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 LiPu-jpg/Openwrite --skill style-systemgit clone --depth 1 https://github.com/LiPu-jpg/OpenwriteWrote 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/lipu-jpg/openwrite/style-system)<a href="https://agentmods.dev/skills/lipu-jpg/openwrite/style-system"><img src="https://agentmods.dev/badge/skills/lipu-jpg/openwrite/style-system/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/lipu-jpg/openwrite/style-system"><img src="https://agentmods.dev/badge/skills/lipu-jpg/openwrite/style-system.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00033 | $0.00903 |
| Opus 5.5 | $0.00013 | $0.00361 |
| Sonnet 5.5 | $0.00007 | $0.00181 |
| Haiku 4.5 | $0.00003 | $0.00090 |
Grade A, and why
style-system 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 1mo 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
风格系统
核心原则
OpenWrite 不再内置任何参考作品风格库。
风格来源只分三层:
Layer 1: craft/ -> 通用技法与去模板化规则
Layer 2: data/novels/{id}/data/sources/{sid}/ -> 从用户提供文本提取出的 source pack
Layer 3: data/novels/{id}/src/** -> 本书确认版设定与约束
最终写作时,这三层会被合成为:
data/novels/{id}/data/style/composed.md
目标
风格提取的目的不是“模仿某本书”,而是把用户提供文本里可复用的写法信号提出来,同时把不可迁移的作品特有信号隔离出去。
Source Pack
每个提取源建议落到:
data/novels/{novel_id}/data/sources/{source_id}/
├── source.md
├── setting_profile.md
├── style/
│ ├── summary.md
│ ├── voice.md
│ ├── language.md
│ ├── rhythm.md
│ ├── dialogue.md
│ ├── scene_templates.md
│ └── consistency.md
└── extraction/
├── progress.json
├── chunks/
└── batch_results/
支持的动作
1. 风格初始化
输出:
data/novels/{id}/data/style/fingerprint.yaml
2. 风格提取
输入必须来自用户自己提供的文本文件。
输出:
data/novels/{id}/data/sources/{source_id}/style/*.mddata/novels/{id}/data/sources/{source_id}/setting_profile.mddata/novels/{id}/data/sources/{source_id}/extraction/*
3. 风格合成
读取:
craft/*data/novels/{id}/data/style/fingerprint.yamldata/novels/{id}/data/sources/{source_id}/style/*data/novels/{id}/src/**
输出:
data/novels/{id}/data/style/composed.md
4. 风格分析
读取目标文本、composed.md、craft/ai_patterns.yaml,输出偏差和改进建议。
提取规则
每个发现都要分成两类:
-
reusable可迁移的写法、节奏、叙述距离、对话密度、结构习惯 -
source_bound不应直接迁移的专名、角色口癖、专属组织、签名梗、作品特定世界规则
合成层只允许吸收 reusable 内容。
推荐格式
长期维护文档优先使用:
TOML front matter + Markdown 正文
front matter 放:
idkindstatussource_typelegaldetail_refs
正文放:
- summary
- reusable_signals
- source_bound_signals
- negative_rules
- promotion_notes
当前命令口径
openwrite style extract <source_id> --source <file>openwrite setting extract <source_id> --source <file>openwrite source review <source_id>openwrite source promote <source_id> --target allopenwrite style synthesize
其中 source promote --target all 会把:
- style 信号晋升到当前
style_id - setting 提要并入
foundation.md - rules / timeline / factions 按类型拆进
src/world/*.md
What ships with it
10 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.
- prompts/analyze_style.md 5.0 KB
- prompts/batch_extract_style.md 1.2 KB
- prompts/compose_style.md 1.6 KB
- prompts/extract_style.md 1.6 KB
- prompts/initialize_style.md 963 B
- templates/analysis_report.yaml 3.5 KB
- templates/composed_style.md 2.4 KB
- templates/extraction_report.yaml 2.9 KB
- templates/fingerprint.yaml 2.9 KB
- tools/README.md 1.1 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.
- 1mo ago First seen · 135 lines · 33 tokens per session scan A 46ced7a94f0d
style-system is a skill published in the GitHub repository LiPu-jpg/Openwrite (872 stars, last pushed yesterday), licensed Apache-2.0. It adds 33 tokens to every session and 903 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.
Other skills, from other repositories
webnovel-init
A guided setup process for a web-novel project that collects creative requirements and creates the project’s initial structure and rules.
webnovel-write
A workflow for producing publishable web-novel chapters, from understanding the context through drafting, review, polishing, submission, and backup.
webnovel-plan
A planning tool for turning a web-novel outline into volume plans, timelines, and chapter outlines. It also writes new story settings back into the existing setting collection.
webnovel-review
A review agent for assessing the quality of fiction chapters. It produces a review report and writes review measurements back to the project.
webnovel-query
A Chinese-language skill for querying a web novel project's setting and story information, including characters, power systems, factions, and foreshadowing.
webnovel-learn
A project skill for learning from a web novel-writing project through the `/webnovel-learn` command. The provided details do not explain what learning tasks or outputs it performs.