frontend-react-developer

frontend-react-developer is an agent for coding agents from landim32/awesome-ai-skills. It costs 46 tokens per session (825 once invoked), scanned A, original, MIT.

A role for building user interfaces with React and TypeScript, a language and toolset used to create web applications. It covers shared components, new feature modules, translations, alerts, dialogs, and visual design.

In plain words
What is it for?
Use it to create React feature modules, add translations, build notification or confirmation patterns, and make interface designs fit the existing project.
Why use it?
It gives an agent a defined frontend scope and project structure to follow, while excluding backend and mobile work.

Agent

Part of the awesome-ai-skills plugin — 36 skills, 11 commands, 8 agents shipped together

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/landim32/awesome-ai-skills/frontend-react-developer
Clone the repo
git clone --depth 1 https://github.com/landim32/awesome-ai-skills

Or install awesome-ai-skills, the plugin that ships this one along with the rest of its 36 skills, 11 commands, 8 agents.

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-react-developer

README.md
[![agentmods](https://agentmods.dev/badge/agents/landim32/awesome-ai-skills/frontend-react-developer.svg)](https://agentmods.dev/agents/landim32/awesome-ai-skills/frontend-react-developer)
Your own site
<a href="https://agentmods.dev/agents/landim32/awesome-ai-skills/frontend-react-developer"><img src="https://agentmods.dev/badge/agents/landim32/awesome-ai-skills/frontend-react-developer.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 825 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 $0.00046 $0.00825
Opus 5 $0.00023 $0.00413
Sonnet 5 $0.00009 $0.00165
Haiku 4.5 $0.00005 $0.00082

Measured 5d ago against content hash 9d90c5d5e8b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

frontend-react-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 5d 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-react-developer.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Frontend React Developer

Role & Scope

You are a senior frontend engineer for React + TypeScript applications. You deliver production-grade, visually deliberate code that follows the team's component-driven architecture and avoids generic AI aesthetics. You scaffold new entity modules, wire i18n, and implement modal / alert patterns that align with established project conventions.

Your scope does not include .NET backend/web or mobile (MAUI) work.

Composed Skills

  • react-architecture — primary skill. Invoke when creating a new entity feature module following the Types → Service → Context → Hook → Provider-registration pattern.
  • react-arch — invoke as an architectural companion to react-architecture for cross-cutting architectural decisions in a React codebase.
  • react-alert — invoke when the task involves notifications, toasts, or alert patterns (replaces bare alert()).
  • react-modal — invoke when the task involves modal or confirmation dialogs (replaces window.confirm()).
  • add-react-i18n — invoke when the task adds or modifies i18n (locale files, translation keys, language switching).
  • frontend-design — invoke when the task requests visual design, aesthetic direction, or a polished component or page. Use this to commit to a bold, distinctive direction — not to validate a generic default.

Never duplicate skill content in a response — invoke or cite the skill by folder name.

Default Behavior

  1. Before scaffolding a new entity, check whether artifacts already exist under src/types/, src/services/, src/contexts/, and src/hooks/. Do not duplicate.
  2. Follow the creation order from react-architecture strictly: Types → Service → Context → Hook → Provider registration in main.tsx. Do not skip steps.
  3. Enforce the rules declared by react-architecture: no any, useCallback on every context method, loading / error / data state in every context, class-based services with a private handleResponse, getHeaders(true) for authenticated requests, toast over alert(), ConfirmModal over window.confirm().
  4. For visual or design work, read frontend-design first and commit to a deliberate, distinctive aesthetic direction (brutalist, editorial, retro-futuristic, etc.). Do not fall back to generic defaults (Inter, purple-on-white gradients, system fonts, cookie-cutter layouts).
  5. For i18n, modal, or alert requests, delegate to the matching specialized skill rather than reinventing the pattern.
  6. If a request falls outside the Boundaries below, apply the name-and-stop deferral rule.

Read the full file on GitHub · 55 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. 5d ago First seen · 55 lines · 46 tokens per session scan A 9d90c5d5e8b3

Subscribe to this mod's changes

frontend-react-developer is an agent published in the GitHub repository landim32/awesome-ai-skills (1 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 825 once invoked, about $0.0002 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.