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 tance-mang/chinese-webnovel-skills --skill cowritegit clone --depth 1 https://github.com/tance-mang/chinese-webnovel-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/tance-mang/chinese-webnovel-skills/cowrite)<a href="https://agentmods.dev/skills/tance-mang/chinese-webnovel-skills/cowrite"><img src="https://agentmods.dev/badge/skills/tance-mang/chinese-webnovel-skills/cowrite/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/tance-mang/chinese-webnovel-skills/cowrite"><img src="https://agentmods.dev/badge/skills/tance-mang/chinese-webnovel-skills/cowrite.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 | $0.00119 | $0.01015 |
| Opus 5 | $0.00060 | $0.00508 |
| Sonnet 5 | $0.00024 | $0.00203 |
| Haiku 4.5 | $0.00012 | $0.00102 |
Grade A, and why
cowrite 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 12d 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.
What it actually says
共写模式（cowrite）
不是"把整章甩给 AI"，而是人机一起写。专治作者最常卡的那一下——不是不会写，是不知道下一句写什么。三档力度，作者自己挑。
何时用
- 卡在"下一段/下一句怎么接"
- 想自己掌舵，让 AI 只补一段、给几个方向
- 想一次看几个版本（稳的/反转的/情绪的）挑一个
- 想只定"目标/冲突/情绪"，正文交给 AI
三档模式
模式1 ｜ Auto（自动写）—— 爽文提速
按章纲整段写。等于调 expand：给章纲 → 出可发布正文。适合套路爽文、要日更产量时。
模式2 ｜ Assist（辅助写）—— 最常用
作者写一点，AI 接一点。读作者已有的正文 + 前情，续写下一段，并给1 个推荐版 + 2 个备选（见下"多版本格式"），作者选 1/2/3。
- 这一档也是"下一句写什么"的解法：给 2–3 个可走的方向，不替作者拍板。
模式3 ｜ Director（导演模式）—— 作者当导演
作者不写正文，只给目标 / 冲突 / 情绪 / 节奏，AI 出正文，多版本供挑。
- 例：目标=男女主关系升温；冲突=误会；高潮=撑伞 → AI 出 3 版。
多版本格式（重点：正文和分析彻底分区，别堆"版本123"）
━━━━━━━━━━ 推荐版本 ★（评分 89）━━━━━━━━━━
推荐原因：人物推进强 / 埋了伏笔 / 情绪稳
风险：情绪稍快
【正文】
……
━━━━━━━━━━ 备选A（75）特点：节奏更快 ━━━━━━━━━━
【正文】
……
━━━━━━━━━━ 备选B（68）特点：感情戏更重 ━━━━━━━━━━
【正文】
……
选择：1 用推荐 ｜ 2 用A ｜ 3 用B ｜ r 重写 ｜ e 我自己改
- 评分是 AI 自评的相对参考（推进/钩子/情绪/风险），不是绝对分；作者最终拍板。
- 一次最多 3 版，别更多——挑起来累。
原则
- 作者掌舵：Assist/Director 给方向、给选项，不替作者定调；推荐≠强制。
- 正文 / 分析分区：正文是正文，评分和理由单独放，别混在一起。
- 接得住前文：续写前对照前情、人设、语言指纹、情绪轨迹、世界状态（调
memory档案），别断片。 - 写完就记：选定的版本要更新进度/情绪轨迹/伏笔（调
memory）。 - 文字仍守网文手感与符号规范（短句、show 不 tell、弯引号""不用「」，见
expand/anti-ai-checklist）。
终端版怎么用（CLI）
/co：辅助写——续写下一段 + 推荐/备选，选数字采用并存档。/director：导演模式——填 目标/冲突/情绪/节奏，出多版。/write [章名]：自动写整段（= expand）。 （见cli/README.md。）
配合
- 整段自动写 →
expand；卡点续写选方向 → 本技能 Assist。 - 选定后更新档案 →
memory；查一致性 →continuity；去 AI 味/打分 →deslop/aidetect。
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.
- 12d ago First seen · 67 lines · 119 tokens per session scan A 38f2ac5df9e1
cowrite is a skill published in the GitHub repository tance-mang/chinese-webnovel-skills (58 stars, last pushed 3mo ago), licensed MIT. It adds 119 tokens to every session and 1,015 once invoked, about $0.0006 per session on Opus 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
top-design
Create award-winning, immersive web experiences at the level of Awwwards-featured agencies. Use when the user mentions "Awwwards quality", "make my site stunning", "scroll animations", "parallax storytelling", "cinematic web design", "portfolio site", or "brand experience". Also trigger when elevating a standard…
traction-eos
Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "Entrepreneurial Operating System", "V/TO", "quarterly rocks", "Level 10 meetings", "accountability chart", "IDS process", "my company feels chaotic", "we keep having the same…
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
add-cloud-flow
Integrates Power Automate cloud flows into a Power Pages site. Lists available flows, suggests relevant ones based on intent, identifies scenarios and web roles, creates metadata files, and generates client-side code to call flows. Handles both new flow registration and adding already-registered flows to additional…
configure-env-variables
Configures environment variables for Power Pages site settings to support ALM across environments. Creates environment variable definitions in Dataverse, guides the user through linking site settings to those variables via the Power Pages Management app, adds the variables to the solution, and generates a…
deploy-site
Deploys an existing Power Pages code site to a Power Pages environment using PAC CLI. Handles tooling verification, authentication, environment confirmation, building, and uploading. Use when the user wants to deploy, upload, or publish their code site.