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-writer-skillsWrote 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-skills/clarify)<a href="https://agentmods.dev/commands/wordflowlab/novel-writer-skills/clarify"><img src="https://agentmods.dev/badge/commands/wordflowlab/novel-writer-skills/clarify/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/wordflowlab/novel-writer-skills/clarify"><img src="https://agentmods.dev/badge/commands/wordflowlab/novel-writer-skills/clarify.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 | $0.00027 | $0.02397 |
| Opus 5 | $0.00014 | $0.01198 |
| Sonnet 5 | $0.00005 | $0.00479 |
| Haiku 4.5 | $0.00003 | $0.00240 |
Grade A, and why
clarify scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
焦点区域（可选）：$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 /plan 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
3.5 问题设计原则（对话式理解）
每个问题应当像真人写手在交流，而不是工程师在填表。
核心原则：
- ✅ 先说观察，再问问题：让作者明白"为什么要问这个"
- ✅ 说人话：用创作者的语言，而不是分类学术语
- ✅ 指出影响：让作者理解这个决策会影响什么
- ❌ 避免直接抛问题：不要一上来就"请问你的目标读者是？"
对比示例：
❌ 工程化提问（避免）：
问题1：你的目标读者是什么年龄段？
A. 18-25岁 B. 26-35岁 C. 36-45岁
✅ 对话式提问（推荐）：
💬 我注意到你的故事有校园元素，但也有职场内容。这两个场景对应的读者群体差异很大——
校园读者喜欢热血成长，职场读者更关注权谋博弈。这会直接影响我们的节奏设计和价值观表达。
所以想先确认：**你主要想写给谁看？**
| 选项 | 说明 |
|------|------|
| A | 学生群体（18-25岁）- 侧重成长和理想主义 |
| B | 职场人士（26-35岁）- 侧重现实和策略思维 |
| C | 通吃（调整为双线叙事，兼顾两者）|
| D | 自定义（请输入你的想法）|
提问结构模板：
💬 [观察到的现象/矛盾点]。[这会影响什么创作决策]。
所以想确认：**[核心问题]**
[选项表格或简答提示]
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 · 237 lines · 27 tokens per session scan A 3a3c4d7e3882
clarify is a command published in the GitHub repository wordflowlab/novel-writer-skills (258 stars, last pushed 10mo ago), licensed MIT. It adds 27 tokens to every session and 2,397 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.