rapid-prototype

rapid-prototype is a command for coding agents from Dokkabei97/forged-claude-code. It costs 25 tokens per session (1,045 once invoked), scanned A, original, MIT.

A command that turns a feature description into a working prototype with an API, a user interface, or either one. A prototype is an early version used to test an idea or technical approach.

In plain words
What is it for?
Use it to prototype features such as photo uploads with generated captions, choosing a stack automatically or selecting Next.js or FastAPI explicitly.
Why use it?
It provides something runnable for demos and early user feedback before the full product is built.

Command

Part of the forged-claude-code plugin — 29 skills, 14 commands, 9 agents, 2 hooks 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 commands/dokkabei97/forged-claude-code/rapid-prototype
Clone the repo
git clone --depth 1 https://github.com/Dokkabei97/forged-claude-code

Or install forged-claude-code, the plugin that ships this one along with the rest of its 29 skills, 14 commands, 9 agents, 2 hooks.

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 rapid-prototype

README.md
[![agentmods](https://agentmods.dev/badge/commands/dokkabei97/forged-claude-code/rapid-prototype.svg)](https://agentmods.dev/commands/dokkabei97/forged-claude-code/rapid-prototype)
Your own site
<a href="https://agentmods.dev/commands/dokkabei97/forged-claude-code/rapid-prototype"><img src="https://agentmods.dev/badge/commands/dokkabei97/forged-claude-code/rapid-prototype.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,045 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 $0.00025 $0.01045
Opus 5 $0.00013 $0.00522
Sonnet 5 $0.00005 $0.00209
Haiku 4.5 $0.00003 $0.00104

Measured 3d ago against content hash 8ab76d39322d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rapid-prototype 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 3d 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.

commands/rapid-prototype.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/rapid-prototype - Quick Prototype Generator

Triggers

  • When you need a working demo for investor presentations
  • When validating a feature idea with real users before full implementation
  • When building a proof-of-concept for technical feasibility

Usage

/rapid-prototype [feature description]
/rapid-prototype "User can upload photos and get AI-generated captions"
/rapid-prototype --stack next       # Force Next.js stack
/rapid-prototype --stack fastapi    # Force FastAPI stack
/rapid-prototype --ui-only          # Frontend only (mock API)
/rapid-prototype --api-only         # API only (no UI)

Behavioral Flow

Phase 1: Feature Analysis

Parse the feature description to identify:

1. Core user action (what the user does)
2. Data entities (what data is involved)
3. External dependencies (APIs, services)
4. UI components needed
5. API endpoints needed

Phase 2: Stack Selection

Auto-detect or use specified stack:

Signal Stack Reason
AI/ML feature FastAPI + React Python ML ecosystem
Form-heavy app Next.js (App Router) Server actions, form handling
Real-time feature Next.js + WebSocket Built-in API routes
Default Next.js Fastest full-stack prototype

Phase 3: Generate Prototype

API Layer:

1. Define data models (TypeScript types / Pydantic models)
2. Create API endpoints (route handlers / FastAPI endpoints)
3. Use in-memory storage or SQLite for MVP (no external DB setup)
4. Add mock data for demo scenarios

UI Layer:

1. Create page layout with Tailwind CSS
2. Build form/input components
3. Wire up API calls
4. Add loading/error states
5. Make it visually presentable (not beautiful, but demo-ready)

Demo Data:

1. Generate realistic seed data
2. Create happy-path demo script
3. Include edge cases for robustness impression

Phase 4: Run & Verify

# Install dependencies
npm install  # or pip install -r requirements.txt

# Start development server
npm run dev  # or uvicorn main:app --reload

# Open in browser
open http://localhost:3000

Read the full file on GitHub · 156 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. 3d ago First seen · 156 lines · 25 tokens per session scan A 8ab76d39322d

Subscribe to this mod's changes

rapid-prototype is a command published in the GitHub repository Dokkabei97/forged-claude-code (2 stars, last pushed 6mo ago), licensed MIT. It adds 25 tokens to every session and 1,045 once invoked, about $0.0001 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.