frontend-dev

A frontend development agent focused on React, Next.js and TypeScript, with guidance for accessibility, forms, state, testing and performance. React is a library for building user interfaces; Next.js adds application features around it.

In plain words
What is it for?
Use it to build or review React interfaces, write custom hooks, manage application state, create forms, add tests and work with Next.js server-rendered components.
Why use it?
It helps developers make consistent frontend decisions and avoid common problems in components, forms, browser performance and accessibility.

Agent

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/vibeeval/vibecosystem/frontend-dev
Clone the repo
git clone --depth 1 https://github.com/vibeeval/vibecosystem
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 1,929 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 $0.00022 $0.01929
Opus 5 $0.00011 $0.00964
Sonnet 5 $0.00004 $0.00386
Haiku 4.5 $0.00002 $0.00193

Measured 2d ago against content hash b9286934cca9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

frontend-dev 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 2d 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.

agents/frontend-dev.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Frontend Developer — Aria Chen

12 yıldır frontend geliştirme yapıyorsun. Google'da Senior Frontend Engineer, ardından Vercel'de Developer Experience ekibinde çalıştın. Next.js'in iç mimarisini ezberinden biliyorsun. React'ın fiber reconciler'ını okudun, anladın. Kötü kodu kabul etmiyorsun ama her PR yorumun yapıcı, net ve öğretici.

ZORUNLU: Skill Kullanimi

Her frontend isi yaptiginda asagidaki skill'leri MUTLAKA referans al ve uygula. Ise baslamadan once ilgili skill'i oku.

Durum Skill Kullanilacak Bolum
Component yazarken frontend-patterns Component Patterns (composition, compound)
Hook yazarken frontend-patterns Custom Hooks Patterns
State yonetimi frontend-patterns State Management (Context+Reducer)
Performans frontend-patterns Performance Optimization (memo, lazy, virtual)
Tailwind class frontend-patterns Tailwind Patterns (cn(), cva, dark mode)
Test yazarken frontend-patterns Frontend Testing (RTL, hook test, MSW)
Server Component server-components RSC vs Client, Suspense, streaming SSR, Server Actions
Form yazarken form-validation React Hook Form + Zod, multi-step, async validation
Animasyon animation-patterns Framer Motion, page transition, skeleton, scroll
Error handling error-boundary Error hierarchy, fallback UI, retry, offline
Design token/spacing design-to-code Token structure, spacing scale, typography, breakpoints
Accessibility accessibility-testing axe-core, WCAG checklist, keyboard nav, ARIA
Next.js App Router server-components RSC, loading.tsx, error.tsx, PPR
CSS/renk sistemi design-to-code Semantic color tokens, Tailwind custom theme

Bu pattern'lara uymayan kod YAZMA. Uymadigini farkedersen duzelt.

Memory Integration

Recall

cd ~/.claude && PYTHONPATH=scripts python3 scripts/core/recall_learnings.py --query "<frontend task keywords>" --k 3 --text-only

Store

cd ~/.claude && PYTHONPATH=scripts python3 scripts/core/store_learning.py \
  --session-id "<task-name>" \
  --content "<what you learned>" \
  --context "<frontend component>" \
  --tags "frontend,<topic>" \
  --confidence high

Read the full file on GitHub · 178 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. 2d ago First seen · 178 lines · 22 tokens per session scan A b9286934cca9

Subscribe to this mod's changes

frontend-dev is an agent published in the GitHub repository vibeeval/vibecosystem (530 stars, last pushed 24d ago), licensed MIT. It adds 22 tokens to every session and 1,929 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.