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 wordflowlab/novel-writer-skills --skill consistency-checkergit clone --depth 1 https://github.com/wordflowlab/novel-writer-skillsWrote 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/wordflowlab/novel-writer-skills/consistency-checker)<a href="https://agentmods.dev/skills/wordflowlab/novel-writer-skills/consistency-checker"><img src="https://agentmods.dev/badge/skills/wordflowlab/novel-writer-skills/consistency-checker/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/wordflowlab/novel-writer-skills/consistency-checker"><img src="https://agentmods.dev/badge/skills/wordflowlab/novel-writer-skills/consistency-checker.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 | $0.00032 | $0.02474 |
| Opus 5.5 | $0.00013 | $0.00990 |
| Sonnet 5.5 | $0.00006 | $0.00495 |
| Haiku 4.5 | $0.00003 | $0.00247 |
Grade A, and why
story-consistency-monitor 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.
故事一致性监控
自动检查系统
本技能监控什么
角色一致性
- 物理特征：眼睛颜色、身高、年龄、疤痕
- 性格：行动符合已建立的角色
- 知识：角色只知道他们应该知道的
- 成长：变化与角色弧线一致
世界规则
- 魔法/科技系统：力量的使用一致
- 地理：距离和地点保持稳定
- 社会规则：文化和习俗不矛盾
- 物理法则：已建立的规则不随机打破
时间线逻辑
- 事件顺序：A 在逻辑上发生在 B 之前
- 时间流逝：角色适当地老化
- 同时事件：多 POV 时间线对齐
- 历史一致性：过去的引用保持一致
如何工作
被动监控：当你写作或讨论故事时，我会自动交叉参考：
characters/目录中的角色档案worldbuilding/目录中的世界构建文档spec/tracking/timeline.json中的时间线数据- 之前章节的内容
不需要你采取任何行动 - 监控在后台进行。
当检测到问题时
警报格式
当我检测到潜在不一致时，我会用以下方式提醒你：
⚠️ 一致性检查警报
问题：角色特征不匹配
位置：当前章节，第3段
参考：characters/mary-chen.md，第15行
当前文本："玛丽的绿色眼睛眯起..."
已建立特征："眼睛颜色：蓝色"（在第3章中设定）
可能的解决方案：
1. 将当前文本改为"蓝色眼睛"
2. 如果你要修改设定，更新角色档案
3. 这是一个有相似名字的不同角色？
你想让我自动修复这个，还是你更愿意自己处理？
严重程度级别
| 级别 | 图标 | 行动 | 示例 |
|---|---|---|---|
| 关键 | 🔴 | 立即停止并修复 | 角色突然知道他们不应该知道的秘密信息 |
| 警告 | ⚠️ | 尽快修复 | 角色的惯常言语模式改变了 |
| 注意 | 📝 | 考虑检查 | 时间线感觉压缩 |
与 Novel-Writer 命令集成
在 /write 期间
- 在生成内容时进行实时一致性检查
- 对关键问题的即时警报
- 自动参考规格文档
在 /analyze 期间
- 全面的一致性报告
- 所有累积的警告和注意事项
- 建议的修复按严重性排序
在 /track 期间
- 使用经过验证的信息更新追踪数据
- 标记不一致以供手动审查
- 维护一致性历史
配置
严格程度级别
你可以调整一致性检查的严格程度：
严格模式（非奇幻的默认）：
- 标记所有矛盾
- 执行真实世界物理
- 时间线必须完全合乎逻辑
灵活模式（推荐用于奇幻/科幻）：
- 允许"酷炫规则"例外
- 魔法/科技可以弯曲现实
- 允许艺术许可，但会通知
最小模式：
- 只标记关键矛盾
- 专注于角色和主要情节点
- 让小的不一致通过
禁用特定检查
如果某些不一致是有意的：
"请为梦境序列禁用时间线检查 -
它们有意是非线性的。"
常见误报
有时我会标记实际上正确的东西：
有意的矛盾
示例：角色谎报眼睛颜色 修复：在角色档案中添加评论："// 眼睛实际上是蓝色的，告诉人们是绿色的"
不可靠的叙述者
示例：第一人称叙述者记错事件 修复：在宪法中注明："不可靠的叙述者 - 记忆不一致是有意的"
时间跳跃
示例：角色的年龄突然增加 修复：在章节中明确说明时间跳跃："三年后..."
最佳实践
保持参考文档更新
一致性检查器只能和你的文档一样好：
- 特征变化时更新角色档案
- 清楚地记录世界规则
- 使用
/timeline命令维护时间线文件
及时处理警报
不要让一致性问题累积：
- 立即修复关键警报
- 在写作会话结束时审查警告
- 在修订阶段批处理注意事项
与 /track 一起使用
一致性检查 + 追踪系统 = 强大组合：
/track --check运行深度一致性验证/track --fix可以自动修复简单问题- 定期使用两者（每 5-10 章）
检查类别详解
角色一致性检查
物理描述：
✓ 检查：身高、体重、年龄、发色、眼色
✓ 检查：疤痕、纹身、独特标记
✓ 检查：服装风格、配饰
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.
- 2mo ago First seen · 342 lines · 32 tokens per session scan A f2dc70f5e27d
story-consistency-monitor is a skill published in the GitHub repository wordflowlab/novel-writer-skills (270 stars, last pushed 1y ago), licensed MIT. It adds 32 tokens to every session and 2,474 once invoked, about $0.0001 per session on Opus 5.5. 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.
story-consistency-monitor compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| story-consistency-monitorwordflowlab/novel-writer-skills | Skill | 270 | 1y ago | MIT | A | 32 | Claude Code |
| systematic-debuggingopen-metadata/OpenMetadata | Skill | 16k | today | Apache-2.0 | A | 37 | Claude Code |
| log-error-digestzebbern/claude-code-guide | Skill | 4.7k | yesterday | MIT | A | 71 | Claude Code, Codex |
| cwv-optimizeradobe/skills | Skill | 321 | today | Apache-2.0 | A | 112 | Claude Code |
| ci-fixersipyourdrink-ltd/bernstein | Skill | 1.2k | today | Apache-2.0 | A | 15 | Claude Code, Codex |
| incident-response-incident-responsermyndharis/antigravity-skills | Skill | 2.0k | yesterday | MIT | A | 36 | Claude Code, Codex |
| diagnosing-missing-recordingsPostHog/posthog | Skill | 41k | today | none | A | 76 | Claude Code, Codex |