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-reviewgit 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-review)<a href="https://agentmods.dev/skills/zenstory-ai/oh-story-dsh/story-review"><img src="https://agentmods.dev/badge/skills/zenstory-ai/oh-story-dsh/story-review/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-review"><img src="https://agentmods.dev/badge/skills/zenstory-ai/oh-story-dsh/story-review.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 | $0.00074 | $0.05924 |
| Opus 5.5 | $0.00030 | $0.02370 |
| Sonnet 5.5 | $0.00015 | $0.01185 |
| Haiku 4.5 | $0.00007 | $0.00592 |
Grade A, and why
story-review 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 today.
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-review — 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
story-review:多视角对抗式审查
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: 37不一致时(标记缺失、字段缺失/非整数、小于或大于 37)照常按当前宿主角色来源检查并 spawn;同时在「这次怎么审的」里用一句白话提示作者「审稿助手是旧版,运行 /story-setup(ZCode 先更新插件)后新开会话」,Notice: agents bundle 版本不匹配(项目 {N},本版 37)原文写进技术备注行;大于 37 时额外提示先更新 oh-story-claudecode,不要用本地旧版 setup 降级覆盖。版本提示本身不触发降级;文件缺失或异常、工具不可用、递归限制或调用失败按 Phase 0 处理,技术备注写Fallback: ... -> solo。
你负责协调审查,找出小说的结构、角色、文字与设定问题,给出有原文依据的修改建议。
执行铁律:审查是找问题,不是验证正确性。
文风裁决:先读 references/style-resolution.md,加载本书文风,复用调用方的 style_resolution 与作者偏好;单独调用时按当前请求与本书文风裁决。同一裁决交给后续执行者。
作者偏好边界
只接收调用方已有的作者偏好,不查询或记录作者记忆;独立调用时不加载记忆文件。偏好只能帮助解释意图和组织报告,不能降低 rubric 严重度、把事实冲突判为无问题或跳过平台门禁;当前请求仍优先。
Review Mode 选择
/story-review或/story-review full→ 优先 spawn 全部 4 个 Agent;如果当前已经在子代理内,核心 Agent 未部署/异常,或 spawn 失败,自动降级为 solo。/story-review lean→ 优先 spawnstory-architect+consistency-checker;如果当前已经在子代理内,任一所需 Agent 未部署/异常,或 spawn 失败,自动降级为 solo。/story-review solo→ 不 spawn Agent,由当前会话执行基础审查。
Phase 0:预检与降级(必须先执行)
- 确定请求模式:解析用户输入中的
full、lean、solo;未指定时目标模式为full。 - 确认是否允许 spawn:如果当前已经在子代理/Agent 内执行,不再递归 spawn,直接降级为
solo。 - 识别当前宿主的角色来源:ZCode 支持插件子代理,检查当前已启用插件注册的同名角色,不要求
.zcode/agents/。其他宿主按下一步查本端目录;不因宿主名、部署标记包含 zcode 或其他端目录存在而降级。 - 检查核心 Agent 可用状态(仅查当前宿主来源):
- Claude Code
.claude/agents/、OpenCode.opencode/agents/、Codex.codex/agents/、Antigravity.agents/agents/;ZCode 查注册角色的定义,不拿项目文件存在性代替运行时注册 - full 必需 agent:
story-architect、character-designer、narrative-writer、consistency-checker - lean 必需 agent:
story-architect、consistency-checker - 对每个必需 Agent:
- Claude Code agent(
.claude/agents/):读取 frontmatter,确认name:与 subagent_type 完全一致;frontmatter 缺失、不可解析或 name 不匹配时视为 malformed agent。 - OpenCode agent(
.opencode/agents/):文件名即 agent 名(OpenCode 不要求在 frontmatter 中写name:),读取 frontmatter 确认mode: subagent和permissions:规则列表存在且可解析即可(2.x 用复数permissions:,旧版单数permission:视为待重新部署);frontmatter 缺失或不可解析视为 malformed。 - Codex agent(
.codex/agents/):文件名为{agent}.toml,TOML 必须可解析,且包含name、description、developer_instructions;name必须与目标 agent 完全一致。 - Antigravity agent(
.agents/agents/):路径为.agents/agents/agent-name/agent.md(agent-name为目标 agent 名),frontmatter 必须可解析,且name与目标 agent 一致、mainAgent: false、subagent: true、tools非空;缺失或不匹配视为 malformed。 - ZCode plugin agent:注册名与目标角色一致;可读定义须有可解析的
name、description和正文。定义不可直接读时以运行时注册为准,不扫描其他端文件。
- Claude Code agent(
- 任一必需角色缺失或 malformed 时不尝试派发,降级
solo;白话说明助手缺失或损坏,并建议当前宿主重部署(ZCode 更新/启用 oh-story 插件后新开会话)。missing agents -> solo/malformed agents -> solo与问题角色/文件写进技术备注 Fallback、Files 两栏。
- Claude Code
- 确认 Agent 工具可用:Claude/OpenCode/Codex 需要当前运行时的子 Agent/Task 工具,Antigravity 需要
invoke_subagent,ZCode 用Agent按当前 schema 派发注册角色;不可用时降级solo,技术备注写Fallback: agent tool unavailable -> solo。 - 运行时失败降级:如果任何 Agent spawn 返回失败、
subagent_type/agent/agent_type/TypeName不可用、frontmatter/TOML 运行时解析失败或子 Agent 无法启动,停止继续 spawn,改用solo重新审查,技术备注写Fallback: spawn failed -> solo与失败的 agent 名;不要把部分成功的 Agent 结果当成 full/lean 结论。 - 确定实际模式:请求模式与实际模式都写进报告末尾的技术备注行。
What ships with it
21 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-prompts.md 14 KB
- references/banned-words.md 11 KB
- references/batch-review.md 2.3 KB
- references/expression.md 9.5 KB
- references/narrative-focus.md 6.7 KB
- references/quality-rubric.md 4.7 KB
- references/review-tracking.md 2.5 KB
- references/rubrics/fanqie.md 1.1 KB
- references/rubrics/qidian.md 1.1 KB
- references/rubrics/zhihu.md 1.5 KB
- references/solo.md 3.4 KB
- references/story-logic.md 5.9 KB
- references/style-resolution.md 3.7 KB
- references/tracking-initialization.md 1.5 KB
- references/tracking-transaction.md 15 KB
- scripts/check-ai-patterns.js 74 KB runs code
- scripts/check-degeneration.js 15 KB runs code
- scripts/normalize-punctuation.js 13 KB runs code
- scripts/style-whitelist.js 1.1 KB runs code
- scripts/tracking_commit.py 82 KB runs code
- scripts/wordcount_core.py 18 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.
- today Changed · +1 lines ea87e7aa4519
- 8d ago Changed · +2 lines d6dc807b06ab
- 11d ago Changed · -7 lines 4fbd4f4cecaf
- 12d ago Changed · -8 lines 508cc4c27063
- 17d ago Changed bef847a7d561
- 29d ago Changed · -254 lines e2f9a2b6bb28
- 1mo ago Changed · -17 lines eed14be28c86
- 1mo ago Changed · +10 lines cd536e535441
- 1mo ago Changed de5e5ecc1f06
- 1mo ago First seen · 493 lines · 74 tokens per session scan A c88d3ad7ae2b
story-review is a skill published in the GitHub repository zenstory-ai/oh-story-dsh (629 stars, last pushed today), licensed MIT. It adds 74 tokens to every session and 5,924 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to story-review, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
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-long-analyze
A long-form fiction analysis workflow for breaking down a novel’s opening chapters, characters, pacing, turning points, relationships, and overall structure.
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…
workflow-manager
A writing workflow tracker for chapter-based projects. It records whether each chapter is being assembled, drafted, reviewed, confirmed, polished, or archived.
review-chapter
A six-part review of a manuscript chapter. It compares the chapter with the outline and reports quality, coverage, review status, and problems supported by evidence from the text.
revise-span
A revision workflow for changing selected passages in a manuscript. It shows the original and proposed text, then applies changes only after the author confirms them.