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/write)<a href="https://agentmods.dev/commands/wordflowlab/novel-writer-skills/write"><img src="https://agentmods.dev/badge/commands/wordflowlab/novel-writer-skills/write/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/write"><img src="https://agentmods.dev/badge/commands/wordflowlab/novel-writer-skills/write.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 | $0.00017 | $0.04915 |
| Opus 5 | $0.00009 | $0.02457 |
| Sonnet 5 | $0.00003 | $0.00983 |
| Haiku 4.5 | $0.00002 | $0.00492 |
Grade A, and why
write 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 10d 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 — 477 lines — stays where its author put it; the contents beside it link to each section on GitHub.
基于七步方法论流程执行章节写作。
前置检查
- 运行脚本
{SCRIPT}检查创作状态
查询协议（必读顺序）
⚠️ 重要：请严格按照以下顺序查询文档，确保上下文完整且优先级正确。
查询顺序：
-
先查（最高优先级）：
memory/constitution.md（创作宪法 - 最高原则）memory/style-reference.md（风格参考 - 如果通过/book-internalize生成）
-
再查（规格和计划）：
stories/*/specification.md（故事规格）stories/*/creative-plan.md（创作计划）stories/*/tasks.md（当前任务）
2.5. 自动加载写作风格和规范（基于配置）：
- 读取
specification.md的 YAML frontmatter - 检查是否配置了
writing-style（写作风格） - 检查是否配置了
writing-requirements（写作规范）
如果配置了 writing-style，加载对应风格文档：
---
writing-style: natural-voice
---
则读取：.claude/knowledge-base/styles/natural-voice.md
如果配置了 writing-requirements，加载对应规范文档：
---
writing-requirements:
- anti-ai-v4
- fast-paced
---
则读取：
.claude/knowledge-base/requirements/anti-ai-v4.md.claude/knowledge-base/requirements/fast-paced.md
⚠️ 优先级说明：
- 风格文档（styles）的优先级高于 spec/presets/ 中的旧版规范
- 规范文档（requirements）会叠加应用（所有配置的规范都生效）
- 如果未配置，则使用默认的 spec/presets/ 规范
-
再查（状态和数据）：
spec/tracking/character-state.json（角色状态）spec/tracking/relationships.json（关系网络）spec/tracking/plot-tracker.json（情节追踪 - 如有）spec/tracking/validation-rules.json（验证规则 - 如有）
-
再查（知识库）：
spec/knowledge/相关文件（世界观、角色档案等）stories/*/content/（前文内容 - 了解前情）
-
再查（写作规范）：
memory/personal-voice.md（个人语料 - 如有）spec/knowledge/natural-expression.md（自然化表达 - 如有）spec/knowledge/punctuation-personality.md（标点个性化 - 如有）spec/knowledge/detail-formulas.md（具象化公式 - 如有）spec/presets/anti-ai-detection.md（反AI检测规范）
-
条件查询（前三章专用）：
- 如果章节编号 ≤ 3 或总字数 < 10000字，额外查询：
spec/presets/golden-opening.md（黄金开篇法则）- 并严格遵循其中的五大法则
- 如果章节编号 ≤ 3 或总字数 < 10000字，额外查询：
⚠️ 强制完成确认（解决失焦问题的关键）
在开始写作前，你必须明确列出已读取的核心文件：
📋 写作前检查清单（已完成）：
✓ 1. memory/constitution.md - 创作宪法
✓ 2. memory/style-reference.md - 风格参考（如有）
✓ 3. stories/*/specification.md - 故事规格
✓ 4. stories/*/creative-plan.md - 创作计划
✓ 5. stories/*/tasks.md - 当前任务
✓ 6. spec/tracking/character-state.json - 角色状态
✓ 7. spec/tracking/relationships.json - 关系网络
✓ 8. spec/tracking/plot-tracker.json - 情节追踪（如有）
✓ 9. spec/tracking/validation-rules.json - 验证规则（如有）
🎨 写作风格和规范（基于配置）：
✓ 写作风格：[style-name]（如配置）或 无配置
✓ 写作规范：[requirement-1, requirement-2, ...]（如配置）或 无配置
📊 上下文加载状态：✅ 完成
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.
- 10d ago First seen · 477 lines · 17 tokens per session scan A bec6a0ba0ecf
write is a command published in the GitHub repository wordflowlab/novel-writer-skills (258 stars, last pushed 10mo ago), licensed MIT. It adds 17 tokens to every session and 4,915 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.