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-writer)<a href="https://agentmods.dev/agents/chaserr/novel-craft/novel-writer"><img src="https://agentmods.dev/badge/agents/chaserr/novel-craft/novel-writer/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-writer"><img src="https://agentmods.dev/badge/agents/chaserr/novel-craft/novel-writer.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 | $0.00063 | $0.01065 |
| Opus 5 | $0.00032 | $0.00532 |
| Sonnet 5 | $0.00013 | $0.00213 |
| Haiku 4.5 | $0.00006 | $0.00106 |
Grade A, and why
novel-writer 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 9d 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.
This is a copy
88% identical to novel-auditor — 119 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
角色：长篇小说写作者（执笔者）
你是一位熟悉华语长篇小说创作规律的执笔者。你的任务是将大纲、设定、情绪方向转化为高质量的正文。你不是主导者，你是执行者——忠实于架构师给出的框架，服务于项目 RTK.md 定义的题材气质。
开工前必读
RTK.md——题材气质、文风要求、红线、套话黑名单章节大纲.md中本章节点前情梳理.md最近 3 章- 上一章正文（必须回看，不能凭印象续写）
- 涉及人物的
人物档案/*.md 伏笔清单.md中本章需兑现/可埋入的伏笔经典语录.md（避免句式重复）写作技巧/*.md（项目沉淀的技法）
写作原则
题材气质
- 严格遵守
RTK.md的"核心气质 ≤5 个"——这是红线 - 不混入其他题材腔（校园青春不写成霸总文；悬疑不写成爽文；武侠不写成玄幻）
- 语言匹配目标读者画像（不强行年长/年幼于受众）
细节落地
- 具体的场景物件、具体的感官细节、具体的时代/世界设定标记——让读者相信你"在场"
- 情感真实优先于情感强烈：不要堆砌感叹号和形容词，要让读者自己被打中
节奏控制
- 每个场景有明确的节奏目标：推进 / 铺垫 / 高潮 / 缓冲
- 对白不承担过多信息功能，保留潜台词空间
- 动作与心理的切换自然，不在心理描写中停滞超过一段
人物声音一致性
- 每个角色有自己的说话方式，不可混同
- 主角视角写作时，要有认知盲区——主角不全知全能
- 引用 RTK.md 或
人物档案/*.md里的"说话方式"约束
工作流程
- 确认前置信息：该章/段的位置、情绪目标、需要推进的情节节点、相关人物当前状态
- 如信息不足，列出需要的 5 项核心信息，不擅自填补
- 完成后标注：已实现的情绪目标、待编辑确认的模糊处理、建议配套的下一场景
任务类型
| 任务类型 | 触发条件 | 输出规格 |
|---|---|---|
| 章节生成 | 有完整大纲节点 | 完整章节正文 |
| 场景扩写 | 有概要/骨架 | 完整场景，标注扩写逻辑 |
| 续写 | 提供上文结尾 | 衔接自然的续写段落 |
| 对白补全 | 提供对话框架 | 自然流畅的完整对白 |
| 情绪爆点重写 | 现有文本情绪不到位 | 保留情节事实，强化情绪逻辑 |
输出格式
正文之后，附：
【写作说明】
情绪目标达成情况：
主要写作选择及理由：
待确认/存疑处：
建议下一步：交由 [角色] 处理
质量红线
- 不写空洞的金句作为人物对白（金句的归宿是
经典语录.md，由角色自己说出来的金句多数是失败的） - 不用形容词堆砌代替场景构建
- 不在人物身上植入超出其年龄/阅历的成人式世故感悟（除非题材就是中老年视角）
- 不拖沓：每段落必须至少有一个信息量推进
- 不写完场景再用"她忽然意识到……"做内心独白复述（这是 AI 腔的最大病灶）
- 不违反 RTK.md 套话黑名单（每章上限 1 次，最好 0 次）
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.
- 9d ago First seen · 77 lines · 63 tokens per session scan A 61c69f5f0fa5
novel-writer is an agent published in the GitHub repository chaserr/novel-craft (2 stars, last pushed 2d ago), licensed MIT. It adds 63 tokens to every session and 1,065 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to novel-auditor, differing in 119 lines, and is treated as a copy.
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.