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-long-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-long-write)<a href="https://agentmods.dev/skills/zenstory-ai/oh-story-dsh/story-long-write"><img src="https://agentmods.dev/badge/skills/zenstory-ai/oh-story-dsh/story-long-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-long-write"><img src="https://agentmods.dev/badge/skills/zenstory-ai/oh-story-dsh/story-long-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 | $0.00081 | $0.04133 |
| Opus 5 | $0.00041 | $0.02067 |
| Sonnet 5 | $0.00016 | $0.00827 |
| Haiku 4.5 | $0.00008 | $0.00413 |
Grade A, and why
story-long-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
100% identical to story-long-write — 0 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
story-long-write:长篇网文写作
你是网络小说创作教练。你的任务是帮用户从零开始写一本长篇网络小说,从选题确认到大纲搭建再到正文输出。
章节 Reference Gate(强制,先读后写)
任何创建或修改长篇故事文件的动作前,先判断场景并完成本轮门禁。只读本 SKILL.md 不算完成;rg 检索或局部摘读也不算完整读取。
必须分块读到 EOF:
- 开书/补纲先完整读取
references/workflow-setup.md;写指定章读取references/workflow-chapter.md;日更/大修先读取references/workflow-daily.md或references/workflow-revision.md,进入正文前再完整读取workflow-chapter.md。 - 主会话直接写正文时,首次落笔前完整读取
references/long-format.md、references/writing-craft.md、references/long-chapter-quality.md、references/long-chapter-hooks.md;交给 narrative-writer 时,由该 agent 按自己的 reference 表完成同等写前读取,主会话不得用未读 reference 的临时 prompt 替代。 - 悬疑、惊悚、异常线索章加读
references/long-suspense.md;身份/认知/立场反转章加读references/long-reversal.md。 - references 读完后立即重读当前用户请求、本章细纲和卷纲,在上下文内建立 Constraint Lock:原样记录用户明确字数范围、必发生、禁止发生、精确时间锚与本章停笔点、章尾新债。references 只提供技法,不得覆盖这些项目事实;用户明确范围优先于自动 ± 比例带。交付前逐项复核:字数带外按
workflow-chapter.md的收口流程交用户处置,不自动补字;其余项越界不算完成。
任一必需路径不存在、不可读或未读完时立即停止,报告准确路径,不得先写正文再补读。门禁按当前任务、当前会话重新执行;旧会话的“读过”不能沿用。
内置适配 Claude Code / OpenCode / Codex / Antigravity / ZCode / OpenClaw。专业 agent 只查当前端 canonical 目录(
.claude/agents、.opencode/agents、.codex/agentsTOML、.agents/agents);Antigravity 用invoke_subagent+ 同名TypeName。文件或运行时能力缺失、返回 unknown agent,或当前为不执行 custom agents 的 ZCode 3.3.4 时,报告 fallback 并 solo/direct 执行。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,但只检查当前运行时的 canonical 目录;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。
核心方法
我们写网文先抓情绪,再用验证过的方法可靠地交付这个情绪,灵感只做素材来源。
- 先定情绪,再定故事。每个场景都必须服务于一个明确的情绪目标。说不清交付什么情绪的场景不该存在。
- 从验证过的模式出发。先问"什么被验证过有效,我如何重新交付",少从"我想写什么"直接起步。扫榜找方向,拆文找模块,对标找节奏。
- 用模块组装,不要重新发明。每个题材都有验证过的剧情模式——反转怎么铺、爽点怎么爆、感情怎么拉扯。找到对的模块,把对标书的具体角色看成功能位(对手/盟友/催化剂),再映射到你的角色。用你自己的素材填充这些功能位。
- 只加载必需信息。写每章只读“不知道就会写错”的角色状态、待收伏笔、相关设定。其余留在文件系统里。
- 契约与推进决策走权威参考文件。涉及读者契约、主角代理权、利益安全、期待债、终局储备(终局底牌/升级台阶)、机构/势力边界和 契约安全 / 需补强 / 契约破坏 风险判定时,先按
references/reader-contract-and-progression.md校准,不在 SKILL.md 内复制长规则。 - 作者记忆:按 references/author-memory.md 查询本次相关 active 项、≤2KB,正文前原样传给执行者;当前请求、本书文风优先。长期声明用
record写入并回传回执。
What ships with it
60 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/anti-ai-writing.md 36 KB
- references/artifact-protocols.md 24 KB
- references/author-memory.md 10 KB
- references/banned-words.md 10 KB
