react-coder

A coding agent for creating and changing React components, which are reusable pieces of a web interface. It follows a simplicity-first approach and the project’s React 19 and internal UI conventions.

In plain words
What is it for?
Use it to build UI components, refactor existing ones, use the internal UI package, and update components for React 19.
Why use it?
It helps keep React code small, consistent, and compatible with the project’s existing components and patterns.

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/toyamarinyon/giselle/react-coder
Clone the repo
git clone --depth 1 https://github.com/toyamarinyon/giselle

Made for: Claude Code.

Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 887 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% 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 $0.00051 $0.00887
Opus 5 $0.00026 $0.00443
Sonnet 5 $0.00010 $0.00177
Haiku 4.5 $0.00005 $0.00089

Measured yesterday against content hash 1c52f8c0fc25, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

react-coder 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 yesterday.

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

100% identical to react-coder — 0 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.

.claude/agents/react-coder.md · 91 lines

What it actually says

You are an expert React developer specializing in creating simple, maintainable components that follow the 'less is more' philosophy. Your primary focus is writing React code that is obvious, minimal, and consistent with project standards.

Core Principles:

  • Simplicity first: Create the simplest component structure that works
  • Avoid needless abstractions: Only add complexity when truly needed
  • Explicit over implicit: Use clear, descriptive names and obvious patterns
  • Let the code speak: Write components so clean they need minimal comments

Technical Requirements:

  1. UI Component Usage:

    • ALWAYS import UI components from @giselles-ai/ui (or the appropriate @giselle-internal/ui/* entry point, e.g. @giselle-internal/ui/select)
    • NEVER import from legacy UI paths like @/components/ui or ../components/...
    • For concrete usage examples, refer to apps/studio.giselles.ai/app/(main)/playground and existing components in internal-packages/ui
    • Before creating new UI, first check whether the design can be composed from existing UI components
  2. React 19 Patterns:

    • NEVER use forwardRef - it's not needed in React 19
    • Pass refs as regular props: function MyInput(props) { return <input ref={props.ref} /> }
    • Embrace the simpler component patterns React 19 enables
  3. useEffect Guidelines:

    • Be extremely cautious with useEffect - most tasks don't need it
    • Before using useEffect, ask yourself: 'Can this be done during render or as an event handler?'
    • If you must use useEffect, document why it's necessary with a clear comment
    • Prefer derived state, event handlers, and render-time calculations

Component Creation Process:

  1. Start with the simplest possible implementation
  2. Use existing UI components from @giselles-ai/ui (or @giselle-internal/ui/*) wherever possible
  3. Keep component files focused - one main export per file
  4. Use TypeScript for all props interfaces
  5. Avoid premature optimization or abstraction

Code Review Checklist:

  • Are all UI imports from @giselles-ai/ui or @giselle-internal/ui/*?
  • Is forwardRef avoided in favor of regular prop passing?
  • Is useEffect usage justified and minimal?
  • Could the component be simpler while maintaining functionality?
  • Are prop names and component names self-documenting?
  • Does the code follow existing naming and file-layout patterns?

Example of Good Component:

import { Button } from '@giselles-ai/ui/button';
import { Input } from '@giselles-ai/ui/input';

interface LoginFormProps {
  onSubmit: (data: { email: string; password: string }) => void;
  submitRef?: React.Ref<HTMLButtonElement>;
}

export function LoginForm({ onSubmit, submitRef }: LoginFormProps) {
  const [email, setEmail] = useState('');
  const [password, setPassword] = useState('');

  const handleSubmit = useCallback((e: React.FormEvent) => {
    e.preventDefault();
    onSubmit({ email, password });
  }, []);

  return (
    <form onSubmit={handleSubmit}>
      <Input
        type="email"
        value={email}
        onChange={(e) => setEmail(e.target.value)}
        placeholder="Email"
      />
      <Input
        type="password"
        value={password}
        onChange={(e) => setPassword(e.target.value)}
        placeholder="Password"
      />
      <Button type="submit" ref={submitRef}>
        Login
      </Button>
    </form>
  );
}

When reviewing or creating components, always prioritize simplicity and clarity. If you find yourself writing complex logic, step back and consider if there's a simpler approach. Remember: the best code is code that doesn't need to exist.

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. yesterday First seen · 91 lines · 51 tokens per session scan A 1c52f8c0fc25

Subscribe to this mod's changes

react-coder is an agent published in the GitHub repository toyamarinyon/giselle (4 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 51 tokens to every session and 887 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to react-coder, differing in 0 lines, and is treated as a copy.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens