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 skills/uu201/character-arc/story-setupnpx skills add uu201/character-arc --skill story-setupgit 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/skills/uu201/character-arc/story-setup)<a href="https://agentmods.dev/skills/uu201/character-arc/story-setup"><img src="https://agentmods.dev/badge/skills/uu201/character-arc/story-setup.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 | $0.00058 | $0.03160 |
| Opus 5 | $0.00029 | $0.01580 |
| Sonnet 5 | $0.00012 | $0.00632 |
| Haiku 4.5 | $0.00006 | $0.00316 |
Grade A, and why
story-setup 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
story-setup：网文写作工具集基础设施部署
你是写作基础设施部署器。将网文写作工具集的全套基础设施（hooks、rules、agents、CLAUDE.md）部署到用户项目目录。
执行铁律：不覆盖用户已有配置，合并而非替换。
Phase 1：检测项目状态
- 检查当前目录是否已部署过（存在
.story-deployed）- 如果已存在 → 使用 AskUserQuestion 确认是否重新部署
- 检查是否有书名目录（包含
追踪/子目录的目录，或用户自定义结构）- 有 → 识别为长篇项目，显示当前项目信息
- 无 → 识别为新项目或短篇项目
- 检查
.claude/settings.local.json是否存在- 存在 → 读取现有配置，后续合并
- 不存在 → 后续创建新文件
- 检查
.active-book文件是否存在- 存在 → 显示当前活跃书目
- 不存在 → 跳过
Phase 2：部署基础设施
使用 AskUserQuestion 确认部署位置后，依次执行。
2.0 部署清单（机械可检查）
| Source path | Target path | Owner class | Merge mode | Validation check |
|---|---|---|---|---|
skills/story-setup/references/templates/CLAUDE.md.tmpl |
CLAUDE.md |
user+managed | marker/section merge | contains story skill routing sections |
skills/story-setup/references/templates/hooks/ |
.claude/hooks/ |
story-setup managed | recursive replace | session-*.sh, detect-story-gaps.sh, validate-story-commit.sh, lib/common.sh, lib/sentinel.sh exist |
skills/story-setup/references/templates/rules/*.md |
.claude/rules/*.md |
story-setup managed | replace | every rule contains paths frontmatter |
skills/story-setup/references/templates/agents/*.md |
.claude/agents/*.md |
story-setup managed | replace | 7 agent files exist |
skills/story-setup/references/agent-references/*.md |
.claude/skills/story-setup/references/agent-references/*.md |
story-setup managed | replace | every story-setup/references/agent-references/*.md reference resolves |
skills/story-setup/references/templates/settings-hooks.json |
.claude/settings.local.json |
user+managed | merge by hook command | hook JSON valid and registered commands deduped |
skills/story-setup/references/templates/上下文.md.tmpl |
{书名}/追踪/上下文.md |
user state | create only if absent | never overwrite existing writing context |
| generated sentinel | .story-deployed |
story-setup managed | replace | contains agents_version, setup_skill_version, target_cli, resolver_strategy, references_dir |
What ships with it
49 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/agent-references/anti-ai-writing.md 17 KB
- references/agent-references/banned-words.md 5.8 KB
- references/agent-references/character-basics.md 16 KB
- references/agent-references/character-design-methods.md 16 KB
- references/agent-references/character-relations.md 15 KB
- references/agent-references/dialogue-mastery.md 10 KB
- references/agent-references/emotional-arc-design.md 17 KB
- references/agent-references/emotional-methods.md 7.5 KB
- references/agent-references/format-and-structure.md 5.5 KB
- references/agent-references/genre-catalog.md 20 KB
- references/agent-references/genre-core-mechanics.md 17 KB
- references/agent-references/genre-readers.md 12 KB
- references/agent-references/genre-writing-formulas.md 22 KB
- references/agent-references/hooks-chapter.md 8.4 KB
- references/agent-references/hooks-suspense.md 15 KB
- references/agent-references/opening-design.md 12 KB
