"、"够了"、"不用了")
- 已达到5个问题上限
5. 整合澄清结果
每个接受的答案后立即:
首次整合时
- 在故事大纲中创建
## 澄清记录章节(如不存在) - 添加
### 澄清会话 [日期]子标题
记录格式
- 问:[问题内容] → 答:[用户答案]
更新相关章节 根据澄清内容更新故事大纲的对应部分:
- 创作定位 → 更新故事概述
- 世界观 → 更新世界观设定
- 角色 → 更新角色设定
- 叙事策略 → 添加到创作说明
- 风格基调 → 添加到风格指南
6. 验证与保存
每次更新后验证:
- 澄清记录完整性
- 没有遗留的模糊标记被新答案解决
- 没有矛盾的陈述
- Markdown 格式正确
将更新后的内容写回故事文件。
7. 完成报告
报告包含:
- 提问和回答的问题数量
- 更新的故事文件路径
- 触及的章节列表
- 覆盖率总结表:
| 类别 | 状态 |
|---|---|
| 创作定位 | ✅ 已澄清 |
| 世界观设定 | ✅ 已澄清 |
| 角色设计 | ⏸ 延迟到规划 |
| ... | ... |
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.
- 8d ago First seen · 175 lines · 22 tokens per session scan A 63897005c9c9
clarify is a command published in the GitHub repository wordflowlab/novel-writer (940 stars, last pushed 10mo ago), licensed MIT. It adds 22 tokens to every session and 1,666 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.
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.