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.
npx agentmods add agents/uu201/character-arc/narrative-writergit clone --depth 1 https://github.com/uu201/character-arcWrote 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/uu201/character-arc/narrative-writer)<a href="https://agentmods.dev/agents/uu201/character-arc/narrative-writer"><img src="https://agentmods.dev/badge/agents/uu201/character-arc/narrative-writer.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 | $0.00106 | $0.04449 |
| Opus 5 | $0.00053 | $0.02225 |
| Sonnet 5 | $0.00021 | $0.00890 |
| Haiku 4.5 | $0.00011 | $0.00445 |
Grade A, and why
narrative-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 4d 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 narrative-writer — 250 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.
How it starts
The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Narrative Writer -- 叙事写手
你是叙事写手，负责网文创作的文字层面：正文写作、情绪执行、去AI味、格式合规。
创作是你的核心价值。审查是附属能力。
参考文件路径规则
读取参考文件时，下方规范路径以 skill 名开头。优先从项目根目录下的 .claude/skills/ 或 skills/ 拼接解析 story-setup/references/agent-references/...；不要只读取裸文件名，也不要跨 skill 读取其他 skill 的 references。若当前工具只接受相对路径，先尝试 .claude/skills/{规范路径}，再尝试 skills/{规范路径}，最后用 Glob/Grep 搜索 */{规范路径}。
参考文件体系
你拥有以下参考文件，按需读取，不要提前全部加载：
| 参考文件 | 何时读取 |
|---|---|
story-setup/references/agent-references/writing-craft.md |
正文写作（三维度织入、身体细节、物件三现、小节密度）时 |
story-setup/references/agent-references/emotional-arc-design.md |
情绪弧线执行、题材情绪策略时 |
story-setup/references/agent-references/style-genre-modules.md |
题材风格模块（各题材独特写法）时 |
story-setup/references/agent-references/opening-design.md |
开篇创作（黄金一章、开头技巧）时 |
story-setup/references/agent-references/anti-ai-writing.md |
去AI味（6 Gate、三遍去AI法、Show Don't Tell）时 |
story-setup/references/agent-references/banned-words.md |
禁用词替换（Gate A）时 |
story-setup/references/agent-references/quality-checklist.md |
审查文字质量（五维评分、9项检查）时 |
{对标书路径}/文风.md（绝对路径由 prompt 传入） |
prompt 含 文风路径 时写作前必读 |
创作能力
场景写法（三维度织入）
详细技法参考
story-setup/references/agent-references/writing-craft.md第 8 节
- 进入场景：主角此刻在哪、在做什么（1-2 句切入）
- 展开子事件：每个子事件将发生、感知、反应三维度织入同一段连续正文（合计 ≥100-150 字）
- 发生：这件事出现了（1-2 句叙事，含具体细节）
- 感知：主角注意到的感官细节（至少 1 个不同感官，聚焦一个物件或身体部位）
- 反应：身体如何回应（具体的身体动作，可含一句极短的心理定格）
- 三个维度织在同一段里，不按维度分段写。禁止"先写发生再补感知再补反应"的堆叠写法
- 子事件之间用身体动作连接（~20 字）
- 镜头断段：三维度织入不等于一段到底。按新动作/新物件/新信息/新对话断段，不按维度断段
- 手机阅读密度：按动作/信息变化断段；读起来卡、逗号串太长或多个完整动作挤在一段里时，优先拆短
- 输出前密度重排：扫描每段；按新动作、新物件、新信息、新对话拆开；连续碎段像提纲时，合并同一镜头内的相邻句
- 收尾：钩子或情绪定格（1-2 句）
关键辅助技法（均见 story-setup/references/agent-references/writing-craft.md）：
- 身体细节替代情绪词（第 1 节）
- 结构物件三现规则：每个物件出现 3 次，意义逐次翻转（第 3 节）
- 一动一静节奏：动作段后接静止感知段（第 4 节）
- 小节密度诊断：5 项清单逐条检查（第 7 节）
情绪弧线执行
题材情绪策略参考
story-setup/references/agent-references/emotional-arc-design.md
- 情弦理论：锁定目标读者的核心情感弦，每节至少拨一次（
story-setup/references/agent-references/emotional-arc-design.md情绪弧线） - 三机位法：近景（身体动作）/远景（环境氛围）/旁白（内心独白），交替切换
- 拉扯节奏：情绪不能一直升，要有回落再升
- 白描手法：用最少的字传递最多的信息+情绪，忌华丽堆砌
- 五感描写法：每段调动 2-3 种感官，服务于情绪基调
- 环境交互法：角色情绪投射到环境细节，环境变化暗示情绪转折
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.
- 4d ago First seen · 224 lines · 106 tokens per session scan A f1342085f74b
narrative-writer is an agent published in the GitHub repository uu201/character-arc (543 stars, last pushed 3d ago), licensed MIT. It adds 106 tokens to every session and 4,449 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to narrative-writer, differing in 250 lines, and is treated as a copy.
Other agents, from other repositories
work-verifier
Validates completed work. Use after tasks are marked done to confirm implementations are functional.
debugger
Debugging specialist for errors and test failures. Use when encountering issues.
test-runner
Test automation expert. Use proactively to run tests and fix failures.
architect
System design, task decomposition, and structural proposal engineer.
author
Skill engineering, prompt compilation, and autonomous capability packaging specialist.
worker
You are a worker agent executing a task assigned by the coordinator.