OpenDesign is an open-source, local-first desktop app that lets coding agents create prototypes, dashboards, slide decks, images, video, and design systems as exportable files. It is used by people working with agent runtimes such as Claude Code, Codex, Cursor, and DeepSeek Harness. The catalogue add-ons extend the OpenDesign workflow with skills, instructions, commands, and plugins.
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 nexu-io/open-design --skill hps-y2k-chromegit clone --depth 1 https://github.com/nexu-io/open-designWrote 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/nexu-io/open-design/hps-y2k-chrome)<a href="https://agentmods.dev/skills/nexu-io/open-design/hps-y2k-chrome"><img src="https://agentmods.dev/badge/skills/nexu-io/open-design/hps-y2k-chrome/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/nexu-io/open-design/hps-y2k-chrome"><img src="https://agentmods.dev/badge/skills/nexu-io/open-design/hps-y2k-chrome.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 176 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
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 | $0.00048 | $0.02825 |
| Opus 5 | $0.00024 | $0.01412 |
| Sonnet 5 | $0.00010 | $0.00565 |
| Haiku 4.5 | $0.00005 | $0.00282 |
Grade A, and why
hps-y2k-chrome 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 8d 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Y2K Chrome (hps-y2k-chrome)
Single-theme deck plugin locked to the y2k-chrome theme from the upstream
MIT-licensed lewislulu/html-ppt-skill
(36 themes × 31 layouts × 27 animations — this plugin ships exactly one of
those skins, fully baked into one self-contained seed: example.html).
Start from example.html. Replace content only. Never rewrite the design
system or the runtime script. No colors or fonts outside this spec.
Locked token sheet (:root — do not add, remove, or recolor)
:root{
--bg:#dfe4ec; --bg-soft:#eef1f6;
--surface:rgba(255,255,255,.72); --surface-2:rgba(255,255,255,.5);
--border:rgba(120,135,170,.32); --border-strong:rgba(80,100,140,.55);
--text-1:#1a1f2e; --text-2:#4a536a; --text-3:#8590a6;
--accent:#8a5cff; --accent-2:#3ccfd8; --accent-3:#ff84c4;
--good:#1fb98c; --warn:#e8a13d; --bad:#e0445a;
--grad:linear-gradient(135deg,#b8c4d8 0%,#f5f7fb 30%,#8a9ab8 55%,#e8ecf4 80%,#6b7a95 100%);
--grad-soft:linear-gradient(135deg,#c9e4ff,#f5d6ff 50%,#d6fffa);
--chrome-text:linear-gradient(180deg,#f8faff 0%,#9aa8c4 50%,#4a5670 100%);
--radius:26px; --radius-sm:16px; --radius-lg:36px;
--shadow:0 12px 30px rgba(70,90,130,.22),inset 0 1px 0 rgba(255,255,255,.9),inset 0 -1px 0 rgba(80,100,140,.2);
--shadow-lg:0 24px 60px rgba(70,90,130,.35),inset 0 2px 0 rgba(255,255,255,.95);
--font-sans:'Space Grotesk','Inter','Noto Sans SC',sans-serif;
--font-display:'Space Grotesk','Inter',sans-serif;
--font-mono:'JetBrains Mono',SFMono-Regular,Menlo,monospace;
--letter-tight:-.03em; --letter-normal:-.01em;
--ease:cubic-bezier(.4,0,.2,1);
}
Fonts: Space Grotesk is both display and body type ('Noto Sans SC'
fallback for CJK), JetBrains Mono for code/labels. Loaded via Google Fonts
@import only — the sole permitted external resource.
Signature devices (use these, nothing else)
- Silver-metal canvas —
bodycarries the full-bleed 5-stop gradientlinear-gradient(135deg,#c4cfe0 0%,#f0f3f8 25%,#aab8d0 50%,#f5f7fb 75%,#b8c4d8 100%). Every slide is transparent over it. Never paint an opaque slide background. - Chrome-clipped type —
.h1,.chrome-text,.stat-bigclip--chrome-text(white→steel→gunmetal) viabackground-clip:text, plusfilter:drop-shadow(0 2px 3px rgba(40,55,85,.38))so the white top stop keeps letter definition over the light canvas. Display numerals and hero words are always chrome, never flat color. - Frosted-glass cards —
.card=--surface(72% white) +backdrop-filter:blur(16px) saturate(140%)+--shadow. Theinset 0 1px 0 rgba(255,255,255,.9)top highlight is the signature — never drop it. Mega radius--radius:26px(lg surfaces 36px). - Candy accents — purple
--accentleads (kickers, progress bar, checks), aqua--accent-2and pink--accent-3support (orbs, chart bars, eyebrow tints). Accents are for small surfaces only; large fills use--grad/--grad-soft. - Glossy orbs —
.orbradial-gradient candy spheres with a white specular highlight, absolutely positioned,z-index:0, decor only. - Chrome sparkles — inline 4-point star SVGs (
.sparkle) filled with the chrome gradient or candy accents. - Chrome capsule pills —
.pill=linear-gradient(180deg,#fff,#d4dcec)with--borderstroke;.pill-accenttints with--accent.
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.
- 8d ago First seen · 178 lines · 48 tokens per session scan A 3867b7052e9d
hps-y2k-chrome is a skill published in the GitHub repository nexu-io/open-design (95,309 stars, last pushed yesterday), licensed Apache-2.0. It adds 48 tokens to every session and 2,825 once invoked, about $0.0002 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
huashu-sparkline-arc
Open Design's revenue-driver narrative: what actually moves ARR, the leverage points, and the forecast. Built as a decision-grade data & finance deck for board, finance leadership.
ve-midnight-editorial
Open Design's financial review: runway, burn, and the sustainability plan that keeps the project independent. Built as a decision-grade data & finance deck for board, leadership.
hps-y2k-chrome
Open Design's KPI decision brief: activation and retention drivers, what's working, and the one metric to move next. Built as a decision-grade data & finance deck for CRO, RevOps, leadership.
html-ppt-zhangzara-long-table
Open Design's unit-economics and BYOK cost model: the assumptions, the sensitivity, and why it scales. Built as a decision-grade data & finance deck for CFO, investors.
html-ppt-weekly-report
Open Design's weekly growth review: stars, installs, activation — the number, the driver, and the recommended move. Built as a decision-grade data & finance deck for growth & product team.
weekly-update
Open Design's weekly metrics standup: this week's numbers, the one anomaly, and the single decision it forces. Built as a decision-grade data & finance deck for ops & growth team.