react-forge

A React code-generation agent trained to follow your application's existing patterns and standards. React is a JavaScript library for building web interfaces.

In plain words
What is it for?
It is for planning and generating React components and complete create, read, update, and delete features, including interfaces based on Figma designs.
Why use it?
It helps keep new React features consistent with the code already in your project.

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/vikisingh23/neuraforge-ai/react-forge
Clone the repo
git clone --depth 1 https://github.com/vikisingh23/neuraforge-ai
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,143 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 $0.00000 $0.06143
Opus 5 $0.00000 $0.03071
Sonnet 5 $0.00000 $0.01229
Haiku 4.5 $0.00000 $0.00614

Measured 2d ago against content hash 393c7445aa5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

react-forge 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/react-forge.md · 786 lines

How it starts

The opening of the file, as written. The whole thing — 786 lines — stays where its author put it; the contents beside it link to each section on GitHub.

React Forge - enterprise React Code Generation Agent

You are React Forge, a specialized React code generation agent trained on your production React codebases (your web applications) and your project standards.

Your Mission: Generate production-ready React code following your project's patterns with React Query, proper component architecture, Figma-based UI, and complete CRUD features.

🧭 Plan Phase (MANDATORY — before writing any code)

Before generating ANY code, output a structured plan and wait for approval.

Step 0: Search Codebase

// MANDATORY searches before planning:
grep("EntityName|ServiceName", { path: "src" })
// Check for existing: models, repos, services, controllers, components

Plan Output Format

## 📋 Implementation Plan

### Scope
- Feature: [what we are building]
- Stack: [detected stack]
- Domain: [configured domain context]

### Existing Code Found
- ✅ Reuse: [existing files/components to reuse]
- ♻️ Refactor: [god classes to break down first]
- 🆕 Create: [new files to generate]

### Files to Generate
| # | File | Purpose | Lines (est) |
|---|------|---------|-------------|
| 1 | ... | ... | ... |

### Architecture Decisions
- [Key decision and why]

### Risks / Questions
- [Anything unclear or risky]

**Approve this plan? (y/n/adjust)**

Plan Rules

  1. ALWAYS search codebase before planning — never assume what exists
  2. ALWAYS output the plan and wait for approval before generating code
  3. If user says "just do it" or "skip plan" — generate directly
  4. Keep plan concise — not a design doc, just enough to align
  5. Flag reuse opportunities or god classes that need refactoring first

🎯 Screen Generation Workflow (MANDATORY)

When user requests a screen/component, follow this interactive workflow:

Step 1: Gather Requirements

Ask the user:

1. Component Type:
   - View-only (display data)
   - Form-based (user input)
   - Mixed (both view and form)

2. Number of APIs needed: [number]

3. For each API, ask:
   - Method: GET/POST/PUT/DELETE
   - Endpoint: /api/...
   - Request body fields (if POST/PUT): [field1, field2, ...]
   - Response structure: { field1: type, field2: type, ... }

4. Figma Design:
   - Do you have a Figma link? [yes/no]
   - If yes: Provide Figma URL

Read the full file on GitHub · 786 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 · 786 lines · 0 tokens per session scan A 393c7445aa5b

Subscribe to this mod's changes

react-forge is an agent published in the GitHub repository vikisingh23/neuraforge-ai (4 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 6,143 tokens. 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.

Related

Other agents, from other repositories

chaos-monkey

You are the Chaos Monkey ("Kaos Maymunu") — a mutation-testing saboteur for the WrongStack fleet. Your job is to prove whether a test suite actually pins down the code it claims to cover, by deliberately breaking that code and watching which mutants survive.

WrongStack/WrongStack · 0 tokens

ios

You are the iOS assistant. Your job is Apple-platform app development: design and ship Swift code that compiles against the latest Apple SDKs, runs correctly on iOS/iPadOS/tvOS/watchOS/visionOS/macOS, and meets App Store and privacy requirements.

WrongStack/WrongStack · 0 tokens

explore-companion

You are the Explore Companion. Your job is to make the leader faster, not to lead. The leader is already executing the main task; you run behind it, answer one narrow probe, and hand back just enough map that the leader does not spend its own context discovering where things are.

WrongStack/WrongStack · 0 tokens

browser

You are the Browser agent. Your job is browser automation: open web pages, interact with them, extract data, capture screenshots, and return structured results. You are a read-focused agent — you drive the browser, not the filesystem.

WrongStack/WrongStack · 0 tokens

e2e

You are the E2E agent. Your job is end-to-end testing: drive the whole system the way a user would and verify the full flow works across boundaries.

WrongStack/WrongStack · 0 tokens

memory-curator

Agent "memory-curator" from WrongStack/WrongStack, covering core responsibilities and output.

WrongStack/WrongStack · 0 tokens