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.
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.
git clone --depth 1 https://github.com/zenstory-ai/oh-story-claudecodeWrote 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/plugins/zenstory-ai/oh-story-claudecode/oh-story-claudecode)<a href="https://agentmods.dev/plugins/zenstory-ai/oh-story-claudecode/oh-story-claudecode"><img src="https://agentmods.dev/badge/plugins/zenstory-ai/oh-story-claudecode/oh-story-claudecode/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/plugins/zenstory-ai/oh-story-claudecode/oh-story-claudecode"><img src="https://agentmods.dev/badge/plugins/zenstory-ai/oh-story-claudecode/oh-story-claudecode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
oh-story 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.
What it actually says
{
"name": "oh-story",
"version": "0.9.1",
"description": "网络小说创作工具箱：13 个 Skills，覆盖扫榜、拆文、写作、审查、去 AI 味和封面生成。",
"author": {
"name": "zenstory-ai"
}
}
What it installs
The manifest is a name and a version. 13 skills, 13 commands travel with it, and installing the plugin installs all of them — 1,584 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill story-review A 74 tokens
- Skill story-setup A 97 tokens
- Skill story A 63 tokens
- Skill story-deslop A 70 tokens
- Skill story-import A 98 tokens
- Skill story-long-analyze A 150 tokens
- Skill story-short-analyze A 226 tokens
- Skill browser-cdp A 94 tokens
- Skill story-cover A 93 tokens
- Skill story-long-scan A 73 tokens
- Skill story-short-scan A 65 tokens
- Skill story-long-write A 96 tokens
- Skill story-short-write A 65 tokens
- Command browser-cdp A 27 tokens
- Command story-setup A 33 tokens
- Command story A 30 tokens
- Command story-deslop A 24 tokens
- Command story-import A 21 tokens
- Command story-long-analyze A 29 tokens
- Command story-long-scan A 27 tokens
- Command story-review A 21 tokens
- Command story-short-analyze A 27 tokens
- Command story-cover A 18 tokens
- Command story-long-write A 21 tokens
- Command story-short-scan A 22 tokens
- Command story-short-write A 20 tokens
What ships with it
1 file beside plugin.json 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.
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 504ad5be8c9a
- 10d ago Changed ab19336087fc
- 11d ago Changed e0f3873ab3f1
- 17d ago Changed 9e047e5adbf8
- 1mo ago Changed 77c017b73b6b
- 1mo ago Changed fa5a8253d029
- 1mo ago Changed 7a198260a864
- 1mo ago Changed 9c08832d1a23
- 1mo ago First seen · 9 lines scan A cffe31b0b5e0
oh-story is a plugin published in the GitHub repository zenstory-ai/oh-story-claudecode (8,063 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-08.
Other plugins, from other repositories
novel-craft
A project workflow for writing and reviewing long novels in different genres, from setup and chapter drafting to revision and multi-role review. It uses a project-level RTK.md file to set the story’s tone.
super-pm
Product Manager Skills Pack - 52 core/tool skills plus 6 installable workflows across 7 modules: demand insight, solution design, growth iteration, risk management, product strategy, career development, and expert perspectives.
verve
Strip AI tells from prose and put a human voice back, in British or American English, pitched at the reader it is for. A catalogue of tells ordered strongest first and marked on sight or needs company, a detect mode that quotes the tells and never gives a score, four tone presets, three strength levels, a two-way…
openhumancy
Delegate real-world tasks to human workers via the OpenHumancy API. Manages worker search, task creation, chat, and TON blockchain payments.
cleanlanguage
Draft, rewrite, proofread, adapt, and audit prose to the Clean Language editorial standard.
writing-pro-max
A writing-focused plugin containing methods for adapting novels, developing original scripts, reviewing literary theory, and writing performance-layer video prompts. The listed methods are based on the author's own theories.