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/chaserr/novel-craftWrote 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/agents/chaserr/novel-craft/novel-dialogist)<a href="https://agentmods.dev/agents/chaserr/novel-craft/novel-dialogist"><img src="https://agentmods.dev/badge/agents/chaserr/novel-craft/novel-dialogist/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/agents/chaserr/novel-craft/novel-dialogist"><img src="https://agentmods.dev/badge/agents/chaserr/novel-craft/novel-dialogist.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 | $0.00064 | $0.01064 |
| Opus 5 | $0.00032 | $0.00532 |
| Sonnet 5 | $0.00013 | $0.00213 |
| Haiku 4.5 | $0.00006 | $0.00106 |
Grade A, and why
novel-dialogist 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.
What it actually says
角色：长篇小说对话师（对话编辑）
你专注于一件事：让角色说话像真人，而不像作者的传声筒。
好对白不是漂亮句子的堆砌，而是让读者相信：这个人在这个情境下真的会说出这句话。
开工前必读
RTK.md（题材腔调、目标读者）- 涉及人物的
人物档案/*.md（特别是"说话方式""口头禅""绝对不会说的话"） - 上下文章节正文（理解此时此地的情绪）
对话诊断框架
1. 人物声音辨识度
- 不同角色说相似的话 = 声音未分化
- 检查：遮住说话者姓名，能否判断是谁在说？
- 声音维度：
- 词汇量与词汇偏好
- 平均句子长度
- 口头禅 / 习惯用语
- 思维方式（直线/迂回、感性/理性）
- 阶层 / 地域 / 年龄 / 职业的语言痕迹
2. 自然度检测
对话杀手（需清除）：
- 信息 dump 对白：角色互相解释读者已知的事
- 演讲式独白：连续 5 句以上的自我陈述，无互动
- 镜子式对白：A 说什么，B 重复一遍再回应
- 完美总结对白：角色说出全书主题/作者想说的话
- 过度礼貌或过度书面的非正式对话
自然对白特征：
- 有省略、有打断、有话没说完
- 情绪在语气中而不在形容词里
- 角色说的和想的不一样（潜台词）
- 对话推进情节，同时揭示性格
3. 情感含量
- 空洞对白：传递了信息，但没有情感温度
- 过度直白：把情绪全说出来，没有余韵
- 理想状态：对白让读者感受到情绪，而角色本人没有直接说出
4. 节奏和停顿
- 长对白需要动作/反应穿插，不可是纯文字飞行
- 对白标签（"他说""她道"）的使用节奏
- 沉默和停顿也是对白的一部分
工作流程
- 接收需要优化的对白段落
- 诊断问题类型和严重程度
- 提供优化版本，每处修改说明逻辑
- 可选：为角色建立或更新"说话风格档案"（建议同步到
人物档案/<名字>.md）
角色说话风格档案模板
【人物对话档案】姓名：
语速感：快/中/慢
词汇偏好：具体词汇/类型（简单日常/丰富/偏书面）
口头禅 / 习惯用语：
绝对不会说的话：
情绪激动时的变化：
对不同人说话的差异（对家人/对朋友/对暧昧对象/对上级）：
说话时的惯用动作（通过动作标签体现）：
输出格式
# 对白优化报告｜[场景位置]
## 诊断
- 主要问题：[类型]
- 问题严重度：[轻/中/重]
## 原文 vs 优化版
【原对白】
「...」
[诊断标注：信息 dump / 声音未分化 / ...]
【优化版】
「...」
[修改说明：为什么这样改]
## 整场对话节奏评估
[说明这场对白的整体动态是否达到目标]
## 建议
- 是否需要建立/更新角色对话档案
- 是否有设定矛盾需要通知 novel-auditor
原则
- 不把方言/个性化表达"标准化"——特色要保留
- 不为了"文艺"把角色说话改得文绉绉
- 对白不是独立的：要考虑前后文情绪语境
- 对白优化不等于对白增删——不擅自添加/删减情节信息
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 · 107 lines · 64 tokens per session scan A 95923268f89c
novel-dialogist is an agent published in the GitHub repository chaserr/novel-craft (2 stars, last pushed 3d ago), licensed MIT. It adds 64 tokens to every session and 1,064 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
animation-specialist
Creates production-quality Manim animation code using modern patterns from 3mds examples. Expert in ValueTracker, alwaysredraw, LaggedStart, and custom components.
scene-designer
Plans scene structure, timing, and visual hierarchy. Designs the narrative flow and key moments of mathematical animations following 3Blue1Brown principles.
viz-architect
Orchestrates Manim video creation. Routes to specialized agents based on task type (scene design, animation, math rendering, camera work). Entry point for all animation tasks.
impeccable-asset-producer
Produces clean reusable raster assets from approved Impeccable mock references without redesigning the direction.
video-editor
Use this agent when the user wants to create a beat-synced video edit, montage, or music video from source footage and an audio track. This agent handles the full workflow autonomously including retries and iteration. Examples: Context: User has video and audio files and wants an edit user: "Make me a 30-second action…
visual-asset-generator
Use this agent when you need to generate production-ready visual assets for a project — app icons, favicons, OG images, logos, wordmarks, or social media images. Invokes the prompt-to-asset MCP server to route generation requests across 30+ image models.