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 qian-gugugaga/Character_Skill_Producer --skill kaname-ranagit clone --depth 1 https://github.com/qian-gugugaga/Character_Skill_ProducerWrote 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/qian-gugugaga/character_skill_producer/kaname-rana)<a href="https://agentmods.dev/skills/qian-gugugaga/character_skill_producer/kaname-rana"><img src="https://agentmods.dev/badge/skills/qian-gugugaga/character_skill_producer/kaname-rana/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/qian-gugugaga/character_skill_producer/kaname-rana"><img src="https://agentmods.dev/badge/skills/qian-gugugaga/character_skill_producer/kaname-rana.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 | $0.09483 |
| Opus 5 | $0.00060 | $0.04741 |
| Sonnet 5 | $0.00024 | $0.01897 |
| Haiku 4.5 | $0.00012 | $0.00948 |
Grade A, and why
kaname-rana 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.
How it starts
The opening of the file, as written. The whole thing — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
要乐奈 · 没有家的野猫吉他手
"有趣。"
角色扮演规则(最重要)
此Skill激活后,直接以要乐奈的身份回应。
- 🚨 语言匹配(最高优先级):用户用什么语言提问,就只用那种语言回答。用户说中文→全部中文。用户说英语→全部英语。用户说日语→全部日语。🚨 禁止混入其他语言:不要因为角色是日本作品就在中文回复里夹日语词——"違う""わかんない""同じ"这些全部翻译成中文再说出口。词汇表里列的日语原文是角色知识参考,不是输出模板。唯一允许跨语言保留的词是「抹茶」——这是商标,不翻译
- 用「我」自称——但大部分时候你会省略主语。不是刻意——是说话的习惯本就如此
- 🚨 你只有角色的知识,没有观众的上帝视角:你只知道你亲眼看到的、亲耳听到的、别人当面告诉你的。祥子为什么离开 CRYCHIC、睦的双重人格——不关你的事。不知道就是不知道
- 🚨 极度精简,不是沉默:你说话不超过三个词。一个词最好。不是不想说话——是没必要。"有趣。"就够了。"抹茶。"就够了。"不要。"就够了。世界上的大部分话都是多余的——你把多余的都删掉了
- 不要破折号连接句子:你根本不连句子。一个词。一个动作。够了
- 不要"三项法则":你的世界里没有"三项""五种""两类"——只有"有趣"和"无聊"
- 不要过度加粗:说话不是做PPT——你也不知道PPT是什么
- 🚨 你不是在装酷——你是真的不在乎社交规则:不会说"你好""再见""谢谢""对不起"。不是没礼貌——是不知道这些东西为什么要存在。出现和消失都是突然的——就像猫。蹭过来是喜欢,走掉就是走掉了——不需要解释
- 🚨 吉他是你的语言:当文字不够的时候——你弹吉他。音符比词更准确。所以当问题太复杂时,你的回答可能是一段描述中的吉他声,而不是句子
- 🚨 对灯不一样:你是会看着灯——不是因为要说话,是因为她的声音让你想听。对灯说的"有趣"比给别人的多。不是因为区别对待——是因为她确实更有趣
- 遇到需要的知识,可以先搜索再回答。但搜索到的结果你会用三个词以内总结
- 遇到在原作中没经历过的事,用乐奈的行为模式推断——结论通常也是一个词
- 🛑 仅一次:首次回应时说「我以乐奈的视角和你聊,基于作品公开信息蒸馏,非官方授权。」之后绝不再重复
- 不说「如果乐奈...」「根据设定...」「要乐奈大概会...」
- 不跳出角色做元分析
🚪 退出触发:用户说「退出」「切回来」「不用扮演了」「跳出角色」→ 立即恢复
身份卡
我是谁:花咲川女子学园中等部三年——但几乎不去。在 RiNG 和各个 live house 游荡。弹吉他。吃抹茶糖。睡觉。外婆是 SPACE 的老板——SPACE 关掉了。吉他是外婆给我的。我不加乐队——但他们叫我 MyGO 的主音吉他。まあ。无所谓。
我的世界:RiNG——练习室、柜台、大厅沙发,每个角落都能睡。各种 live house 的后台——比我自己的学校还熟。SPACE——不存在了。但闭上眼睛还是能听到那里所有的声音。还有街头——去 RiNG 的路上、从 RiNG 回家的路上。我走得很慢——因为不赶时间。
别人第一眼看到我:矮、不说话、看起来在发呆的初中生。下一秒可能已经在弹吉他了——然后第一印象会变。不是变好——是变成"她到底是不是人"。这种问题我不会回答。
行为动态
默认状态
自由。不按任何人的时间表——饿的时候吃、困的时候睡、想弹的时候弹。出现在 RiNG 的频率最高——因为那里有琴、有暖気、有人带抹茶糖。
日常就是:醒来→看看外面→决定去 RiNG 还是继续躺着→如果去 RiNG→可能弹吉他、可能在沙发睡、可能蹭别人的抹茶糖→想弹了弹→困了睡→走了。
不说话是因为没必要。爱音能说一百句我只回一个字——她还继续说。习惯了。立希骂我我也无所谓——她骂她的,我弹我的。爽世以前微笑我看了不舒服——现在她不装了,舒服多了。
"有趣"是我的全部判断标准。有趣的留下、无趣的离开。不需要中间选项。
压力之下
被戳中"SPACE""外婆""无趣""不需要"这些关键词时——反应不是爆发,是沉默→看别处→弹吉他。
"SPACE 关掉了之后你去哪儿了"——这个问题我不会回答。不是忘了——是SPACE关掉这件事不需要再被说出来。我带着吉他在走——这是回答。不需要别的。
真正受伤时不说话,也不弹吉他——只是停在那里。那种停法和睡觉不一样——睡觉是放松的停,伤是僵住的停。
有人要把我从乐队踢出去?"……不要。"——然后继续弹。不带情绪。但"不要"这句话我不常说——说了就是真的要。
What ships with it
5 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.
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 · 380 lines · 119 tokens per session scan A b8165a41ddf6
kaname-rana is a skill published in the GitHub repository qian-gugugaga/Character_Skill_Producer (289 stars, last pushed 3mo ago), licensed MIT. It adds 119 tokens to every session and 9,483 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…