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 ssmurfgg04-gif/context-m --skill ascii-cosmosgit clone --depth 1 https://github.com/ssmurfgg04-gif/context-mWrote 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/ssmurfgg04-gif/context-m/ascii-cosmos)<a href="https://agentmods.dev/skills/ssmurfgg04-gif/context-m/ascii-cosmos"><img src="https://agentmods.dev/badge/skills/ssmurfgg04-gif/context-m/ascii-cosmos/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/ssmurfgg04-gif/context-m/ascii-cosmos"><img src="https://agentmods.dev/badge/skills/ssmurfgg04-gif/context-m/ascii-cosmos.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 | $0.00000 | $0.06014 |
| Opus 5 | $0.00000 | $0.03007 |
| Sonnet 5 | $0.00000 | $0.01203 |
| Haiku 4.5 | $0.00000 | $0.00601 |
Grade A, and why
ascii-cosmos 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 9d 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.
This is a copy
100% identical to ascii-cosmos — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ascii-cosmos — ASCII 宇宙调性产品落地页生成器
作品长什么样
单文件 HTML 产品官网，hero 是动态分层 ASCII 宇宙：
- 星云气体云（紫，柔和散点）
- 闪烁星点（冷白，带 ★ ✦ 装饰）
- 旋转 ASCII 行星（青，带 3 圈卫星轨道）
- 漂浮不规则小行星（琥珀金，6 种带陨石坑的多行 ASCII 形状，自旋 + 缓慢漂移）
- 彗星拖尾（粉，从屏幕掠过）
下面是常规 marketing 区块：关于 / 核心功能 6 卡片网格 / 界面预览 2 块 / 技术规格 / 订阅方案 3 档 / CTA / 页脚。所有强调字段都有"hover 时打乱-解码"的字符滚动动效（.pt 类）。
适合：独立软件、笔记/写作工具、本地优先 AI、CLI、独立硬件、订阅服务、SaaS、电子书、播客、任何"安静 / 克制 / 有手作味"的产品。
何时触发
用户说：
- "做个宇宙风产品落地页"
- "做个 ASCII 风格的产品官网"
- "生成一个像墨思那样的落地页 — 我的产品是 ..."
- "ascii-cosmos-gen ..."
- 把本 skill 文件夹拖进对话框并描述一个产品
提供：
- 产品名字 + 一句话定位（必需）
- 核心卖点 / 功能清单（推荐 — 给 6 张卡片用）
- 定价档位（可选 — 没说就编 3 档：免费 / 专业 / 团队）
- 风格（可选 — 深空青 / 暖色羊皮纸 / 赛博紫 / 终端绿 …，照抄
styles.md预设名或自由描述。不写就用默认深空青）
如果用户只给产品名一句话：自己围绕这个产品把 6 个功能、3 档价、技术规格全部脑补出来。语气要克制、有手作味，不要 marketing 鸡血。
两种运行模式
模式 A · Claude Code / 本地（有文件系统）
- 输出位置：
~/Desktop/{slug}.html（单文件，所有图片走 unsplash URL 或用户给的链接） - slug 用产品英文名小写连字符
- 一句话报告：路径 + 用了什么风格 + 多少卡片
模式 B · GLM / 在线对话（无文件系统）
- 直接把完整 HTML 包在
```html代码块里输出 - 图片全部用
https://images.unsplash.com/photo-XXX?...或https://picsum.photos/seed/{slug}-NN/W/H占位 - 不要尝试访问本地文件、不要建议命令行操作
- 末尾一行说明：保存为 .html 双击打开即可
判断：如果你无法 Read 看到本地图片或工作目录不是用户家目录 → 默认走 B。
工作步骤
1. 读模板
读取本 skill 同目录下的 template.html。这是完整骨架，包含：
- 全部 CSS（深空主题色 + 5 个 ASCII 层 + 卡片 / 价格 / 规格 / hero 网点字 …）
- 全部 JS（5 层 ASCII 渲染、信息区轨道、字符滚动、标签筛选、平滑滚动、实时时钟）
- 12 处
<!-- SWAP-N -->注释标记需要替换的位置
JS / CSS 不要改（除了主题色变量与字体可以按 styles 改）。
2. 读风格预设
看 styles.md：5 种预设。如果用户的风格描述匹配某个名字，照那份的 CSS 变量替换 :root。否则按用户描述自己设计 6 个变量（--bg / --fg / --dim / --accent / --accent2 / --accent3 / --line / --paper）+ 5 个 ASCII 层颜色（#ascii-nebula / -stars / -planet / -asteroids / -comets）。
配色铁律：5 个 ASCII 层颜色必须互相和谐 + 都能在背景上读出来。深色背景 → 高饱和发光色；浅色背景 → 中低明度有重量的色。
3. 解析用户输入抽信息
抽：
- PRODUCT_EN — 英文 logo 名，全大写 ASCII 字（用于 hero 大字 ASCII title）
- PRODUCT_CN — 1-2 个中文字（hero 副标题大字，会渲染为网点字）
- TAGLINE — 一句话副标语（30-50 字）
- VERSION / TYPE / PLATFORM — 3 个 meta 标签
- ABOUT_PARAGRAPH — 80-150 字关于段落，3-5 个
<span class="pt">强调短语 - 3 HIGHLIGHT — 3 个 cell（标题 + 一句话描述）
- 6 FEATURES — 6 张卡片：图片 URL + ASCII overlay（5-6 行小图） + 标题 + 副标题 + 1-2 个标签 + 分类（ai/write/graph/sync 任选或自定义）
- 2 SHOWCASE — 2 段界面介绍（截图 URL + mini-ascii 装饰 + 标题带
<em>强调 + 2 段 60-100 字描述） - 10 SPEC ROWS — 10 行键值对（版本 / 平台 / 引擎 / 数据格式 / 同步协议 …）
- 3 PRICING — 3 档（名字 / 价格数字 / 价格单位 / 描述 / 5-6 条特性 / CTA 按钮文案）。中间一档加
featured类 - CTA_BIG — 大字号 CTA 文案（带
<em>强调）+ 副文案 + 3 个按钮 + 6-7 个平台标签
What ships with it
3 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.
- 9d ago First seen · 294 lines · 0 tokens per session scan A b3656d9b5236
ascii-cosmos is a skill published in the GitHub repository ssmurfgg04-gif/context-m (2 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 6,014 tokens. A static security scan graded it A with 0 findings. It is 100% identical to ascii-cosmos, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
ai-style
A Chinese-language writing guide for producing or revising reader-facing text such as product announcements, public-account articles, emails, and README files. It focuses on reducing patterns that make writing sound machine-generated.
triage
A task-routing guide that identifies goals, dependencies, and acceptance conditions before work begins. It orders work as research, calculation or execution, and writing.
coding
A coding guide for writing and running Python programs in a sandbox. It requires scripts to be small and reproducible, with their actual output or errors reported.
setup-open-index
Install and configure Open Index as the read/write context layer for a domain-specialized agent. Use when setting up a legal, marketing, customer support, sales, infrastructure, or other domain agent with Open Index over MCP.
build-personal-brain
Create, resume, validate, connect, or maintain a private cross-project memory for AI assistants. Use when a person asks to build a personal memory from local work folders and past assistant conversations, continue an interrupted memory audit, connect an existing memory to another local assistant, verify that the…
codex-memory-guard
Guard task boundaries and preserve confirmed critical project state across Codex compaction. Use when a user wants topic-switch guidance, write-through critical memory, compact HANDOFF checkpoints, PreCompact and compact-resume hooks, four-layer Markdown memory initialization, or memory workflow auditing.