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 xg-gh-25/SwarmAI --skill s_frontend-designgit clone --depth 1 https://github.com/xg-gh-25/SwarmAIWrote 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/xg-gh-25/swarmai/s_frontend-design)<a href="https://agentmods.dev/skills/xg-gh-25/swarmai/s_frontend-design"><img src="https://agentmods.dev/badge/skills/xg-gh-25/swarmai/s_frontend-design/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/xg-gh-25/swarmai/s_frontend-design"><img src="https://agentmods.dev/badge/skills/xg-gh-25/swarmai/s_frontend-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00054 | $0.00266 |
| Opus 5.5 | $0.00022 | $0.00106 |
| Sonnet 5.5 | $0.00011 | $0.00053 |
| Haiku 4.5 | $0.00005 | $0.00027 |
Grade A, and why
frontend-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Frontend Design
This skill loads full instructions on activation. Read INSTRUCTIONS.md before proceeding.
TRIGGER: "build a landing page", "create a website", "design a UI", "frontend prototype", "interactive page", "HTML page", "web app mockup" DO NOT USE: for backend APIs (just code directly) or for reviewing existing UI (use web-design-review)
MANDATORY: Generate Design System Before Coding
Before writing ANY frontend code, run the design system generator to get industry-specific style, color, typography, and anti-pattern recommendations:
"$SWARM_BACKEND_BIN" py scripts/search.py "<product description>" --design-system -p "ProjectName" -f markdown
This is NOT optional. The database has 161 industry-specific reasoning rules that prevent generic AI aesthetics. Skip this step only if the user explicitly provides a complete design system (colors, fonts, style).
What ships with it
55 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.
- data/animation_feelings.csv 1.1 KB
- data/anti_slop.md 3.1 KB
- data/ATTRIBUTION.md 1.5 KB
- data/charts.csv 19 KB
- data/colors.csv 32 KB
- data/design-judgment.md 39 KB
- data/landing.csv 14 KB
- data/products.csv 57 KB
- data/slide_bold_previews/8-bit-orbit.md 4.6 KB
- data/slide_bold_previews/biennale-yellow.md 4.4 KB
- data/slide_bold_previews/block-frame.md 4.4 KB
- data/slide_bold_previews/blue-professional.md 4.6 KB
- data/slide_bold_previews/bold-poster.md 4.7 KB
- data/slide_bold_previews/broadside.md 4.2 KB
- data/slide_bold_previews/capsule.md 4.3 KB
- data/slide_bold_previews/cartesian.md 4.3 KB
- data/slide_bold_previews/cobalt-grid.md 4.2 KB
- data/slide_bold_previews/coral.md 4.4 KB
- data/slide_bold_previews/creative-mode.md 4.4 KB
- data/slide_bold_previews/daisy-days.md 4.5 KB
- data/slide_bold_previews/editorial-forest.md 4.5 KB
- data/slide_bold_previews/editorial-tri-tone.md 4.6 KB
- data/slide_bold_previews/emerald-editorial.md 4.5 KB
- data/slide_bold_previews/grove.md 4.8 KB
- data/slide_bold_previews/long-table.md 5.1 KB
- data/slide_bold_previews/mat.md 4.6 KB
- data/slide_bold_previews/monochrome.md 4.4 KB
- data/slide_bold_previews/neo-grid-bold.md 4.3 KB
- data/slide_bold_previews/peoples-platform.md 4.5 KB
- data/slide_bold_previews/pin-and-paper.md 4.6 KB
- data/slide_bold_previews/pink-script.md 4.7 KB
- data/slide_bold_previews/playful.md 4.2 KB
- data/slide_bold_previews/raw-grid.md 4.4 KB
- data/slide_bold_previews/retro-windows.md 4.6 KB
- data/slide_bold_previews/retro-zine.md 4.5 KB
- data/slide_bold_previews/sakura-chroma.md 4.8 KB
- data/slide_bold_previews/scatterbrain.md 4.8 KB
- data/slide_bold_previews/signal.md 4.7 KB
- data/slide_bold_previews/soft-editorial.md 4.8 KB
- data/slide_bold_previews/stencil-tablet.md 4.7 KB
- data/slide_bold_previews/studio.md 4.6 KB
- data/slide_bold_previews/vellum.md 4.6 KB
- data/slide_bold_templates.csv 4.3 KB
- data/slide_presets.csv 2.6 KB
- data/styles.csv 139 KB
- data/typography.csv 49 KB
- data/ui-reasoning.csv 52 KB
- data/ux-guidelines.csv 18 KB
- INSTRUCTIONS.md 15 KB
- manifest.yaml 595 B
- scripts/core.py 11 KB runs code
- scripts/design_system.py 46 KB runs code
- scripts/search.py 5.3 KB runs code
- tests/test_slide_bold_previews.py 2.5 KB runs code
- tests/test_slide_taste_assets.py 5.1 KB runs code
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.
- yesterday Changed · -1 lines · -9 tokens per session b7ccaf309e83
- 2mo ago First seen · 24 lines · 63 tokens per session scan A cd6ab0ef251c
frontend-design is a skill published in the GitHub repository xg-gh-25/SwarmAI (56 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 266 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
mobile-design
Guidance for designing and building mobile app interfaces on iOS and Android, including React Native and Flutter projects. Covers touch interaction, on-device performance, platform conventions, navigation, and offline behavior, and emphasizes reasoning about constraints over copying fixed values. Use it when creating…
frontend-design
A reasoning framework for web UI design decisions — components, layout, color, type, effects, and motion. Use it when composing interfaces, picking palettes or fonts, structuring page layouts, or pushing a design past generic defaults. It teaches the principles and trade-offs behind each choice rather than prescribing…
game-art
Reference for game art direction and production pipelines, covering visual style selection, 2D and 3D asset workflows, color theory, animation, resolution and scale rules, file organization, and common mistakes to avoid. Use it when picking an art style for a project, setting up an asset pipeline, defining a palette…
tailwind-patterns
Captures the way Tailwind CSS v4 is meant to be used, where configuration lives in CSS through the @theme directive, the Rust-based engine compiles utilities, and tokens surface as CSS custom properties. Useful when setting up or migrating a v4 project, defining a design-token system, reaching for container queries…
web-design-guidelines
Audits front-end UI code against an external, regularly updated set of web interface guidelines covering accessibility, usability, and interaction quality, then reports each issue in a compact file-and-line format. Fits when reviewing existing UI for best-practice compliance, checking accessibility, or auditing UX…
taste-skill
A taste filter for marketing-style web work (landing pages, portfolios, and redesigns) that fights generic, machine-generated "design" output. The agent reads the brief first, commits to a deliberate direction, and ships interfaces that look authored rather than templated. It reaches for genuine design systems when…