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 cskwork/oh-my-symphony --skill superdesigngit clone --depth 1 https://github.com/cskwork/oh-my-symphonyWrote 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/cskwork/oh-my-symphony/superdesign)<a href="https://agentmods.dev/skills/cskwork/oh-my-symphony/superdesign"><img src="https://agentmods.dev/badge/skills/cskwork/oh-my-symphony/superdesign/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/cskwork/oh-my-symphony/superdesign"><img src="https://agentmods.dev/badge/skills/cskwork/oh-my-symphony/superdesign.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 | $0.00067 | $0.02356 |
| Opus 5.5 | $0.00027 | $0.00942 |
| Sonnet 5.5 | $0.00013 | $0.00471 |
| Haiku 4.5 | $0.00007 | $0.00236 |
Grade A, and why
superdesign 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 2d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/superdesign - intent-driven elegance
Intent -> trend-aware direction that fits -> elegant UI -> verified against a deterministic anti-slop gate. One-line CSS tweak: skip this skill, edit directly.
Core principles
- Elegance is baseline, not padding. Polished = correct, not extra credit.
- Read intent first. Design to the brief (kind, audience, brand, constraints), never to a default template.
- Trend-aware != trend-chasing. Apply only trends that serve the intent. Record the trend read, dated.
- Anti-slop enforced, not eyeballed. Every surface passes
anti-slop-gate.mjs+ contrast gate. Designer never self-approves. - Diverse by intent. Route to the aesthetic family + medium that fit; no single house style.
- Self-contained + graceful fallback. Asset/trend tooling degrades: works without Stitch/gpt-image-2/WebSearch; missing tools -> documented placeholder + baked snapshot, never faked assets or invented data. Rendered verification is the one hard dependency: build modes render with
playwright-cli(the only render driver,reference/playwright-cli.md); if it cannot be installed, STOP and ask - never substitute a headless render. - Verify vs ground truth. Run the static gate AND render the built surface with
playwright-cli, honor reduced-motion + WCAG AA, report what passed with command output. - Hard stops. External publish (deploy/push/post) or destructive steps need explicit consent; ambiguous brief -> one question (non-interactive run: conservative read, assumption logged in the brief, proceed).
Mode (classify the design intent, state it in one line)
| Signal | Mode | Approach |
|---|---|---|
| new UI / landing / app / screen from scratch | CREATE | default loop |
| redesign / modernize / improve / refresh existing UI | REDESIGN | audit-first (reference/redesign.md) |
| tokens / palette / type / theme / design system only | SYSTEM | reference/design-system.md |
| critique / audit / review (no build) | CRITIQUE | review-only, run detectors (reference/critique.md) |
| explore / moodboard / directions / "what style" | EXPLORE | divergent, trend-heavy, no commit (reference/explore.md) |
| image / icon / illustration / SVG / logo (asset only) | ASSET | fallback chain (reference/assets.md) |
What ships with it
30 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.
- agents/asset-producer.md 1.4 KB
- agents/design-critic.md 2.8 KB
- agents/designer.md 2.0 KB
- agents/trend-scout.md 1.3 KB
- LICENSE 1.0 KB
- reference/aesthetics.md 3.2 KB
- reference/assets.md 2.0 KB
- reference/critique.md 1.7 KB
- reference/dashboard.md 10 KB
- reference/design-brief.md 1.9 KB
- reference/design-system.md 1.1 KB
- reference/engagement.md 4.6 KB
- reference/explore.md 1.1 KB
- reference/impeccable-rules.md 2.1 KB
- reference/mobile.md 2.6 KB
- reference/playwright-cli.md 2.7 KB
- reference/redesign.md 1.2 KB
- reference/sources.md 4.9 KB
- reference/taste-core.md 8.2 KB
- reference/trend-research.md 1.6 KB
- reference/trend-snapshot.md 3.3 KB
- reference/web.md 2.5 KB
- templates/anti-slop-gate.mjs 4.8 KB runs code
- templates/claims.md 1.2 KB
- templates/contrast-gate.mjs 2.8 KB runs code
- templates/contrast-pairs.example.json 338 B
- templates/design-brief.md 411 B
- templates/preflight-gate.sh 2.2 KB runs code
- templates/render-gate.sh 3.8 KB runs code
- templates/trend-pulse.md 465 B
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.
- 2d ago First seen · 95 lines · 67 tokens per session scan A 5ec41ac86d6f
superdesign is a skill published in the GitHub repository cskwork/oh-my-symphony (35 stars, last pushed today), licensed Apache-2.0. It adds 67 tokens to every session and 2,356 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-18.
Other skills, from other repositories
glassmorphism
Glassmorphism design system skill. Use when building frosted-glass UI components with blur, transparency, and layered depth effects.
liquid-glass
Apple Liquid Glass design system. Use when building UI with translucent, depth-aware glass morphism following Apple's design language. Provides CSS tokens, component patterns, dark/light mode, and animation specs.
frontend-design
Frontend design skill fused from Impeccable + custom extensions. Covers design philosophy, anti-AI-slop patterns, typography, color (OKLCH), spatial design, motion, interaction, responsive, UX writing, state management, engineering, and 4 style variants. Includes 20 command skills for audit/critique/polish/animate/etc.
adapt
Adapt designs to work across different screen sizes, devices, contexts, or platforms. Implements breakpoints, fluid layouts, and touch targets. Use when the user mentions responsive design, mobile layouts, breakpoints, viewport adaptation, or cross-device compatibility.
extract
Extract and consolidate reusable components, design tokens, and patterns into your design system. Identifies opportunities for systematic reuse and enriches your component library. Use when the user asks to create components, refactor repeated UI patterns, build a design system, or extract tokens.
normalize
Audits and realigns UI to match design system standards, spacing, tokens, and patterns. Use when the user mentions consistency, design drift, mismatched styles, tokens, or wants to bring a feature back in line with the system.