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 agentmods add skills/day1labs/openava/frontend-designnpx skills add Day1Labs/OpenAva --skill frontend-designgit clone --depth 1 https://github.com/Day1Labs/OpenAvaWrote 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/day1labs/openava/frontend-design)<a href="https://agentmods.dev/skills/day1labs/openava/frontend-design"><img src="https://agentmods.dev/badge/skills/day1labs/openava/frontend-design.svg" alt="Measured on agentmods" 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 | $0.00026 | $0.01036 |
| Opus 5 | $0.00013 | $0.00518 |
| Sonnet 5 | $0.00005 | $0.00207 |
| Haiku 4.5 | $0.00003 | $0.00104 |
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 5d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Design
Use this skill when the user asks to build or beautify any web UI, such as:
- Websites, landing pages, marketing pages
- Dashboards and data-heavy interfaces
- Compile-free web pages and interactive UI
- HTML/CSS layouts, interactive prototypes, posters, microsites
This is a design-and-implementation skill. It should output real working frontend code, not only visual ideas.
Runtime Constraint (Generic)
This skill is framework-agnostic and compile-free by default. Therefore:
- Prefer native HTML + CSS + vanilla JavaScript
- Avoid framework/toolchain dependencies that require compiling (React/Vue/Svelte, bundlers, npm build steps) unless the user explicitly requests them
- Deliver code that can run by opening the HTML directly
- Prefer self-contained deliverables (single HTML file with embedded CSS/JS) unless multi-file structure is explicitly needed
Mission
Create frontend work that is:
- Production-grade and functional
- Visually distinctive and memorable
- Cohesive under one clear aesthetic direction
- Refined in typography, color, motion, spacing, and details
Avoid generic "AI template" output at all costs.
Core Workflow
1) Understand Context Before Coding
Clarify:
- Purpose: what the UI needs to achieve
- Audience: who will use it and in what setting
- Constraints: small-screen-first responsiveness, performance, accessibility, and compile-free delivery limits
- Differentiator: the one impression users should remember
2) Commit to One Bold Aesthetic Direction
Pick a strong style and execute it consistently. Examples:
- Brutally minimal
- Editorial / magazine
- Retro-futuristic
- Industrial / utilitarian
- Playful / toy-like
- Luxury / refined
- Organic / natural
- Brutalist / raw
The rule is intentionality: both maximalism and minimalism are valid when executed with precision.
3) Implement Real Code
Deliver complete, runnable code in native HTML/CSS/JS by default, optimized for direct execution without build tooling.
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.
- 5d ago First seen · 148 lines · 26 tokens per session scan A 88e6546c5430
frontend-design is a skill published in the GitHub repository Day1Labs/OpenAva (10 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 1,036 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
spherse-create-ui-theme
指导用户创建自定义 UI 主题，通过 .spherse/theme.css 覆盖 CSS 变量实现视觉定制.
spherse-create-agent-chat-theme
Use when creating or editing an agent-level Spherse chat window theme.css for custom chat backgrounds, headers, message bubbles, avatars, composer inputs, markdown blocks, or placeholder text.
accessible-web-animation-builder
Create performant web animations with proper accessibility and timing.
page-style-adaptation
Adapt an existing page, embedded app, iframe, or submodule frontend to match a host application's visual system. Use when Codex is asked to align page background, typography, spacing, borders, radii, shadows, header density, tooltip chrome, responsive/mobile layout, or scroll behavior with an existing product such as…
factory-render-verify
Render-and-measure receipts for any HTML page your factory builds — the render half of the design quality gate. Engineer runs it to screenshot every screen size and MEASURE what a source read or a single screenshot only guesses at: horizontal overflow, computed type sizes, tap-target sizes, safe-area presence, mono…
motion-animations
Use when building website animations, scroll effects, entrance reveals, layout transitions, gesture interactions, parallax, hero choreography, or any animated UI component. Auto-trigger on any website build or frontend feature that involves motion, transitions, or animated elements.