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 WhiteGiverMa/meme-skills --skill meme-yuzhoulengmogit clone --depth 1 https://github.com/WhiteGiverMa/meme-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/whitegiverma/meme-skills/meme-yuzhoulengmo)<a href="https://agentmods.dev/skills/whitegiverma/meme-skills/meme-yuzhoulengmo"><img src="https://agentmods.dev/badge/skills/whitegiverma/meme-skills/meme-yuzhoulengmo/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/whitegiverma/meme-skills/meme-yuzhoulengmo"><img src="https://agentmods.dev/badge/skills/whitegiverma/meme-skills/meme-yuzhoulengmo.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 | $0.00122 | $0.05413 |
| Opus 5 | $0.00061 | $0.02707 |
| Sonnet 5 | $0.00024 | $0.01083 |
| Haiku 4.5 | $0.00012 | $0.00541 |
Grade A, and why
meme-yuzhoulengmo 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
宇宙冷漠(口癖/模仿梗)
触发条件:用户提到「宇宙冷漠」「农神」「菜农来辣」「宇!宙!冷!漠!」「宇宙员」「宇宙冷漠2.0」「人类最大的恐惧」「真空剑圣」,或涉及口吃结巴、不懂装懂、半桶水侃侃而谈、找补越描越黑等情境时加载。
一、概述
「宇宙冷漠」是源自《杀戮尖塔2》(Slay the Spire 2)塔圈直播切片的口癖/模仿梗。B站主播菜农来辣(人称「农神」)在一次直播中看到「宇宙冷漠」这张牌时,自信满满地试图向观众解释其含义,却因结巴口吃、逻辑混乱,从"我非常了解"一路滑坡到"很难解释这个东西,解释不了",形成强烈的喜剧反差。切片爆火后,经鬼畜视频、AI歌曲等二次创作发酵,成为塔2圈内最具辨识度的无意义复读梗之一。
二、起源
原始直播
B站主播菜农来辣(农神)以「不懂装懂」为核心直播人设,经常以半桶水知识侃侃而谈。某次直播游玩《杀戮尖塔2》时,他遇到了储君职业的普通卡牌「宇宙冷漠」,随即开始向观众炫耀自己对"宇宙冷漠"这个词的理解。
切片传播
2026年3月14日,B站用户 FFF655 将这一片段切片发布:
切片在塔2圈迅速爆火。农神「茶壶里煮东西——有货倒不出」、结巴口吃却侃侃而谈的表演,成为圈内经典笑料。
农神回应(宇宙冷漠2.0)
2026年4月12日凌晨,B站用户幽浮碳基河豚将农神直播回应宇宙冷漠梗的片段切片发布:
直播中,农神一边啃鸡腿一边为自己此前的「唐氏」发言和自造的「宇宙员」一词找补——他坚称自己是认真的,并发明了一套「宇航员 vs 宇宙员」的理论来证明自己没有口误。越描越黑的样子比原切片更加好笑,被圈内称为「宇宙冷漠2.0」。
注意:农神两次直播的具体日期未确认,按切片时间暂推测为切片发布的前一天(即原直播约3月13日,回应直播约4月11日)。
关联卡牌
「宇宙冷漠」在《杀戮尖塔2》中的实际数据:
| 属性 | 内容 |
|---|---|
| 角色 | 储君 |
| 花费 | 1 点能量 |
| 稀有度 | 普通 |
| 类型 | 技能牌 |
| 效果 | 获得 6 点格挡,将弃牌堆中的一张牌放到你的抽牌堆顶部 |
| 升级效果 | 格挡 6 → 9 |
另外,农神在直播中稍后提到的「剑圣」也是一张关联卡牌(非同一选牌界面,而是几层后打怪奖励中爆出的野生金卡):
| 属性 | 内容 |
|---|---|
| 卡牌名 | 剑圣 |
| 角色 | 储君 |
| 花费 | 2 点能量 |
| 稀有度 | 稀有(金卡) |
| 类型 | 能力牌 |
| 效果 | 君王之剑现在会额外命中一次 |
三、核心特征 / 含义
3.1 口癖特征
农神在切片中的说话方式构成了梗的核心记忆点:
- 「噶人焖」:方言化的「家人们」,是农神的标志性口癖
- 循环反复:从"我是非常了解的"到"我是相当了解",不断重复强调同一个意思
- 渐进崩溃:自信开场 → 语无伦次 → 承认失败,形成完整喜剧弧线(见下方原文)
- 混淆概念:将宇航员的「总观效应」与「宇宙冷漠」混为一谈,进一步暴露知识漏洞
3.2 核心笑点
梗的本质是自信与能力之间的巨大落差:农神用最自信的语气说最站不住脚的内容,最终自己都被绕进去,承认"解释不了"——而这种"翻车"本身正是「不懂装懂」人设的完美兑现。
3.3 农神原话(全文)
宇宙冷漠这张牌我是非常了解的,宇宙冷漠,我跟你们讲,宇宙冷漠是最大的恐惧,我对这个有所了解,噶人焖。宇宙冷漠这个词儿我是相当了解,噶人焖,你们知道吗?我不是说这张牌,咱们说这个词儿。我对,这个是来自于人类最大的恐惧,宇宙冷漠,你们知道吗?
人类最大的恐惧,其实就是宇宙冷漠,你知道吗?也称为宇宙黑暗,很多人其实不知道,世界上最恐惧,最能够让人崩溃的东西,其实就是宇宙冷漠,这玩意儿很牛逼。这玩意可以瞬间击溃一个人的意识跟心理防线。
宇宙员会得这个吗?宇宙员得的叫总观总观效应对吧?我跟你们讲宇宙员,宇宙员得的叫总观效应,而且他也没有出太阳系,很多人不知道宇宙能不能很恐怖这玩意儿,这是人类最恐惧的一个东西。
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 · 212 lines · 122 tokens per session scan A 6e7846e626a7
meme-yuzhoulengmo is a skill published in the GitHub repository WhiteGiverMa/meme-skills (7 stars, last pushed 3mo ago), licensed MIT. It adds 122 tokens to every session and 5,413 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 2026-08-31.
Other skills, from other repositories
gentleman-trainer
Vim Trainer RPG system patterns for Gentleman.Dots. Trigger: When editing files in installer/internal/tui/trainer/, adding exercises, modules, or game mechanics.
game-builder
Convert any topic into playable browser games. Types: trivia, matching, word puzzles, adventure games. Uses Phaser.js or Kaboom.js.
teach-me
Teach the user to build browser games themselves across sessions, by building real games together. Not for building a game for them.
hr-game-development
Help HR and recruiting teams hire and assess game development candidates across engineering, design, and art disciplines. Use when asked to write a game developer job description, create a gameplay engineer interview, assess a game designers portfolio, build a game studio leveling framework, or similar…
godot-genre-educational
Expert blueprint for educational games including gamification loops (learn/apply/feedback/adapt), progress tracking (student profiles, mastery %), adaptive difficulty (target 70% success rate), spaced repetition, curriculum trees (prerequisite system), and visual feedback (confetti, XP bars). Use for learning apps…
tutorial-workflow
A workflow for designing, reviewing, and testing tutorials and new-player onboarding for a game. It checks whether the tutorial teaches the game’s goals, turns, and cause-and-effect actions rather than merely listing buttons or reading like a rulebook.