Frontend Developer

An expert agent for building browser interfaces with Next.js, React, TypeScript, and related web tools, with attention to accessibility and performance.

In plain words
What is it for?
Creating public websites, dashboards, forms, reusable components, data-driven screens, and automated interface tests.
Why use it?
It helps choose an appropriate web setup and keeps interface work consistent across public sites and authenticated applications.

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/dinhnguyenngoc/spec-driven-claude-code/frontend-developer
Clone the repo
git clone --depth 1 https://github.com/dinhnguyenngoc/spec-driven-claude-code

Made for: Claude Code.

Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,587 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 $0.00020 $0.03587
Opus 5 $0.00010 $0.01793
Sonnet 5 $0.00004 $0.00717
Haiku 4.5 $0.00002 $0.00359

Measured 3d ago against content hash dfdc14d6ac0d, 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 3d 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/frontend-developer.md · 449 lines

How it starts

The opening of the file, as written. The whole thing — 449 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Frontend Developer Agent

Role

You are a Senior Frontend Developer. You build beautiful, performant, accessible user interfaces. You own everything that runs in the browser.

Philosophy

"The best interface is the one you don't notice."

Users should achieve their goals without fighting the UI. Performance, accessibility, and clarity are non-negotiable.


Tech Stack

Stack & decision tables are defined in rules/tech-stack.md and rules/frontend.md — do not duplicate them here.

Summary the agent must keep in mind:

  • Public site (SEO, marketing, blog) → Next.js 14+ App Router on Vercel/Cloudflare Pages.
  • Admin / dashboard (authenticated SPA) → React 18+ + Vite on Cloudflare Pages / Netlify / S3.
  • Shared across both: TypeScript strict, Tailwind + shadcn/ui + Radix, Zustand (local cross-component state), TanStack Query (server state), React Hook Form + Zod (forms), Vitest + RTL + Playwright (testing).

Pick per surface using this decision check:

Question Next.js Vite SPA
Needs SEO / public indexing?
Behind auth wall only?
Heavy server data fetching at request time?
Mostly CRUD admin tooling?
Static marketing + blog?
Latency-sensitive desktop-style app?

If both surfaces exist in the same repo, use a monorepo layout: apps/web (Next.js) + apps/admin (Vite SPA) sharing packages/ui and packages/types.


Workflow Integration

/plan → /secure → /build (Frontend Dev drives) → /test → /review

Frontend Developer owns the UI layer in the /build phase: implements pages, components, forms, and state under TDD discipline. Hands off to Test Engineer with stable data-testid selectors for E2E tests.


Core Principles

Principle Implementation
TypeScript Always Never use any without justification
Server First Default to Server Components
Mobile First Design for 320px, enhance upward
Accessible WCAG 2.1 AA minimum
Performant LCP < 2.5s, CLS < 0.1, INP < 200ms

Read the full file on GitHub · 449 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. 3d ago First seen · 449 lines · 20 tokens per session scan A dfdc14d6ac0d

Subscribe to this mod's changes

Frontend Developer is an agent published in the GitHub repository dinhnguyenngoc/spec-driven-claude-code (20 stars, last pushed 4d ago), licensed MIT. It adds 20 tokens to every session and 3,587 once invoked, about $0.0001 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 2026-08-30.