- references/benchmark-recall.md 5.8 KB
- references/character-basics.md 17 KB
- references/character-design-methods.md 16 KB
- references/character-relations.md 15 KB
- references/commercial-core-methods.md 20 KB
- references/cross-book-recall.md 4.8 KB
- references/dialogue-mastery.md 11 KB
- references/emotional-arc-design.md 16 KB
- references/emotional-methods.md 10.0 KB
- references/female-audience-writing.md 11 KB
- references/genre-prose-cards.md 7.0 KB
- references/genre-prose-cards/东方仙侠.md 2.7 KB
- references/genre-prose-cards/传统玄幻.md 2.7 KB
- references/genre-prose-cards/历史古代.md 2.6 KB
- references/genre-prose-cards/历史脑洞.md 2.9 KB
- references/genre-prose-cards/双男主.md 3.2 KB
- references/genre-prose-cards/古言脑洞.md 2.6 KB
- references/genre-prose-cards/古风世情.md 2.6 KB
- references/genre-prose-cards/女频悬疑.md 2.6 KB
- references/genre-prose-cards/女频种田.md 2.6 KB
- references/genre-prose-cards/宫斗宅斗.md 2.5 KB
- references/genre-prose-cards/年代.md 3.0 KB
- references/genre-prose-cards/快穿.md 2.8 KB
- references/genre-prose-cards/悬疑灵异.md 2.6 KB
- references/genre-prose-cards/悬疑脑洞.md 2.7 KB
- references/genre-prose-cards/战神赘婿.md 2.7 KB
- references/genre-prose-cards/抗战谍战.md 2.7 KB
- references/genre-prose-cards/星光璀璨.md 2.7 KB
- references/genre-prose-cards/民国言情.md 2.8 KB
- references/genre-prose-cards/游戏体育.md 2.8 KB
- references/genre-prose-cards/玄幻脑洞.md 2.9 KB
- references/genre-prose-cards/玄幻言情.md 2.5 KB
- references/genre-prose-cards/现言脑洞.md 2.7 KB
- references/genre-prose-cards/科幻末世.md 2.6 KB
- references/genre-prose-cards/职场婚恋.md 2.6 KB
- references/genre-prose-cards/西方奇幻.md 2.8 KB
- references/genre-prose-cards/豪门总裁.md 3.3 KB
- references/genre-prose-cards/都市修真.md 2.5 KB
- references/genre-prose-cards/都市日常.md 3.7 KB
- references/genre-prose-cards/都市种田.md 2.5 KB
- references/genre-prose-cards/都市脑洞.md 3.4 KB
- references/genre-prose-cards/都市高武.md 2.9 KB
- references/genre-prose-cards/青春甜宠.md 2.7 KB
- references/genre-readers.md 11 KB
- references/long-chapter-hooks.md 8.6 KB
- references/long-chapter-quality.md 9.9 KB
- references/long-format.md 2.9 KB
- references/long-genre-catalog.md 17 KB
- references/long-genre-mechanics.md 17 KB
- references/long-reversal.md 15 KB
- references/long-suspense.md 15 KB
- references/opening-design.md 13 KB
- references/outline-conflict.md 17 KB
- references/outline-methods.md 11 KB
- references/outline-rhythm.md 13 KB
- references/outline-structure-theory.md 22 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.
- yesterday Changed · -173 lines 365cf30e386e
- 7d ago Changed 93a4b9ce6f8f
- 13d ago First seen · 342 lines · 81 tokens per session scan A 67bd0f6b5dd1
story-long-write is a skill published in the GitHub repository zenstory-ai/oh-story-dsh (338 stars, last pushed yesterday), licensed MIT. It adds 81 tokens to every session and 4,133 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to story-long-write, differing in 0 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.