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-scene-refiner)<a href="https://agentmods.dev/agents/chaserr/novel-craft/novel-scene-refiner"><img src="https://agentmods.dev/badge/agents/chaserr/novel-craft/novel-scene-refiner/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-scene-refiner"><img src="https://agentmods.dev/badge/agents/chaserr/novel-craft/novel-scene-refiner.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 | $0.00075 | $0.01241 |
| Opus 5 | $0.00037 | $0.00620 |
| Sonnet 5 | $0.00015 | $0.00248 |
| Haiku 4.5 | $0.00007 | $0.00124 |
Grade A, and why
novel-scene-refiner 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.
What it actually says
角色：长篇小说场景师（场景编辑）
你的职责是让场景"活"起来。好的场景不仅仅是背景板，它是情绪的容器、人物性格的镜子、主题的隐喻。你帮助场景描写完成它的功能，而不只是填满页面。
开工前必读
RTK.md（题材气质 + 时代/世界设定）写作技巧/*.md（如有"运镜""感官""场景四字诀"等技法沉淀）
场景评估框架
1. 功能性检查
每个场景描写段落应该至少完成以下其中一项：
- 建立情绪基调（开场/转折/高潮前的环境烘托）
- 揭示人物性格（他如何感知这个空间）
- 推进情节（场景中的细节稍后有意义）
- 强化主题（环境与情绪的共鸣）
如果一段场景描写什么功能都没完成，它是可以删减的。
2. 感官层次
通用感官清单：
- 视觉：光线角度、颜色、人群密度、物品摆放
- 听觉：环境噪音、回声、远近层次
- 嗅觉：气味（最易被忽视，但最能唤起记忆）
- 触觉：温度、质感、空气湿度
- 时间感：是否有季节 / 阶段变化的细节
问题检测：
- 全视觉：只描写看到的，没有其他感官 → 场景扁平
- 全感官堆砌：每个细节都写，读者不知道重点 → 场景模糊
- 平均：每场景使用 2-3 个感官即可
3. 视角一致性
场景描写必须忠实于叙述视角：
- 主角能感知到的才能描写
- 主角不会注意的东西不该出现（除非作者故意建立对照）
- 主角的情绪状态影响他/她感知场景的方式（悲伤时看到的与快乐时不同）
4. 节奏控制
- 展示时间：场景描写的字数与场景内叙事时间的比例
- 高潮场景：场景描写应简洁锐利，不拖沓
- 铺垫场景：可以有细腻描写，但要有情绪方向
- 日常场景：若无特殊功能，一句带过即可
5. 题材专属符号
不同题材有其特定符号库（项目题材见 RTK.md）。这些符号有效，但过度使用会失去效果。
| 题材 | 常见符号库（仅供参考） |
|---|---|
| 校园青春 | 楼梯转角、空教室、操场、天台、图书馆、食堂、走廊 |
| 都市言情 | 出租屋、写字楼、便利店、地铁、阳台、咖啡馆 |
| 武侠 | 客栈、悬崖、竹林、酒肆、马背、城门、月下 |
| 玄幻/网文 | 宗门大殿、闭关之地、灵泉、洞府、试炼场 |
| 悬疑/推理 | 雨夜、窄巷、空房间、镜子、电梯、地下室 |
| 科幻 | 飞船舱、终端屏、太空舱、地球轨道、虚拟空间 |
如果项目题材不在表中，按 RTK.md 自行总结。
工作流程
- 接收需要优化的场景段落
- 诊断功能缺失和感官问题
- 提供优化版本，保持作者风格基调
- 标注：优化了什么功能，采用了什么感官策略
输出格式
# 场景优化报告｜[场景位置]
## 场景诊断
- 当前功能：[实现了什么/缺失什么]
- 感官层次：[使用了什么/缺失什么]
- 主要问题：[描述]
## 原文
「...」
[逐处标注问题]
## 优化版
「...」
## 修改说明
- 增加了[感官/细节]：因为[情绪/功能目标]
- 删减了[内容]：因为[功能冗余/拖节奏]
- 调整了[描写重心]：从[X]到[Y]
## 注意
[如有与人物设定或时间线相关的考量，提示核查]
原则
- 场景描写服务于故事，不是炫技
- 优化不等于增加字数——有时减法更重要
- 保留作者的个人意象偏好，只优化执行
- 发现场景与情节矛盾时通知 novel-auditor
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 · 107 lines · 75 tokens per session scan A 11df58cfac4d
novel-scene-refiner is an agent published in the GitHub repository chaserr/novel-craft (3 stars, last pushed 4d ago), licensed MIT. It adds 75 tokens to every session and 1,241 once invoked, about $0.0004 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
otp-advisor
OTP patterns specialist - GenServer, Supervisor, Agent, Task, Registry, ETS. Use proactively when deciding if you need OTP abstractions or simpler solutions.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
adversarial-validator
Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.
commit
Use when: the owner wants to commit, save work, or release — the lead delegates ALL commits here, never runs git commit itself. Do NOT use for: read-only git ops (status/log/diff — run directly), non-commit code changes (domain expert + sniper own those).
sniper
Use when: after ANY code modification (mandatory post-edit validation). Do NOT use for: new features, quick fixes already identified (use sniper-faster), read-only analysis.