story-long-write

story-long-write is a skill for Claude Code from zenstory-ai/oh-story-claudecode. It costs 81 tokens per session (4,133 once invoked), scanned A, original, MIT.

A Chinese-language coaching workflow for creating long online novels, from the initial idea and outline through characters, plot threads, and chapter drafts. It also supports continuing, revising, or rewriting specified chapters.

In plain words
What is it for?
Developing a novel premise, building a world and cast, planning plot arcs, drafting chapters, and revising existing sections.
Why use it?
It helps manage the many connected decisions in a long story so later chapters stay consistent with the outline and established details.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

Part of the oh-story plugin — 13 skills, 13 commands shipped together

Good fit Developing a novel premise, building a world and cast, planning plot arcs, drafting chapters, and revising existing sections.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zenstory-ai/oh-story-claudecode/story-long-write
About the project

oh-story-claudecode is a skill package for planning, analyzing, and writing Chinese web fiction, covering both short and long novels. It is intended for writers using Claude Code, Codex, OpenClaw, and other supported AI-agent environments, with workflows for market research, story breakdowns, drafting, editing, and cover creation. The catalogue entries are the package's skills, commands, agents, and plugin.

zenstory-ai/oh-story-claudecode · 6,780 stars · on GitHub · zenstory.ai

Install

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.

Any agent
npx skills add zenstory-ai/oh-story-claudecode --skill story-long-write
Clone the repo
git clone --depth 1 https://github.com/zenstory-ai/oh-story-claudecode

Made for: Claude Code.

Or install oh-story, the plugin that ships this one along with the rest of its 13 skills, 13 commands.

Its marketplace also offers this one on its own, as the plugin story-long-write/plugin install story-long-write after adding the marketplace above.

Wrote 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.

agentmods badge for story-long-write

README.md
[![agentmods](https://agentmods.dev/badge/skills/zenstory-ai/oh-story-claudecode/story-long-write/github.svg)](https://agentmods.dev/skills/zenstory-ai/oh-story-claudecode/story-long-write)
Your own site
<a href="https://agentmods.dev/skills/zenstory-ai/oh-story-claudecode/story-long-write"><img src="https://agentmods.dev/badge/skills/zenstory-ai/oh-story-claudecode/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.

agentmods 80×15 button for story-long-write

Your own site · 80×15
<a href="https://agentmods.dev/skills/zenstory-ai/oh-story-claudecode/story-long-write"><img src="https://agentmods.dev/badge/skills/zenstory-ai/oh-story-claudecode/story-long-write.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,133 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 8 Sept 2026
  • Snyk pass 8 Sept 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 3d ago against content hash 365cf30e386e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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 3d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/story-long-write/SKILL.md · 169 lines

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:

  1. 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.mdreferences/workflow-revision.md,进入正文前再完整读取 workflow-chapter.md
  2. 主会话直接写正文时,首次落笔前完整读取 references/long-format.mdreferences/writing-craft.mdreferences/long-chapter-quality.mdreferences/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。
  3. 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
  4. 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/agents TOML、.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-deployedagents_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。

  1. 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。
  2. 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。
  3. 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。
  4. 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。
  5. 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。
  6. 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。

Read the full file on GitHub · 169 lines

Files

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.

Changes

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.

  1. 3d ago Changed · -185 lines 365cf30e386e
  2. 4d ago Changed · +12 lines 463cd4e1456e
  3. 13d ago First seen · 342 lines · 81 tokens per session scan A 93a4b9ce6f8f

Subscribe to this mod's changes

story-long-write is a skill published in the GitHub repository zenstory-ai/oh-story-claudecode (6,780 stars, last pushed today), 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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories