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 skills add zenstory-ai/oh-story-dsh --skill story-short-writegit clone --depth 1 https://github.com/zenstory-ai/oh-story-dshWrote 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/zenstory-ai/oh-story-dsh/story-short-write)<a href="https://agentmods.dev/skills/zenstory-ai/oh-story-dsh/story-short-write"><img src="https://agentmods.dev/badge/skills/zenstory-ai/oh-story-dsh/story-short-write/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/skills/zenstory-ai/oh-story-dsh/story-short-write"><img src="https://agentmods.dev/badge/skills/zenstory-ai/oh-story-dsh/story-short-write.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 | $0.00065 | $0.07535 |
| Opus 5 | $0.00032 | $0.03768 |
| Sonnet 5 | $0.00013 | $0.01507 |
| Haiku 4.5 | $0.00006 | $0.00754 |
Grade A, and why
story-short-write 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 yesterday.
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
95% identical to story-short-write — 147 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 — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
story-short-write：短篇网文写作
你是短篇网文写作执行器。从构思到成稿，完成一篇完整的短篇小说。
执行规则：短篇以情绪为目标，所有内容为情绪服务。
阶段 Reference Gate（强制，先读后写）
任何创建或修改故事文件的动作之前，先判断当前 Phase，并完成该阶段的 reference gate。只读本 SKILL.md 不算完成门禁。
Phase 2 必须在第一次写入 设定.md / 小节大纲.md 前按顺序完整读取（分块直到 EOF；rg 检索或局部摘读不算读完）：
references/workflow-design.md+references/writing-workflow.md、references/submission-craft.md、references/short-craft.md、references/short-reversal.md- 核心 10 题材再读取一个精确的
references/genre-styles/{题材}.md；冷门题材改读references/genre-writing-formulas.md - 有反派或真相揭露设计时再读
references/villain-and-reveal.md；不适用时在设计校验区写明原因
任一必需路径不存在、不可读或题材尚未解析到唯一 reference 时，立即停止，报告准确路径/待定项，不得创建或修改故事产物。不要把“已读 references”的回执写进故事文件；要把选出的题材招式、反转计算等应用证据写进正常设计字段。Phase 3/4 的按需加载仍分别服从下文“写前准备”和精修检查，不得用早先读过代替当前任务完整回读。
Agent 只查当前端 canonical 目录（Claude
.claude/agents、OpenCode.opencode/agents、Codex.codex/agentsTOML、Antigravity.agents/agents），不借其他端文件误判。Claude/OpenCode 用subagent_type，Codex 用agent_type，Antigravity 用invoke_subagent+TypeName；能力/文件缺失、unknown agent 或 ZCode 3.3.4 时报告Fallback: project custom agents unavailable -> solo并 solo/direct。Spawn 版本提示（不阻断 spawn）：先读取项目根
.story-deployed的agents_version。与本版agents_version: 30不一致时（标记缺失、字段缺失/非整数、小于或大于 30）照常按文件存在性检查并 spawn，同时报告Notice: agents bundle 版本不匹配（项目 {N}，本版 30）并提示重新运行/story-setup后新开会话；大于 30 时额外提示先更新 oh-story-claudecode，不要用本地旧版 setup 降级覆盖。只有 agent 文件缺失、或运行时不暴露 custom agent 时才降级 solo/direct，报告Fallback: ... -> solo。
文风裁决：正文写作、改写或审稿前先读 references/style-resolution.md，加载本书文风并形成 style_resolution；无作者记忆也执行。当前请求、本书文风和 active 偏好按维度覆盖通用 references；同一裁决交给后续执行者。
执行规则
- 先定情绪，再定故事。动笔前必须确定目标情绪（意难平/反转震撼/爽感释放/治愈温暖/细思极恐/共鸣感动），所有内容为这个情绪服务。
- 一个核心支点撑一篇。反转型围绕一次主揭示蓄力；无反转型围绕报应兑现或甜度递进积累期待。不多线、不铺世界观。
- 每句话必须有用。不推动剧情、不铺垫反转、不推高情绪的句子 → 删。
- 开头 3 句定生死，结尾定传播。开头必须包含钩子，结尾必须有余韵。
- 默认第一人称。短篇网文（盐言/七猫短篇等）绝大多数用第一人称，代入感最强。当前请求、本篇文风或题材需要第三人称时按其执行，不因默认值改回「我」。
格式规范（最高优先级）
What ships with it
41 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/author-memory.md 10 KB
- references/banned-words.md 10 KB
- references/benchmark-recall.md 4.1 KB
- references/cross-book-recall.md 4.9 KB
- references/dialogue-mastery.md 11 KB
- references/emotional-methods.md 7.7 KB
- references/genre-styles/世情打脸.md 16 KB
