style-system

style-system is a skill for Claude Code, Codex from LiPu-jpg/Openwrite. It costs 33 tokens per session (903 once invoked), scanned A, original, Apache-2.0.

A system for extracting writing patterns from text supplied by the user and applying them as a project writing guide.

In plain words
What is it for?
Use it to initialize a writing style, study reference text, create a style guide, or check for drift from an established style.
Why use it?
It separates reusable writing habits from story-specific details, making the intended style easier to use consistently.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to initialize a writing style, study reference text, create a style guide, or check for drift from an established style.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lipu-jpg/openwrite/style-system
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 LiPu-jpg/Openwrite --skill style-system
Clone the repo
git clone --depth 1 https://github.com/LiPu-jpg/Openwrite

Made for: Claude Code, Codex.

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 style-system

README.md
[![agentmods](https://agentmods.dev/badge/skills/lipu-jpg/openwrite/style-system/github.svg)](https://agentmods.dev/skills/lipu-jpg/openwrite/style-system)
Your own site
<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.

agentmods 80×15 button for style-system

Your own site · 80×15
<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>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 903 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
  • 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 $0.00033 $0.00903
Opus 5.5 $0.00013 $0.00361
Sonnet 5.5 $0.00007 $0.00181
Haiku 4.5 $0.00003 $0.00090

Measured 1mo ago against content hash 46ced7a94f0d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

presets/goethe/skills/style-system/SKILL.md · 135 lines

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/*.md
  • data/novels/{id}/data/sources/{source_id}/setting_profile.md
  • data/novels/{id}/data/sources/{source_id}/extraction/*

3. 风格合成

读取:

  • craft/*
  • data/novels/{id}/data/style/fingerprint.yaml
  • data/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:

  • id
  • kind
  • status
  • source_type
  • legal
  • detail_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 all
  • openwrite 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

Read the full file on GitHub · 135 lines

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. 1mo ago First seen · 135 lines · 33 tokens per session scan A 46ced7a94f0d

Subscribe to this mod's changes

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.