frontend-dev-guidelines

frontend-dev-guidelines is a skill for Claude Code, Codex from tamnguyendinh/Anvien. It costs 17 tokens per session (2,687 once invoked), scanned A, a copy of frontend-dev-guidelines, MIT.

A set of guidelines for building and changing React frontends, which are the user-facing parts of web applications. It covers component structure, data loading, routing, styling, TypeScript, and performance.

In plain words
What is it for?
Use it when creating React components, pages, or features; fetching data; setting up routes; applying MUI styles; or improving frontend loading and code organization.
Why use it?
It gives developers consistent decisions for organizing frontend code and handling loading states, data, and notifications. This reduces guesswork when adding pages or features.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import { featureApi } from '../api/featureApi';.

Good fit Use it when creating React components, pages, or features; fetching data; setting up routes; applying MUI styles; or improving frontend loading and code organization.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/tamnguyendinh/Anvien
agentmods
npx agentmods add skills/tamnguyendinh/anvien/frontend-development

Made for: Claude Code, Codex.

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 frontend-dev-guidelines

README.md
[![agentmods](https://agentmods.dev/badge/skills/tamnguyendinh/anvien/frontend-development/github.svg)](https://agentmods.dev/skills/tamnguyendinh/anvien/frontend-development)
Your own site
<a href="https://agentmods.dev/skills/tamnguyendinh/anvien/frontend-development"><img src="https://agentmods.dev/badge/skills/tamnguyendinh/anvien/frontend-development/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 frontend-dev-guidelines

Your own site · 80×15
<a href="https://agentmods.dev/skills/tamnguyendinh/anvien/frontend-development"><img src="https://agentmods.dev/badge/skills/tamnguyendinh/anvien/frontend-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,687 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 92% copy Near-identical to another mod 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 $0.00017 $0.02687
Opus 5 $0.00009 $0.01344
Sonnet 5 $0.00003 $0.00537
Haiku 4.5 $0.00002 $0.00269

Measured 10d ago against content hash 6e922459392b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

frontend-dev-guidelines 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 10d 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.

Origin

This is a copy

92% identical to frontend-dev-guidelines — 5 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

internal/aicontext/skills/frontend-development/SKILL.md · 400 lines

How it starts

The opening of the file, as written. The whole thing — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Frontend Development Guidelines

Purpose

Comprehensive guide for modern React development, emphasizing Suspense-based data fetching, lazy loading, proper file organization, and performance optimization.

When to Use This Skill

  • Creating new components or pages
  • Building new features
  • Fetching data with TanStack Query
  • Setting up routing with TanStack Router
  • Styling components with MUI v7
  • Performance optimization
  • Organizing frontend code
  • TypeScript best practices

Quick Start

New Component Checklist

Creating a component? Follow this checklist:

  • Use React.FC<Props> pattern with TypeScript
  • Lazy load if heavy component: React.lazy(() => import())
  • Wrap in <SuspenseLoader> for loading states
  • Use useSuspenseQuery for data fetching
  • Import aliases: @/, ~types, ~components, ~features
  • Styles: Inline if <100 lines, separate file if >100 lines
  • Use useCallback for event handlers passed to children
  • Default export at bottom
  • No early returns with loading spinners
  • Use useMuiSnackbar for user notifications

New Feature Checklist

Creating a feature? Set up this structure:

  • Create features/{feature-name}/ directory
  • Create subdirectories: api/, components/, hooks/, helpers/, types/
  • Create API service file: api/{feature}Api.ts
  • Set up TypeScript types in types/
  • Create route in routes/{feature-name}/index.tsx
  • Lazy load feature components
  • Use Suspense boundaries
  • Export public API from feature index.ts

Import Aliases Quick Reference

Alias Resolves To Example
@/ src/ import { apiClient } from '@/lib/apiClient'
~types src/types import type { User } from '~types/user'
~components src/components import { SuspenseLoader } from '~components/SuspenseLoader'
~features src/features import { authApi } from '~features/auth'

Read the full file on GitHub · 400 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. 10d ago First seen · 400 lines · 17 tokens per session scan A 6e922459392b

Subscribe to this mod's changes

frontend-dev-guidelines is a skill published in the GitHub repository tamnguyendinh/Anvien (9 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 2,687 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to frontend-dev-guidelines, differing in 5 lines, and is treated as a copy.