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 WyvernCW/Monich --skill dot-matrix-xhsgit clone --depth 1 https://github.com/WyvernCW/MonichWrote 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/wyverncw/monich/dot-matrix-xhs)<a href="https://agentmods.dev/skills/wyverncw/monich/dot-matrix-xhs"><img src="https://agentmods.dev/badge/skills/wyverncw/monich/dot-matrix-xhs/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/wyverncw/monich/dot-matrix-xhs"><img src="https://agentmods.dev/badge/skills/wyverncw/monich/dot-matrix-xhs.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 | $0.00222 | $0.05434 |
| Opus 5 | $0.00111 | $0.02717 |
| Sonnet 5 | $0.00044 | $0.01087 |
| Haiku 4.5 | $0.00022 | $0.00543 |
Grade A, and why
dot-matrix-xhs 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- dot-matrix-xhs — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dot-matrix-xhs — Bayer 抖动黑白点阵封面
把任意一张照片实时做 Bayer 8×8 有序抖动，变成"报纸印刷点阵"，叠在杂志感四角文字 + 中文 2×2 大标题骨架上。容器比例固定 1280×1644（小红书纵版封面），但用 container-query (cqh) 单位排版，缩到任何尺寸都不糊。
怎么用这份 skill
- 看气质：先 Read
点阵.html（深夜篝火 / a fire at midnight 范例），重点看 Bayer dithering 的颗粒密度、暗角强度、四角栏目字的层级关系。这一步只是为了"知道对的样子长什么样"。 - 挑骨架：从下面 4 个版式骨架里选一个（单图封面 / 上图下字 / 系列三联 / 内页长文），禁止整张 clone 深夜篝火（同样的 2×2 + 中部方括号 + 底部 wordmark 一起出现就是撞脸）。
- 抄积木：Canvas Bayer 函数、容器查询排版、四角文字布局可以直接搬。
- 过红线：写完对照"必须 / 禁止"清单自检。
视觉 DNA — 这些不能丢
少了任意一条就不再是点阵杂志感：
- 黑底 + Canvas 真做 Bayer 抖动：底层一定是一张被 Bayer 8×8 抖动过的图，不是 CSS noise，不是 SVG filter，不是预渲染好的 PNG，必须 Canvas 实时跑。任何图（人物、风景、物件）经过
adjustBrightness(-20~-30) + adjustLevels(60~80, 190~210) + bayerDither后才是对的。 - 像素硬边渲染：canvas 必须
image-rendering:pixelated，缩放时点阵保持硬边，不能因放大变模糊变灰。 - 上下双向 vignette：
linear-gradient(180deg, rgba(0,0,0,.55) 0%, transparent 18%, transparent 70%, rgba(0,0,0,.45) 100%)，让顶部刊号和底部 wordmark 有底气；不要四角 vignette（圆形会立刻变成手机相机镜头味）。 - 杂志栏目式四角：左上=刊号 (
No 04 / 2026)、右上=栏目英文+中文小字、左下=主 wordmark、右下=年份+credit。至少填 3 角，这是独立刊物的标识；少于 3 角就只是张图配字。 - 超大粗黑中文标题：
Noto Sans JP Black+PingFang SC兜底，font-weight:900，line-height:1.1，letter-spacing:0（中文密排不加字距）。禁止细体 / 楷书 / 隶书 / 圆体。 - 白字带轻 text-shadow：所有覆盖在点阵图上的文字都要
text-shadow:0 0 .8cqh rgba(0,0,0,.85)，让白字在浅色点阵区域也读得清。
必须 / 禁止（写完自检）
必须：
- Canvas 真做了 Bayer dithering（不是 CSS 滤镜、不是 SVG noise、不是预渲染图）
- 容器有固定
aspect-ratio（封面用 1280/1644，海报可自由） - 容器加
container-type:size，排版单位用cqh/cqw - 四角至少 3 角有内容（刊号、栏目、wordmark、credit 选 3）
- 主标题字重 ≥ 800
- 中文 webfont 按"四件套"加载（preconnect + preload + print-onload + noscript）
- canvas 三行
image-rendering:pixelated / -moz-crisp-edges / crisp-edges一个不能少
禁止：
- 不要照抄"2×2 中文字阵列 + 中心方括号 + 底部 wordmark"完整组合 — 那是深夜篝火的指纹
- 不要用 SVG noise /
filter: contrast/background-image: radial-gradient(...dot)模拟点阵 — 一眼假 - 不要让点阵保留灰阶（Bayer 输出必须是纯黑 0 或纯白 255 二值，不允许中间值）
- 不要给图加饱和色调（黄昏滤镜、青蓝调、奶油色）— 这套审美就是 1-bit 纯黑白
- 不要圆角 — 框架、按钮、卡片全是直角
- 不要 emoji / 3D 贴纸 / 渐变色 / 玻璃拟态 / 阴影漂浮
- 标题不要 PingFang Regular / Source Han Sans Light — 必须 Heavy / Black 字重
- 不要照搬"深/夜/篝/火 + VOL IV / 2026 + 夜火 wordmark + 小红书号 955873829" — 那是范例的指纹
What ships with it
1 file 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 · 319 lines · 222 tokens per session scan A 51fc36919cc4
dot-matrix-xhs is a skill published in the GitHub repository WyvernCW/Monich (3 stars, last pushed 2mo ago), licensed MIT. It adds 222 tokens to every session and 5,434 once invoked, about $0.0011 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 2026-09-03.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.