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 2998980-hue/surreal-pop-collage --skill surreal-pop-collagegit clone --depth 1 https://github.com/2998980-hue/surreal-pop-collageWrote 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/2998980-hue/surreal-pop-collage/surreal-pop-collage)<a href="https://agentmods.dev/skills/2998980-hue/surreal-pop-collage/surreal-pop-collage"><img src="https://agentmods.dev/badge/skills/2998980-hue/surreal-pop-collage/surreal-pop-collage/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/2998980-hue/surreal-pop-collage/surreal-pop-collage"><img src="https://agentmods.dev/badge/skills/2998980-hue/surreal-pop-collage/surreal-pop-collage.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 | $0.00116 | $0.01797 |
| Opus 5 | $0.00058 | $0.00898 |
| Sonnet 5 | $0.00023 | $0.00359 |
| Haiku 4.5 | $0.00012 | $0.00180 |
Grade A, and why
surreal-pop-collage 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 13d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
超现实波普拼贴 Surreal Pop Collage
黑白现实、平涂梦境、一物不对劲、元素源于图、色从图中来。
照片还是那张照片，但世界被换掉了：主体去色成黑白保留为"现实锚"，背景被 2–3 个巨大平涂色形替换，全图只有一个不可能的巨物——超现实的全部力量在于"只有一处不对劲"。
决策优先级(冲突时按此顺序)
- 锚点可识别——3 秒内认出原图主体，脸部核心区不许压元素
- 只有一个不对劲——巨物唯一；出现第二个不可能元素就删
- 元素源于场景——巨物和色形都要能从原图/场景典故里指出处
- 平涂纪律——色形无渐变、无立体阴影，这是和照片真实感对撞的关键
- 明亮度——整体保持亮，禁止暗黑恐怖
授权与隐私
- 用户给了照片并要求生成/改造，即视为已授权调用生图服务，不再追问
- 只把最终 prompt 和参考图发给生图服务；不传播、不另存用户原图
第一步：场景卡
读原图，逐项写下：
- 锚点主体：最有识别度的主体(人/物/景)，位置与占比
- 区域边界：天空/地面/水面/墙面等可被平涂替换的区域
- 原生色：2–3 个主色(色形颜色的来源)
- 主导动势：最强方向线(对角/纵深/视线)
- 场景典故：若为文化地标，它最出名的一句话知识(巨物的首选来源)
第二步：色形推导(禁止默认红日蓝天)
- 形状：圆(日/月)、拱、地平线色块、整面天空，选 2–3 个，贴合场景原有区域边界
- 颜色三选一策略：①场景已有色提纯(草绿→翠绿) ②互补色对撞(暖橙场景→群青) ③情绪反转色(阴郁场景→明黄)
- 平涂无渐变
第三步：巨物选择(禁止默认海豚鲸鱼)
按优先级选一个：
- 典故巨物(文化地标首选)：从景点最出名的典故里选，但先翻译成"可见的物件或动作"——运石→船队拖石、渔隐→巨网罩园、贴水→离水漂浮、以壁为纸→真山从纸里晕出、碑刻→刻线流成真河。只取大众记忆点(3 秒要懂)。自检：能写出"白居易的灯笼升成月亮"这种一句话配文才算焊上
- 场景元素荒诞化：把图里已有的小东西放大到不合常理(咖啡杯大过楼房)
- 语义最远物：和场景距离最远的东西(沙漠里游泳的人)
- 尺度颠倒：人小物大或反之
第四步：小元素与涂鸦
- 成群小元素(飞鸟/落叶/纸船)3–5 个，大小梯度 100/60/30，沿一条弧线分布
- 白色手绘涂鸦线条 2–3 条(刷痕/波浪线/星星)，做手工痕迹
- 禁止孤立单个装饰
Prompt 编译器(四段式)
只写能变成像素的指令：
- 风格定位：
surreal pop collage, vertical 3:4 - 现实锚：
keep the [主体] clearly recognizable but desaturated to black and white, preserving its texture - 平涂世界与巨物：
the background replaced by huge flat matte color shapes: [色形+颜色，按推导规则], one impossible giant element: [巨物，按选择规则], flat matte colors, no gradients - 小元素与约束：
[小元素群] in graduated sizes following an arc, a few white hand-drawn graffiti strokes, the black-and-white reality collides with the flat color world, no text, no watermark
范例(纽约街景)：surreal pop collage, keep this city street canyon recognizable but desaturated to black and white, the sky replaced by one huge flat lemon-yellow plane purified from the taxis, the street replaced by a flat brick-red plane, one impossible giant element: a giant traffic light hanging between the towers like a chandelier, a flock of small pigeons in graduated sizes following an arc, a few white hand-drawn graffiti strokes, flat matte colors, no gradients, no text, no watermark
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.
- 13d ago First seen · 97 lines · 116 tokens per session scan A eb6b90578f9e
surreal-pop-collage is a skill published in the GitHub repository 2998980-hue/surreal-pop-collage (307 stars, last pushed 1mo ago), licensed MIT. It adds 116 tokens to every session and 1,797 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…