v3.0.0
The Forger's Guide
43+ commands, 20 skills, 12 agents. From idea to deploy, without friction.
01What is Forge?v3.0
We plan first. Not because we're slow — but because the time you 'save' by skipping planning you pay back ten times over in rework, architecture bugs, and code nobody understands.
Forge is a unified planning and construction system for building production-ready SaaS applications with Claude Code. It's a complete factory that takes you from idea to deployed code.
The Philosophy
The Complete Flow
02Installation & First Steps
Mac / Linux
Windows (WSL)
Step 0: What you need first
Before cloning Forge, you need three tools. If you already have them, skip to Step 1.
Claude Code (or Claude Desktop)
What is it? The AI agent you'll use to build. Claude Desktop is the version with a graphical interface — easiest to get started.
Option A — Claude Desktop (recommended if you're not technical):
Download it at claude.ai/download. Claude Code is included automatically.
claude.ai/downloadOption B — CLI only (for advanced users):
npm install -g @anthropic-ai/claude-code
Verify it works:
claude --version
Node.js 18+
What is it? The engine that runs your app's code. Forge needs it to run Next.js.
Mac:
brew install node
Windows (inside Ubuntu/WSL):
curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash - sudo apt-get install -y nodejs
Verify it works:
node --version
GitHub Access (your Forge invite)
What is GitHub? A platform for storing and sharing code — think of it as a specialized Google Drive for software.
- 1Look in your email for a message from noreply@github.com with subject "You've been invited..."
- 2Click "View invitation" → then click "Accept invitation"
- 3If you bought Ultimate: repeat with the second email (Forge Arsenal)
Windows Users
Forge runs natively on macOS and Linux. On Windows, you need WSL 2 (Windows Subsystem for Linux). It takes about 5 minutes:
Open PowerShell as Administrator and run:
wsl --install
Restart your computer when prompted
Open Ubuntu from the Start menu and create your Linux username/password
Inside Ubuntu, install Node.js:
curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash - sudo apt-get install -y nodejs git
Continue with the setup steps above — all commands run inside Ubuntu/WSL
Setup in 4 Steps
Clone the repository
git clone https://github.com/getforja/forge-pro.git ~/forge
Create the forge alias
# For zsh (macOS default) echo "alias forge='cp -r ~/forge/. .'" >> ~/.zshrc source ~/.zshrc # For bash echo "alias forge='cp -r ~/forge/. .'" >> ~/.bashrc source ~/.bashrc
Create your first project
mkdir mi-saas && cd mi-saas forge # Copy all infrastructure npm install # Install dependencies cp example.mcp.json .mcp.json # Configure MCPs (add your keys) npm run dev # Start dev server
Start Claude Code
claude . # Open Claude Code in the project /forge-check # Verify everything is configured /onboarding # Personalized route to get started
What does forge install?
| File / Folder | Purpose |
|---|---|
| CLAUDE.md | Factory OS — The agent's brain (all the rules) |
| .claude/ | Commands, agents, skills, PRPs, AI templates, design systems |
| example.mcp.json | Pre-configured MCPs (you need your own keys) |
| src/ | Source code with Feature-First architecture |
| package.json | Golden Path dependencies (Next.js 16, React 19, etc.) |
03The Forge Flow (End-to-End)
Phase 1: Planning — /plan
The /plan command activates La Herreria, a pipeline of up to 10 skills that transform your idea into an executable Blueprint.
| # | Skill | Output | Time |
|---|---|---|---|
| 1 | Business Model Canvas | BMC-[name].md | ~30 min |
| 2 | Product Definition Report | PDR-[name].md | ~20 min |
| 3 | Tech Spec | TECH-SPEC-[name].md | ~15 min |
| 4 | UX Research | UX-RESEARCH-[name].md | ~40 min |
| 5 | User Stories | USER-STORIES-[name].md | ~30 min |
| 6 | UX Design | UX-DESIGN-[name].md | ~45 min |
| 7 | UI Design Wireframes | UI-WF-[name].md | ~45 min |
| 8 | UI Implementation | Design system + UI + DESIGN.md | ~30 min |
| 9 | Security Audit | SECURITY-AUDIT-[name].md | ~60 min |
| 10 | Master Blueprint | BLUEPRINT-[name].md | ~45 min |
Total: 5-8 hours -> 10 professional documents. Times vary by idea complexity and user interactions.
