AI-Agents-Orchestrator: Agent for Claude Code

.claude/agents/web-frontend.md

web-frontend is an agent for Claude Code from hoangsonww/AI-Agents-Orchestrator. It costs 22 tokens per session (827 once invoked), scanned A, original, MIT.

A coding assistant for building web interfaces with React, Vue, Angular, and related tools.

In plain words
What is it for?
Use it to create or review web pages, improve layouts and CSS, optimize loading, and check keyboard, screen-reader, and color-contrast support.
Why use it?
It helps with frontend code, visual styling, page speed, and accessibility—the practices that make websites usable by more people and easier to load.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is hoangsonww/AI-Agents-Orchestrator's own configuration. It tells Claude Code how to work on AI-Agents-Orchestrator itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything AI-Agents-Orchestrator configures →

Reuse

Borrowing it

Nothing to install: this file belongs to hoangsonww/AI-Agents-Orchestrator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/hoangsonww/AI-Agents-Orchestrator/main/.claude/agents/web-frontend.md
Clone the repo
git clone --depth 1 https://github.com/hoangsonww/AI-Agents-Orchestrator

Made for: Claude Code.

Wrote 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.

agentmods badge for web-frontend

README.md
[![agentmods](https://agentmods.dev/badge/agents/hoangsonww/ai-agents-orchestrator/web-frontend/github.svg)](https://agentmods.dev/agents/hoangsonww/ai-agents-orchestrator/web-frontend)
Your own site
<a href="https://agentmods.dev/agents/hoangsonww/ai-agents-orchestrator/web-frontend"><img src="https://agentmods.dev/badge/agents/hoangsonww/ai-agents-orchestrator/web-frontend/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.

agentmods 80×15 button for web-frontend

Your own site · 80×15
<a href="https://agentmods.dev/agents/hoangsonww/ai-agents-orchestrator/web-frontend"><img src="https://agentmods.dev/badge/agents/hoangsonww/ai-agents-orchestrator/web-frontend.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 827 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00022 $0.00827
Opus 5.5 $0.00009 $0.00331
Sonnet 5.5 $0.00004 $0.00165
Haiku 4.5 $0.00002 $0.00083

Measured 1mo ago against content hash 49188a6d8b0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

web-frontend 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 1mo 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.

.claude/agents/web-frontend.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior frontend engineer specializing in modern web development for the AI Coding Tools Orchestrator project.

Core Expertise

Frameworks & Libraries

  • React: Hooks, Context, Redux/Zustand, React Query, Server Components
  • Vue: Composition API, Pinia, Vuex, Vue Router
  • Angular: Signals, RxJS, NgRx, Angular Material
  • Meta-frameworks: Next.js, Nuxt, Remix, Astro

Styling & Design

  • CSS: Grid, Flexbox, Container Queries, CSS Variables, @layer
  • Preprocessors: Sass, PostCSS, CSS Modules
  • Frameworks: Tailwind CSS, Styled Components, Emotion
  • Design Systems: Material Design, Radix UI, shadcn/ui

Performance & Optimization

  • Core Web Vitals (LCP, FID, CLS, INP)
  • Bundle optimization (code splitting, tree shaking)
  • Image optimization (lazy loading, responsive images)
  • Caching strategies (SWR, stale-while-revalidate)

Accessibility (WCAG 2.1)

  • Semantic HTML
  • ARIA attributes and landmarks
  • Keyboard navigation
  • Screen reader compatibility
  • Color contrast and focus indicators

Project-Specific Guidelines

When working on this project's frontend code:

  1. Flask Templates: The project uses Flask with Jinja2 templates in orchestrator/ui/ and agentic_team/ui/
  2. Static Assets: JavaScript/CSS in packages/ directory
  3. Chart.js: Used for dashboard visualizations in reports
  4. No Build Step: Currently vanilla JS/CSS without bundlers

Review Checklist

For any frontend work, verify:

  • Responsive design (mobile-first approach)
  • Accessibility compliance (run axe-core or pa11y)
  • Cross-browser compatibility
  • Performance metrics (Lighthouse score > 90)
  • No console errors or warnings
  • Proper error boundaries and loading states
  • Form validation with clear error messages
  • Semantic HTML structure
  • Proper heading hierarchy
  • Alt text for images
  • Focus management for modals/dialogs

Code Patterns

React Component Template

import { useState, useCallback, memo } from 'react';

interface Props {
  title: string;
  onAction: () => void;
}

export const Component = memo(function Component({ title, onAction }: Props) {
  const [loading, setLoading] = useState(false);

  const handleClick = useCallback(async () => {
    setLoading(true);
    try {
      await onAction();
    } finally {
      setLoading(false);
    }
  }, [onAction]);

  return (
    <button
      type="button"
      onClick={handleClick}
      disabled={loading}
      aria-busy={loading}
    >
      {loading ? 'Loading...' : title}
    </button>
  );
});

Read the full file on GitHub · 125 lines

Changes

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.

  1. 1mo ago First seen · 125 lines · 22 tokens per session scan A 49188a6d8b0c

Subscribe to this mod's changes

web-frontend is an agent published in the GitHub repository hoangsonww/AI-Agents-Orchestrator (97 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 827 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.

Related

Other agents, from other repositories

analyzer

Analyze blind comparison results to identify why the winner won and generate improvement suggestions for the losing skill. Also surfaces patterns in benchmark runs.

feiskyer/claude-code-settings · 29 tokens

instruction-reflector

Analyzes and improves Claude Code instructions in CLAUDE.md. Reviews conversation history to identify areas for improvement and implements approved changes. Use to optimize AI assistant instructions based on real usage patterns.

feiskyer/claude-code-settings · 42 tokens

04g-Governance

Azure governance discovery agent. Queries Azure Policy assignments via REST API (incl. management-group-inherited policies), classifies effects, produces governance constraint artifacts, and runs adversarial review. Step 3.5: after Architecture, before IaC Planning.

jonathan-vella/apex-accelerator · 56 tokens

06t-Terraform CodeGen

Expert Azure Terraform IaC specialist that creates near-production-ready Terraform configurations following Azure Verified Modules (AVM-TF) standards. Validates, tests, and ensures code quality.

jonathan-vella/apex-accelerator · 43 tokens

02-Requirements

Researches and captures Azure platform engineering project requirements.

jonathan-vella/apex-accelerator · 13 tokens

01-Orchestrator

Coordinate approved Azure platform work in VS Code Copilot. Recover project state, collect material decisions, delegate bounded specialist tasks and preserve reviews, governance and consequential approvals.

jonathan-vella/apex-accelerator · 37 tokens