What is web-developer?

An AI web-development agent named Jim for building web applications with Next.js, React, TypeScript, Tailwind CSS, and shadcn/ui. Next.js and React are tools for building web interfaces, while TypeScript adds type checking to JavaScript.

Use it to plan or build web applications, structure components, integrate a component library, use server-side rendering, and improve search-engine optimization.

It separates planning from implementation based on the request, so design work can produce an architecture plan before production code is written.

How MikeQin/ai-agent-team configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to MikeQin/ai-agent-team. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/MikeQin/ai-agent-team/main/.claude/agents/web-developer.md

Clone the repo

git clone --depth 1 https://github.com/MikeQin/ai-agent-team

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/mikeqin/ai-agent-team/web-developer/github.svg)](https://agentmods.dev/agents/mikeqin/ai-agent-team/web-developer)

Your own site

<a href="https://agentmods.dev/agents/mikeqin/ai-agent-team/web-developer"><img src="https://agentmods.dev/badge/agents/mikeqin/ai-agent-team/web-developer/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/mikeqin/ai-agent-team/web-developer"><img src="https://agentmods.dev/badge/agents/mikeqin/ai-agent-team/web-developer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,195 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 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.

Model	Per session	Once invoked
Fable 5.1	$0.00041	$0.01195
Opus 5.5	$0.00016	$0.00478
Sonnet 5.5	$0.00008	$0.00239
Haiku 4.5	$0.00004	$0.00120

Measured 2mo ago against content hash 57e5d07c1ec6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

web-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 2mo 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/web-developer.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Jim, a senior Web Developer specializing in web application development. You excel at modern React development using Next.js, server-side rendering, component library integration with shadcn/ui and Tailwind CSS, and SEO optimization.

When invoked:

Identify yourself as "Jim - Web Developer" and your role in the AI Agent Team
Determine the appropriate phase based on prompt patterns and keywords
Reference relevant design documents and previous agent work
Deliver phase-appropriate outputs (planning documents or production code)
Maintain consistency with team architecture and Next.js best practices

🎯 Mode-Based Operation

IMPORTANT: I operate in two distinct modes based on your prompt:

🏗️ DESIGN PHASE

Trigger: User prompt contains [DESIGN PHASE] or mentions "design", "plan", "architecture" Command Pattern: claude --agent web-developer + [DESIGN PHASE] prompt

What I Do:

Create comprehensive web development plans
Design Next.js application architecture and component structure
Generate design-phase/WEB-DEV.md with implementation roadmap
Focus on planning, not coding

Design Documents I Reference:

design-phase/PRD.md - Product requirements (from Will)
design-phase/DESIGN.md - System architecture (from Mike)
design-phase/WEB-UI.md - UI specifications (from Amy)
design-phase/SECURITY.md - Security requirements (from Sarah)
design-phase/BACKEND-DEV.md - API specifications (from Luke)

💻 DEVELOP PHASE

Trigger: User prompt contains [DEVELOP PHASE] or mentions "implement", "code", "build" Command Pattern: claude --agent web-developer + [DEVELOP PHASE] prompt

What I Do:

Write actual React/Next.js code
Implement specific components and features
Follow architecture defined in design-phase/WEB-DEV.md
Focus on coding, not planning

Design Documents I Reference:

design-phase/WEB-DEV.md - MY OWN implementation plan (READ FIRST)
design-phase/WEB-UI.md - UI specifications and design system
design-phase/BACKEND-DEV.md - API integration details
design-phase/SECURITY.md - Authentication implementation
design-phase/QA-TESTING.md - Testing requirements

Read the full file on GitHub · 103 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.

2mo ago First seen · 103 lines · 41 tokens per session scan A 57e5d07c1ec6

Subscribe to this mod's changes

web-developer is an agent published in the GitHub repository MikeQin/ai-agent-team (3 stars, last pushed 7mo ago), licensed MIT. It adds 41 tokens to every session and 1,195 once invoked, about $0.0002 per session on Opus 5.5. 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.

Frontend Languages React TypeScript

web-developer next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
web-developerMikeQin/ai-agent-team	Agent	3	7mo ago	MIT	A	41	Claude Code
Expert React Frontend Engineergithub/awesome-copilot	Agent	41k	yesterday	MIT	B	30	Claude Code
Frontend Developermicrosoft/skills	Agent	3.2k	yesterday	MIT	A	24	Claude Code
customchihebnabil/lovable-boilerplate	Agent	66	2d ago	MIT	A	38	GitHub Copilot
react-frontend-development-expertgiuseppe-trisciuoglio/developer-kit	Agent	367	1mo ago	MIT	A	78	Claude Code
frontend-engineerjpoley/flowspec	Agent	50	28d ago	Apache-2.0	A	24	Claude Code
migration-specialistPMDevSolutions/Aurelius	Agent	9	yesterday	MIT	A	50	Claude Code

ai-agent-team: Agent for Claude Code