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 AnthonyPoschen/agent-skills --skill frontend-designgit clone --depth 1 https://github.com/AnthonyPoschen/agent-skillsWrote 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/anthonyposchen/agent-skills/frontend-design)<a href="https://agentmods.dev/skills/anthonyposchen/agent-skills/frontend-design"><img src="https://agentmods.dev/badge/skills/anthonyposchen/agent-skills/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/anthonyposchen/agent-skills/frontend-design"><img src="https://agentmods.dev/badge/skills/anthonyposchen/agent-skills/frontend-design.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 | $0.00137 | $0.04543 |
| Opus 5 | $0.00068 | $0.02271 |
| Sonnet 5 | $0.00027 | $0.00909 |
| Haiku 4.5 | $0.00014 | $0.00454 |
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 4d 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 — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Design
Create interfaces that make a real task easy to understand and complete. Make visual choices serve the product and its users; do not treat a collection of components as a finished design.
Design Consultation
When consulted before implementation, establish the few decisions that coding cannot safely infer. Do not block a small, reversible change for a full brief; use repository evidence and state reasonable assumptions. Ask only when an unknown would materially change the workflow, content priority, or visual direction.
Treat DESIGN.md in the target project as the durable record of design
knowledge. Look for it before making a material design decision. At the first
substantive design consultation, create it if it does not exist. Update it when
user feedback, repository evidence, testing, or a design review changes an
assumption, constraint, priority, or decision. Record the decision and its
reason, not a transcript of the conversation.
Capture these decisions when the work is substantial, likely to span multiple sessions, or needs handoff to another implementer:
- Outcome and success: the user outcome, the primary action or decision, and how the team will know the design worked.
- Audience and context: who uses it, their familiarity and urgency, the device or environment, and any access needs that shape the interaction.
- Primary workflow: entry point, happy path, key alternatives, and the feedback or recovery needed after success, failure, or interruption.
- Content and data: the real information, its relative importance, expected density, long or empty values, and any content that must remain visible.
- States and rules: permissions, validation, loading, empty, error, destructive, selected, and time-sensitive states that change what a person can see or do.
- Constraints: existing design system or product conventions, technical limits, supported viewports and input methods, accessibility requirements, brand constraints, and licensed assets or fonts.
- Visual direction: a few concrete adjectives, comparable product references, and anti-references that clarify the desired character without copying another product.
- Scope and tradeoffs: what is deliberately out of scope, what can be a sensible default, and which unresolved questions need a prototype or user decision.
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.
- 4d ago Changed · +62 lines e488ee3a51b7
- 8d ago First seen · 349 lines · 137 tokens per session scan A 0a894ce06602
frontend-design is a skill published in the GitHub repository AnthonyPoschen/agent-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 137 tokens to every session and 4,543 once invoked, about $0.0007 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
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
animation-principles
Apply animation principles — easing, staging, follow-through — to one specific UI motion. Use when tuning how an animation feels. For product-wide duration and easing tokens use motion-system (design-systems); for a full interaction spec use micro-interaction-spec.
refactoring-ui
Audit and fix visual hierarchy, spacing, color, and depth in web UIs. Use when the user mentions "my UI looks off" (or amateur/unprofessional), "fix the design", "Tailwind styling", "color palette", "visual hierarchy", "design system", "spacing scale", or "component styling". Also trigger when building consistent…