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 flitzrrr/frontend-design-skills --skill agent-ui-designgit clone --depth 1 https://github.com/flitzrrr/frontend-design-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/flitzrrr/frontend-design-skills/agent-ui-design)<a href="https://agentmods.dev/skills/flitzrrr/frontend-design-skills/agent-ui-design"><img src="https://agentmods.dev/badge/skills/flitzrrr/frontend-design-skills/agent-ui-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/flitzrrr/frontend-design-skills/agent-ui-design"><img src="https://agentmods.dev/badge/skills/flitzrrr/frontend-design-skills/agent-ui-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 | $0.00049 | $0.01510 |
| Opus 5 | $0.00024 | $0.00755 |
| Sonnet 5 | $0.00010 | $0.00302 |
| Haiku 4.5 | $0.00005 | $0.00151 |
Grade A, and why
agent-ui-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 11d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent-UI-Design
Design patterns for chat interfaces, agent UX, streaming UI, and tool visualization. Based on 21st.dev Agents SDK and award-winning agent products.
Scope
Use this skill when:
- You are designing a chat interface for an AI application
- You need to visually represent agent tool calls
- You are implementing streaming rendering for real-time text output
- You are visualizing sandbox states and execution environments
- You are designing a three-panel layout for agent dashboards
Principles
1. Agent-Ready Design
Components must natively support streaming content, tool calls, and asynchronous state transitions. Chat UIs are a core pattern, not an add-on.
2. Transparency over Magic
The user must know at all times what the system is doing. No silent background work -- every agent step is visible.
3. Progressive Complexity
The default view shows the essentials. Details (tool parameters, raw data, logs) are available on demand.
4. Streaming as Experience
Real-time text output is not a technical detail but a deliberately designed UX element. The speed at which text appears influences perceived intelligence.
5. Errors as Design Cases
Tool errors, timeouts, and unexpected results are normal states, not exceptions. They require dedicated visual design.
Rules
Chat Architecture
- DO: Three-column chat architecture following the 21st.dev pattern:
- Thread Sidebar (left): List of past conversations, scrollable, with search.
- Chat Panel (center): Message stream with input field. Primary interaction.
- Context Panel (right): Optional, for results, previews, forms.
- DO: Lazy-load message history. Only the last N messages initially, older ones on scroll-up.
- DON'T: Keep the entire message history in client state. Use server-side persistence.
- DON'T: Chat panel without a visible input field. It must always be clear where to type.
Message Types
- DO: Differentiate messages by role:
- User Message: Right-aligned, accent color, compact layout.
- Assistant Message: Left-aligned, neutral, expandable for tool results.
- System Message: Centered, subtle, informational.
- Tool Call: Visually distinct with status indicator.
- DO: Markdown rendering in assistant messages (headings, lists, code blocks).
- DO: Code blocks with syntax highlighting and copy button.
- DON'T: Style all message types identically. Visual differentiation provides orientation.
What ships with it
2 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.
- 11d ago First seen · 135 lines · 49 tokens per session scan A 06198e0a0ce4
agent-ui-design is a skill published in the GitHub repository flitzrrr/frontend-design-skills (5 stars, last pushed 5mo ago), licensed MIT. It adds 49 tokens to every session and 1,510 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 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
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.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.