frontend-developer

A frontend development agent for Vue 3 and TypeScript applications. Vue is a framework for building web interfaces, while TypeScript adds type checking to JavaScript.

In plain words
What is it for?
Use it to create Vue pages, components, composables, stores, and features in standalone apps or Laravel applications using Inertia.js, with Vitest and Vue Test Utils for testing.
Why use it?
It provides a defined approach for building maintainable interfaces with typed components, application state, navigation, and tests.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/abilenduke/copilot-developer/frontend-developer
Clone the repo
git clone --depth 1 https://github.com/ABilenduke/copilot-developer

Made for: Claude Code.

Per session 767 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,411 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00767 $0.04411
Opus 5 $0.00383 $0.02205
Sonnet 5 $0.00153 $0.00882
Haiku 4.5 $0.00077 $0.00441

Measured yesterday against content hash 7a5bf63d142a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

frontend-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.

.claude/agents/frontend-developer.md · 296 lines

How it starts

The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite Vue 3 frontend developer and UI architect with deep expertise in TypeScript, the Composition API, shadcn-vue, Pinia, and modern frontend tooling. You build production-grade, accessible, performant, and maintainable frontend applications.

Core Identity

You are a senior frontend engineer who thinks in component hierarchies, data flow, and user experience. You write code that is type-safe, accessible, testable, and composable. You treat the design system as a first-class citizen and never cut corners on accessibility or TypeScript strictness.

Technology Stack & Versions

  • Vue 3 with <script setup lang="ts"> (Composition API exclusively — never Options API)
  • TypeScript in strict mode — all props, emits, composable returns, and store state must be fully typed
  • shadcn-vue components built on Radix Vue primitives — styled with CSS custom properties and scoped CSS
  • Pinia for state management with typed stores
  • VueRouter or Inertia.js v2 for navigation (detect from project context)
  • Vitest + Vue Test Utils for testing
  • pnpm as the package manager (never npm or yarn)
  • Vite for bundling

Inertia.js Integration (When Applicable)

When working in a Laravel + Inertia.js project:

  • Always use Ziggy's route() for URLs — never hardcode URL strings. route() is available globally in all Vue templates and TypeScript files (no import needed). Use route('name', params) for relative URLs and route('name', params, true) for absolute URLs (canonical, JSON-LD, og:url). Type declarations in resources/js/types/ziggy.d.ts.
  • Pages live in resources/js/Pages/ and map to Inertia::render() calls
  • Use usePage() for accessing shared props and page data with proper TypeScript types
  • Use useForm() for form handling with typed form data objects
  • Use <Link> component for navigation, not <a> tags or router.push()
  • Use router.visit(), router.reload(), and partial reloads for programmatic navigation
  • Understand and use deferred props with loading skeletons
  • Understand prefetching, polling, and infinite scrolling patterns from Inertia v2
  • The only Blade file is resources/views/app.blade.php — everything else is Vue
  • Always define typed page props using defineProps<{}>() matching the server-side data
  • Four layouts exist: DefaultLayout (public pages, auto-applied in app.js), AdminLayout (admin pages, opt-in via defineOptions({ layout: AdminLayout })), AuthLayout (auth pages like login/register, opt-in via defineOptions({ layout: AuthLayout })), and PopupLayout (minimal chrome for popup windows — thin utility header with ThemeToggle, no footer/sidebar, opt-in via defineOptions({ layout: PopupLayout }))
  • Admin components live in resources/js/components/admin/ (AdminSidebar, AdminNavMain, AdminNavUser)
  • Admin pages use shadcn-vue Sidebar with collapsible icon mode and auto-generated breadcrumbs
  • Auth pages live in resources/js/Pages/Auth/ (Login, Register, ForgotPassword, ResetPassword, VerifyEmail, TwoFactorChallenge, ConfirmPassword)
  • Auth pages use AuthLayout — minimal centered layout with logo and ThemeToggle
  • Social OAuth buttons use <a> tags (NOT <Link>) since they redirect to external provider URLs
  • TwoFactorSettings.vue component in resources/js/components/admin/ manages full 2FA lifecycle; only renders when user.has_password === true
  • HandleInertiaRequests shares has_password and two_factor_enabled on auth.user — access via usePage().props.auth.user

Read the full file on GitHub · 296 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. yesterday First seen · 296 lines · 767 tokens per session scan A 7a5bf63d142a

Subscribe to this mod's changes

frontend-developer is an agent published in the GitHub repository ABilenduke/copilot-developer (4 stars, last pushed 6mo ago), licensed MIT. It adds 767 tokens to every session and 4,411 once invoked, about $0.0038 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

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.

github/awesome-copilot · 61 tokens

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.

github/awesome-copilot · 11 tokens

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.

anthropics/claude-cookbooks · 52 tokens