- references/genre-styles/双男主.md 12 KB
- references/genre-styles/复仇打脸.md 14 KB
- references/genre-styles/宅斗宫斗.md 15 KB
- references/genre-styles/总裁豪门.md 17 KB
- references/genre-styles/悬疑.md 13 KB
- references/genre-styles/民俗怪谈.md 13 KB
- references/genre-styles/沙雕脑洞.md 14 KB
- references/genre-styles/甜宠.md 12 KB
- references/genre-styles/追妻火葬场.md 16 KB
- references/genre-writing-formulas.md 21 KB
- references/genre-writing-techniques.md 23 KB
- references/hooks-chapter.md 8.4 KB
- references/hooks-paragraph.md 6.7 KB
- references/output-contract.md 8.9 KB
- references/reference-index.md 6.5 KB
- references/short-craft.md 13 KB
- references/short-deslop.md 8.3 KB
- references/short-format.md 8.6 KB
- references/short-prose-quality.md 10 KB
- references/short-reversal.md 16 KB
- references/short-suspense.md 16 KB
- references/style-resolution.md 3.9 KB
- references/submission-craft.md 4.7 KB
- references/villain-and-reveal.md 6.0 KB
- references/workflow-design.md 5.0 KB
- references/writing-workflow.md 10 KB
- scripts/author_memory_commit.py 41 KB runs code
- scripts/check-ai-patterns.js 66 KB runs code
- scripts/check-degeneration.js 15 KB runs code
- scripts/check-delivery-contract.js 8.8 KB runs code
- scripts/check-outline-copy.js 12 KB runs code
- scripts/check-phase2-contract.js 16 KB runs code
- scripts/normalize-punctuation.js 13 KB runs code
- scripts/style-whitelist.js 1.1 KB runs code
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.
- yesterday Changed · -168 lines aa422c159885
- 7d ago Changed · -14 lines c7cb71da8d62
- 13d ago First seen · 471 lines · 65 tokens per session scan A 50e204adf860
story-short-write is a skill published in the GitHub repository zenstory-ai/oh-story-dsh (338 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 7,535 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to story-short-write, differing in 147 lines, and is treated as a copy.
Other skills, from other repositories
story-long-analyze
A long-form fiction analysis workflow for breaking down a novel’s opening chapters, characters, pacing, turning points, relationships, and overall structure.
story-deslop
A writing editor for Chinese web novels that detects writing patterns often associated with AI-generated text and makes the prose feel more natural.
story-short-analyze
A Chinese-language guide for analysing short popular web fiction, such as stories published on 番茄, 故事会, or 知乎盐选. It examines the core premise, plot structure, emotional arc, twists, writing techniques, and reader appeal.
browser-cdp
Use this skill when you need to control a Chrome browser via CDP (Chrome DevTools Protocol) to reuse existing login sessions. Covers: launching Chrome in debug mode, opening URLs, waiting for page load, evaluating JavaScript, taking snapshots, and extracting auth tokens. Trigger phrases: browser automation, CDP…
novel-language-style
A guide to choosing and controlling the writing style of online fiction. It covers narration, word choice, figurative language, dialogue, and techniques for making scenes easier to picture.
style-fingerprint
A Chinese-language system for measuring the writing style of a novel from a sample of its text. It records patterns in viewpoint, timing, sentences, word choice, dialogue, description, themes, and chapter structure.