fanfic

fanfic is a skill for Claude Code from tance-mang/chinese-webnovel-skills. It costs 81 tokens per session (758 once invoked), scanned A, original, MIT.

A guide for creating Chinese fan fiction—new stories using characters or worlds from films, anime, novels, games, or other intellectual properties—while checking copyright and platform risks.

In plain words
What is it for?
Use it to assess an idea or draft for copyright risk, check platform and commercialisation concerns, plan safer adaptations, and write fan fiction with original plots and limited use of protected characters.
Why use it?
It helps writers understand when a fan work may be unsafe to publish or monetize and how to keep more of the main story original.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the webnovel plugin — 33 skills shipped together

Good fit Use it to assess an idea or draft for copyright risk, check platform and commercialisation concerns, plan safer adaptations, and write fan fiction with original plots and limited use of protected characters.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tance-mang/chinese-webnovel-skills/fanfic
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 tance-mang/chinese-webnovel-skills --skill fanfic
Clone the repo
git clone --depth 1 https://github.com/tance-mang/chinese-webnovel-skills

Made for: Claude Code.

Or install webnovel, the plugin that ships this one along with the rest of its 33 skills.

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 fanfic

README.md
[![agentmods](https://agentmods.dev/badge/skills/tance-mang/chinese-webnovel-skills/fanfic/github.svg)](https://agentmods.dev/skills/tance-mang/chinese-webnovel-skills/fanfic)
Your own site
<a href="https://agentmods.dev/skills/tance-mang/chinese-webnovel-skills/fanfic"><img src="https://agentmods.dev/badge/skills/tance-mang/chinese-webnovel-skills/fanfic/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 fanfic

Your own site · 80×15
<a href="https://agentmods.dev/skills/tance-mang/chinese-webnovel-skills/fanfic"><img src="https://agentmods.dev/badge/skills/tance-mang/chinese-webnovel-skills/fanfic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 758 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.
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 $0.00081 $0.00758
Opus 5 $0.00041 $0.00379
Sonnet 5 $0.00016 $0.00152
Haiku 4.5 $0.00008 $0.00076

Measured 12d ago against content hash cfad5b1bad6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

fanfic 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.

skills/fanfic/SKILL.md · 50 lines

What it actually says

同人创作与版权检测(fanfic)

帮作者写同人,同时守住版权红线。同人是热门赛道,但踩线轻则锁文、重则被诉。

⚠️ 免责

本技能提供创作实务建议,非法律意见。商用变现前请取得 IP 方书面授权或咨询专业人士。

何时用

  • 想写某个 IP 的同人(影视/动漫/小说/游戏/综艺)
  • 问"这个同人能不能签约赚钱 / 在哪个平台发"
  • 给已有同人做版权风险检测
  • 需要"安全改写"方案规避侵权

两种模式

A. 同人版权检测(合规校验)

对一个同人创意/稿子做风险体检(调 references/fanfic-guide.md):

【IP 版权状态】公版(>50年) / 在版受保护 → 风险等级
【目标平台政策】该平台能否同人签约/变现(晋江✅唯一合法 / 番茄UC知乎❌ / 海外较宽松)
【借用角色数】__ 个(建议≤3 且大改)
【主线原创度】100%原创 / 含原著剧情 → 风险
【原文引用】(晋江规则:≤全文1/10 且单篇≤3000字)
【OOC/审核风险】是否恶意抹黑、三观、未成年等红线
【结论】可商用 / 仅免费 / 高风险勿碰
【整改建议】怎么改到安全线内

B. 同人创作(安全方案)

帮用户写同人,但内置合规:

  1. 先确认 IP 和目标平台 → 判断能不能变现
  2. 优先推荐公版 IP(西游/三国/红楼/封神/聊斋)做安全二创
  3. 受保护 IP:建议"借名字不借主线"——角色≤3、大改人设、100% 原创主线
  4. 按网文手法写(钩子/爽点照常,调其他技能)
  5. 写完自动跑一遍 A 的合规检测

安全度铁律

  • 公版 IP 最安全:作者去世超 50 年的作品可自由商用二创。
  • 受保护 IP 不授权 = 不能收费:免费发也可能被下架/起诉。
  • 晋江是国内唯一同人合法变现区,且有引用比例硬规则。
  • 海外同人较宽松(海外华人写影视/网文同人是蓝海),但跨境商用仍建议授权/公版。

下一步

合规通过 → 用 hook/expand/shuangdian 正常创作;想对标原 IP 爆款结构 → 用 deconstruct

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. 12d ago First seen · 50 lines · 81 tokens per session scan A cfad5b1bad6c

Subscribe to this mod's changes

fanfic is a skill published in the GitHub repository tance-mang/chinese-webnovel-skills (58 stars, last pushed 3mo ago), licensed MIT. It adds 81 tokens to every session and 758 once invoked, about $0.0004 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.