plan-enhance

plan-enhance is a command for Claude Code from wordflowlab/novel-writer. It costs 0 tokens per session (659 once invoked), scanned A, original, MIT.

An optional writing-planning aid that searches genre-specific knowledge files and applies relevant guidance to a story plan. A genre is a category such as fantasy, urban fiction, or a story about starting over.

In plain words
What is it for?
Use it to identify a story’s genre, find matching planning guidance, and shape openings, scenes, conflicts, or chapter plans.
Why use it?
It keeps planning advice focused on the story’s type instead of loading unrelated material or applying every rule indiscriminately.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Good fit Use it to identify a story’s genre, find matching planning guidance, and shape openings, scenes, conflicts, or chapter plans.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/wordflowlab/novel-writer/plan-enhance
Install

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.

Clone the repo
git clone --depth 1 https://github.com/wordflowlab/novel-writer

Made for: Claude Code.

Wrote 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.

agentmods badge for plan-enhance

README.md
[![agentmods](https://agentmods.dev/badge/commands/wordflowlab/novel-writer/plan-enhance/github.svg)](https://agentmods.dev/commands/wordflowlab/novel-writer/plan-enhance)
Your own site
<a href="https://agentmods.dev/commands/wordflowlab/novel-writer/plan-enhance"><img src="https://agentmods.dev/badge/commands/wordflowlab/novel-writer/plan-enhance/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.

agentmods 80×15 button for plan-enhance

Your own site · 80×15
<a href="https://agentmods.dev/commands/wordflowlab/novel-writer/plan-enhance"><img src="https://agentmods.dev/badge/commands/wordflowlab/novel-writer/plan-enhance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 659 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00659
Opus 5 $0.00000 $0.00329
Sonnet 5 $0.00000 $0.00132
Haiku 4.5 $0.00000 $0.00066

Measured 10d ago against content hash 752a2326c8ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

plan-enhance 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.

plugins/genre-knowledge/commands/plan-enhance.md · 63 lines

What it actually says

🆕 可选:动态加载类型知识(genre-knowledge插件)

如果plugins/genre-knowledge/目录存在,你可以动态搜索并应用类型化写作知识。

知识搜索策略

步骤1:识别故事类型

  • story.md中提取类型标签(如"玄幻"、"爽文"、"都市重生"等)
  • 如无明确标签,根据故事内容(金手指、世界观、冲突类型)推断

步骤2:搜索相关知识

使用Glob搜索知识文件(按优先级):

  1. 通用方法论(所有类型适用):

    plugins/genre-knowledge/knowledge/fundamentals/*.md
    

    推荐优先阅读:

    • emotion-value-core-laws.md - 五大商业创作法则
    • scene-mru-structure.md - MRU场景结构(目标-冲突-决定)
  2. 类型专属知识(根据识别的类型):

    plugins/genre-knowledge/knowledge/genres/*{类型关键词}*.md
    

    示例:

    • 爽文类型:搜索 *shuangwen*.md
    • 玄幻类型:搜索 *xuanhuan*.md
    • 都市类型:搜索 *urban*.md

步骤3:知识应用原则

  • 🎯 优先级:类型专属知识 > 通用方法论 > 通用规范
  • 📖 选择性应用:快速浏览文件,提取与当前章节规划相关的知识点
  • ⚠️ 不要全盘照搬:知识文件是参考,需结合具体故事情况灵活应用
  • 🔍 按需搜索:不要一次性加载所有知识,只在需要时搜索相关内容
应用示例

场景:规划一部"都市重生爽文"的开篇3章

搜索知识:

Glob: plugins/genre-knowledge/knowledge/fundamentals/emotion-value-core-laws.md
Glob: plugins/genre-knowledge/knowledge/genres/shuangwen-golden-opening.md

提取要点:

  • 从五大法则中应用"极限铺垫原则"(开篇构建困境)
  • 从黄金开篇中应用"动态场景切入"和"核心冲突前置"

规划应用:

  • 第1章:动态场景切入重生瞬间,立刻展现主角困境
  • 第2章:简要揭示重生金手指(核心信息差)
  • 第3章:完成第一个小逆袭(打脸爽点)
注意事项
  • ⚠️ 知识文件基于商业网文创作经验,不适合所有类型
  • ⚠️ 不要让知识约束创意,保持故事的独特性
  • ⚠️ 如果故事不属于商业类型文,可以跳过此部分
Changes

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.

  1. 10d ago First seen · 63 lines · 0 tokens per session scan A 752a2326c8ee

Subscribe to this mod's changes

plan-enhance is a command published in the GitHub repository wordflowlab/novel-writer (943 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 659 tokens. 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.