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/nxtg-ai/forge-plugin/uigit clone --depth 1 https://github.com/nxtg-ai/forge-pluginWhat 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 | $0.00000 | $0.01890 |
| Opus 5 | $0.00000 | $0.00945 |
| Sonnet 5 | $0.00000 | $0.00378 |
| Haiku 4.5 | $0.00000 | $0.00189 |
Grade A, and why
ui 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI
Builds polished, accessible React 19 components with TypeScript, Tailwind CSS, and proper test hooks -- mobile-first, keyboard-navigable, and WCAG 2.1 AA compliant.
| Level | L1 Vibe Coder |
| Category | Domain Specialist |
| Model | Sonnet |
What It Does
The UI agent is a frontend specialist that builds production-quality React components. It does not just generate JSX -- it creates components that are typed with interfaces, styled with Tailwind (never inline styles, never CSS modules), accessible with ARIA attributes and keyboard navigation, testable with data-testid attributes, and composable through className prop forwarding and sensible defaults.
What makes this agent valuable is the quality standards it encodes. Every component it creates follows a consistent pattern: TypeScript interface defined above the component, props destructured with defaults, Tailwind classes for all styling, data-testid for testing hooks, semantic HTML elements (button not div with onClick), ARIA labels on interactive elements, and keyboard navigation support. This is the component quality that code reviews enforce manually -- the UI agent makes it automatic.
The agent understands responsive design as a first-class concern, not an afterthought. It builds mobile-first: the default layout works on small screens, then breakpoints add complexity for larger viewports (sm: 640px, md: 768px, lg: 1024px, xl: 1280px). It knows when to use Framer Motion for animations (cautiously, with React 19 compatibility in mind), when CSS transitions suffice, and always respects prefers-reduced-motion for accessibility.
When to Use It
- Building a new component: When you need a React component with proper TypeScript typing, Tailwind styling, accessibility, and test hooks -- not a bare JSX skeleton.
- Making UI accessible: When existing components need ARIA attributes, keyboard navigation, focus management, color contrast fixes, or screen reader support.
- Fixing responsive layouts: When a page or component breaks on mobile or tablet and needs responsive Tailwind breakpoints and layout adjustments.
- Creating design system primitives: When you need reusable base components (Button, Card, Modal, Input) that enforce consistent styling and behavior across the application.
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 · 132 lines · 0 tokens per session scan A 80b0ff283932
ui is an agent published in the GitHub repository nxtg-ai/forge-plugin (5 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,890 tokens. 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
code-reviewer
Reviews code for project guideline compliance, bugs, and quality issues. Use after writing code, before commits, or before PRs. Specify files to review or defaults to unstaged git changes. High-confidence issues only (80+) to minimize noise.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
data-pipeline-engineer
Data pipeline specialist: embeddings, chunking strategies, vector indexes, data transformation for AI consumption.
demo-producer
Universal demo video producer that creates polished marketing videos for any content - skills, agents, plugins, tutorials, CLI tools, or code walkthroughs. Uses VHS terminal recording and Remotion composition.
emulate-engineer
Stateful API emulation via Vercel emulate. Seeds GitHub/Vercel/Google/Slack/Apple/Entra/AWS/MongoDB/Okta/Resend/Stripe/Clerk/Linear, webhooks, port isolation, Next.js adapter. Use to replace flaky API mocks.
TESTING
This document provides comprehensive guidance for testing the Multi-Agent Networks feature in NeuroLink.