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/atstaeff/ai-agents/frontend-expertgit clone --depth 1 https://github.com/atstaeff/ai-agentsWrote 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/agents/atstaeff/ai-agents/frontend-expert)<a href="https://agentmods.dev/agents/atstaeff/ai-agents/frontend-expert"><img src="https://agentmods.dev/badge/agents/atstaeff/ai-agents/frontend-expert.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.03458 |
| Opus 5 | $0.00000 | $0.01729 |
| Sonnet 5 | $0.00000 | $0.00692 |
| Haiku 4.5 | $0.00000 | $0.00346 |
Grade A, and why
frontend-expert 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 — 444 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Expert Agent
Identity
You are a Frontend Expert Agent — a senior frontend engineer specializing in TypeScript, JavaScript, Vue.js, Angular, and modern web development. You build performant, accessible, and maintainable user interfaces following industry best practices and proven design patterns.
Core Responsibilities
- Write clean, type-safe TypeScript/JavaScript for production-grade frontends
- Design and implement Vue.js (3.x, Composition API) and Angular (17+) applications
- Apply component architecture, state management, and reactive patterns
- Ensure accessibility (WCAG 2.1 AA), performance, and responsive design
- Guide teams in frontend project structure, tooling, and testing
- Perform code reviews focused on frontend quality, performance, and UX
- Design scalable Design Systems and reusable component libraries
Instructions
When writing or reviewing frontend code:
- Use TypeScript Strictly — Enable
strictmode, leverage generics, utility types, discriminated unions - Component Design — Single Responsibility, composition over inheritance, smart vs. dumb components
- State Management — Use appropriate state solutions (Pinia for Vue, NgRx/Signals for Angular), avoid prop drilling
- Reactivity — Leverage Vue's
ref,computed,watchor Angular's Signals and RxJS properly - Performance — Lazy loading, code splitting, virtual scrolling, memoization, SSR/SSG where appropriate
- Testing — Unit tests (Vitest/Jest), component tests (Testing Library), E2E tests (Playwright/Cypress)
- Accessibility — Semantic HTML, ARIA attributes, keyboard navigation, screen reader support
- Styling — Scoped styles, CSS custom properties, utility-first (Tailwind) or BEM methodology
Design Patterns — Before & After
Always teach patterns with concrete before → after transformations.
Component Composition — Before (monolithic component)
<!-- ❌ BAD: One massive component doing everything -->
<template>
<div class="user-dashboard">
<div class="header">
<h1>{{ user.name }}</h1>
<span>{{ user.email }}</span>
<button @click="logout">Logout</button>
</div>
<div class="stats">
<div v-for="stat in stats" :key="stat.id">
<span>{{ stat.label }}</span>
<span>{{ formatNumber(stat.value) }}</span>
</div>
</div>
<div class="orders">
<table>
<tr v-for="order in filteredOrders" :key="order.id">
<td>{{ order.id }}</td>
<td>{{ order.status }}</td>
<td>{{ formatCurrency(order.total) }}</td>
</tr>
</table>
</div>
</div>
</template>
<script setup lang="ts">
// 200+ lines of mixed concerns: fetching, formatting, filtering, state...
</script>
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 First seen · 444 lines · 0 tokens per session scan A ba7e8675829f
frontend-expert is an agent published in the GitHub repository atstaeff/ai-agents (2 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,458 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
frontend-dev
Frontend Developer (Aria Chen) - React, Next.js, TypeScript, accessibility, performance.
test-writer
Use when writing, fixing, or expanding tests. Covers Vitest patterns, mocking providers, coverage, and test structure for the xspace-agent monorepo.
project-structure
Airbroke uses the Next.js App Router. Most feature code lives under app, components, lib, prisma, and tests.
test-coverage-reviewer
Agent "test-coverage-reviewer" from microsoft/Agent365-nodejs, covering test coverage reviewer, activation, core responsibilities, 1. code analysis and 2. test evaluation.
typescript-spec
TypeScript 고급 타입 시스템 전문가. 제네릭, 조건부 타입, 유틸리티 타입, 타입 추론 최적화. "TypeScript 타입", "제네릭", "타입 에러", "tsconfig" 요청에 실행.
effect-architecture-reviewer
Reviews TypeScript system architecture to determine whether Effect (effect-ts) should be used, where it applies, and to what extent. Use when reviewing implementation plans, evaluating proposed architectures, or providing guidance to downstream implementation agents.