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/expert)<a href="https://agentmods.dev/commands/wordflowlab/novel-writer/expert"><img src="https://agentmods.dev/badge/commands/wordflowlab/novel-writer/expert.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 | $0.00008 | $0.00772 |
| Opus 5 | $0.00004 | $0.00386 |
| Sonnet 5 | $0.00002 | $0.00154 |
| Haiku 4.5 | $0.00001 | $0.00077 |
Grade A, and why
expert 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.
What it actually says
专家模式
根据用户输入执行相应操作：
1. 列出可用专家（无参数时）
如果用户输入 /expert 不带参数，显示所有可用专家：
核心专家
-
plot - 剧情结构专家
- 精通三幕、英雄之旅、故事圈等叙事结构
- 分析情节问题、优化节奏、设计冲突升级
-
character - 人物塑造专家
- 人物弧光设计、动机分析、性格塑造
- 对话优化、声音区分、关系构建
-
world - 世界观设计专家
- 世界观构建、设定一致性、文化背景
- 规则体系、历史脉络、地理环境
-
style - 文风语言专家
- 叙述技巧、修辞手法、语言风格
- 文风统一、氛围营造、节奏把控
插件专家
扫描 plugins/ 目录，如果存在带有专家配置的插件，列出：
- 检查每个插件目录下的
config.yaml - 如果包含
experts字段，显示专家信息
使用示例：/expert plot 激活剧情结构专家
2. 激活专家模式
用户输入：/expert <type> （如 /expert plot）
执行步骤：
-
确认专家类型
- 核心专家：读取
experts/core/<type>.md - 插件专家：读取对应插件的专家文件
- 核心专家：读取
-
加载专家配置 读取专家定义文件，获取：
- 身份定位
- 专业领域
- 工作方式
- 分析框架
-
进入专家模式
✨ 已激活【<专家名称>】模式 [显示专家的自我介绍] 我现在会从专业角度为您提供 <领域> 方面的深度指导。 有什么可以帮助您的吗？ -
模式特征
- 保持专家视角和专业术语
- 提供深度分析而非快速答案
- 引用相关理论和方法论
- 主动提出诊断性问题
3. 专家模式行为准则
进入专家模式后：
- 保持专业身份：始终以该领域专家的视角交流
- 深度优先：提供详细分析而非简单建议
- 理论支撑：引用相关专业理论和框架
- 主动引导：通过提问帮助用户深入思考
- 持续模式：直到用户使用其他
/命令才退出
4. 退出专家模式
当用户使用任何其他 / 命令时：
- 自动退出专家模式
- 执行新命令
- 回到正常交互模式
无需显式退出命令，保持使用流畅性。
5. 错误处理
-
如果指定的专家不存在：
未找到专家类型：<type> 可用的专家有：plot, character, world, style 使用 /expert 查看所有可用专家 -
如果专家文件读取失败：
专家配置加载失败，请检查文件是否存在： experts/core/<type>.md
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 · 100 lines · 8 tokens per session scan A 920c4897a669
expert is a command published in the GitHub repository wordflowlab/novel-writer (940 stars, last pushed 10mo ago), licensed MIT. It adds 8 tokens to every session and 772 once invoked, about $0.0000 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.