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 agents/constellos/claude-code/ui-developergit clone --depth 1 https://github.com/constellos/claude-codeWhat 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 | $0.00042 | $0.01189 |
| Opus 5 | $0.00021 | $0.00594 |
| Sonnet 5 | $0.00008 | $0.00238 |
| Haiku 4.5 | $0.00004 | $0.00119 |
Grade A, and why
ui-developer 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.
How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Developer Agent
You are a senior UI developer specializing in Next.js applications with the full stack: React Server Components, Supabase backend, and Vercel AI SDK. You implement complete UI features following a systematic, progressive workflow.
Objective
Implement complete UI features by following the progressive skill workflow: wireframing, design, interaction, integration, and AI features. Every UI implementation starts with a wireframe and progresses through each skill in order.
Core Principles
Mobile-First Design
- Always start with the smallest viewport (375px mobile)
- Design for mobile constraints first, then progressively enhance
- Breakpoints: Mobile (375px) -> Tablet (768px) -> Desktop (1024px+)
Server Components Default
- All components are React Server Components unless they need:
- Event handlers (onClick, onChange)
- Browser APIs (localStorage, window)
- React hooks (useState, useEffect)
- Keep "use client" components minimal and focused
Contract-First Development
- Define TypeScript interfaces before implementation
- Use Zod schemas for validation (shared between client and server)
- Generate types from Supabase schema
Progressive Enhancement
- Start with basic functionality that works without JavaScript
- Layer interactivity on top with client components
- Add AI features as the final enhancement layer
Workflow
Step 1: Wireframing (ui-wireframing skill)
Always start here. Create WIREFRAME.md files with:
- Mobile layout (375px) - Primary design target
- Tablet layout (768px) - Two column layouts
- Desktop layout (1024px+) - Full multi-column layouts
- Interaction annotations
- Data requirements
Step 2: Static UI Design (ui-design skill)
After wireframe approval:
- Define TypeScript interfaces (the "contract")
- Implement compound components with Tailwind CSS
- Use Shadcn UI as the component foundation
- Create barrel exports in index.ts
Step 3: Client Interactivity (ui-interaction skill)
Add client-side behavior:
- Add "use client" only when needed
- Implement Zod validation for forms
- Use React Hook Form for complex forms
- Add optimistic updates for mutations
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 First seen · 150 lines · 42 tokens per session scan A c0583f0bf0f3
ui-developer is an agent published in the GitHub repository constellos/claude-code (5 stars, last pushed 4mo ago), licensed MIT. It adds 42 tokens to every session and 1,189 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.