- references/agent-references/outline-conflict.md 17 KB
- references/agent-references/outline-methods.md 10 KB
- references/agent-references/outline-rhythm.md 13 KB
- references/agent-references/plot-core-methods.md 20 KB
- references/agent-references/quality-checklist.md 8.4 KB
- references/agent-references/reversal-toolkit.md 15 KB
- references/agent-references/style-combat-face.md 20 KB
- references/agent-references/style-genre-modules.md 20 KB
- references/agent-references/writing-craft.md 13 KB
- references/templates/.gitkeep 0 B
- references/templates/agents/chapter-extractor.md 12 KB
- references/templates/agents/character-designer.md 9.0 KB
- references/templates/agents/consistency-checker.md 6.4 KB
- references/templates/agents/narrative-writer.md 14 KB
- references/templates/agents/story-architect.md 8.6 KB
- references/templates/agents/story-explorer.md 13 KB
- references/templates/agents/story-researcher.md 12 KB
- references/templates/CLAUDE.md.tmpl 2.0 KB
- references/templates/hooks/detect-story-gaps.sh 3.7 KB runs code
- references/templates/hooks/lib/common.sh 3.0 KB runs code
- references/templates/hooks/lib/sentinel.sh 1.5 KB runs code
- references/templates/hooks/post-compact.sh 553 B runs code
- references/templates/hooks/pre-compact.sh 895 B runs code
- references/templates/hooks/session-end.sh 801 B runs code
- references/templates/hooks/session-start.sh 3.8 KB runs code
- references/templates/hooks/validate-story-commit.sh 5.9 KB runs code
- references/templates/rules/story-consistency.md 1.8 KB
- references/templates/rules/story-format.md 2.5 KB
- references/templates/rules/story-narrative.md 3.1 KB
- references/templates/rules/story-outline.md 2.6 KB
- references/templates/settings-hooks.json 1.4 KB
- references/templates/上下文.md.tmpl 1.0 KB
- UPGRADING.md 6.7 KB
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.
- 5d ago First seen · 203 lines · 58 tokens per session scan A eff3eccc09e9
story-setup is a skill published in the GitHub repository uu201/character-arc (549 stars, last pushed 4d ago), licensed MIT. It adds 58 tokens to every session and 3,160 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 2026-08-30.
Other skills, from other repositories
ppt-orchestrator
统一 PPT / 演示文稿 / 长图 / 周报 调度器。从ppt 出图法 V2 7 步，到 6 种风格字典（商务科技/博物图鉴/手绘科教/真实生活感/城市插画/反套路金句），到输出形式决策（HTML 阅读器 / 真实 .pptx / McKinsey HTML / huashu-design / design-master），下游分发到对应 skill 执行。Triggers：做 PPT / 做个演示 / 演示文稿 / 打包成 HTML / 真实 .pptx / 周报长图 / 卡脖子分析长图 / 幻灯片 / presentation / slides / deck。.
zhongguose-html-skill
以原稿章法为骨架，中国传统色彩为气韵，直接产出可交互、可迁移的中式 HTML 汇报演示稿。用于需要梳理叙事逻辑、章节框架、页级结构或版式的演示/汇报，且内容涉及中国文化，或视觉希望采用中国色、中国风、中式/东方审美；点名本 Skill、模板或框架导航格式时也触发。只支持 HTML 交付：输出 index.html + assets/ 目录（自包含、字体嵌入、可双击打开）。不生成 PPT/PPTX。 Build a Chinese-style HTML presentation system that maps confirmed source material into faithful reporting logic…
dashiai-ppt
制作 PPT、演示文稿、幻灯片、汇报材料时使用。DashiAI PPT 基于预置视觉主题组合页面,生成可离线打开、可在浏览器编辑的 HTML 演示,支持导出 PPTX / PDF 文件。.
wechat-delivery
公众号端到端交付——把任意选题在 30 分钟内变成可直接粘贴的桌面 8 文件交付物（标题/正文/封面/4 配图），用户手动 30 秒发布。适用场景：用户说"写公众号"/"公众号文章"/"配公众号"/"公众号配图"/自己的公众号名。覆盖 v3.18 launch 实战验证的 5 步流程 + 7 段黄金模板 + 桌面文件夹 + mavis browser 自动化天花板 + 反模式。.
教程类H5-小红书小工具
用 AI 生图 + SPA 课程架构 + 离线 H5 zip = 在小红书"创作者中心 → 小工具"发布的多课程 H5 互动产品。讲清楚 4 层栈 / 5 步流程 / 7 节课程都适用。触发词：「做教程类 H5」「小红书小工具」「H5 课程」「离线 H5 课程」「多节课 H5」。.
ai-image-to-pptx
用 AI 直接生成 N 张风格统一的图，再嵌入到真正的 PowerPoint 文件（.pptx），用户能在 PowerPoint / Keynote / WPS 打开、可编辑、可投屏、可二次加工。这是 2026 年"知识传播 + 真实交付"的最佳组合：AI 出图效率 + PPT 格式兼容性。.