Optional Skills
Depending on the Build Mode, the pipeline may include:
- —Lean Canvas — Quick BMC alternative for MVPs
- —Job Stories — Alternative to User Stories (When I... format)
- —Pre-Mortem — Risk analysis before building
- —Interview Script — Script for validating with real users
Phase 2: Construction — /build
The /build command takes the approved Blueprint and executes it. It asks how you want to build:
Phase by phase, with your approval at each step. Ideal if you want total control. El Yunque maps real context, generates subtasks, validates with Playwright, and documents learnings.
Delimit → Map → Execute → Shield → Transition
Launches N autonomous agents in parallel sandboxes. Each with a different personality (literal, creative, disruptive). You cherry-pick the best.
Faster but less granular control. Ideal for independent features.
04Planning — La Herreria
The /plan command activates La Herreria, a pipeline of up to 10 skills that transform your idea into an executable Blueprint. Each skill produces a professional document.
The 10 Skills
| # | Skill | Output | Time |
|---|---|---|---|
| 1 | Viability Check | Go / No-Go decision | ~10 min |
| 2 | Business Model Canvas | BMC-[name].md | ~30 min |
| 3 | Product Definition Report | PDR-[name].md | ~20 min |
| 4 | Tech Spec | TECH-SPEC-[name].md | ~15 min |
| 5 | UX Research | UX-RESEARCH-[name].md | ~40 min |
| 6 | User Stories | USER-STORIES-[name].md | ~30 min |
| 7 | UX Design | UX-DESIGN-[name].md | ~45 min |
| 8 | UI Implementation | Design system + UI + DESIGN.md | ~30 min |
| 9 | Security Audit | SECURITY-AUDIT-[name].md | ~60 min |
| 10 | Master Blueprint | BLUEPRINT-[name].md | ~45 min |
Total: 5-8 hours → 10 professional documents. Times vary by project complexity.
Build Modes
La Herreria adapts to your project type:
10+4 skills · 5-8h — Complete pipeline for production products
7 skills · 2-3h — Validate before investing more time
10 skills · 4-6h — No business model needed
4 steps · ~1h — High-conversion landing page
7 steps · 2-4h — Features with Vercel AI SDK + OpenRouter
Project Personalizationv2.8
The /forge-init command personalizes CLAUDE.md for your specific project. It adds an Active Project section, generates a project-specific README, and deactivates irrelevant skills based on your project type.
/forge-init
05El Crisol — Strategic Validationv2.5
El Crisol is an optional phase between /plan and /build. It runs 7 strategic analyses to validate your Blueprint before you invest time building. The output is an interactive HTML dashboard with a Build Confidence Score.
The 7 Analyses
Build Confidence Score
A weighted score from 1-10 across all 7 dimensions. It tells you whether to proceed, adjust, or pivot before writing code.
| Score | Verdict | Action |
|---|---|---|
| 8-10 | Go | Proceed to /build with confidence. |
| 5-7 | Caution | Review weak areas before building. |
| 1-4 | No-Go | Significant issues found. Revisit your plan. |
Output
El Crisol produces an interactive HTML dashboard with Bento Grid layout, Liquid Glass effects, and Chart.js visualizations. All 7 analyses in a single, shareable file.
06Build Modes
When you run /plan, La Herreria asks what you want to build. Each mode activates an optimized pipeline:
10+4 skills · 5-8h
Full pipeline with BMC, PDR, Tech Spec, UX Research, User Stories, UX/UI Design, Security Audit, and Blueprint. For products going to production with real users.7 skills · 2-3h
Reduced pipeline: Lean Canvas, fast PDR, Tech Spec, User Stories, Wireframes, and Blueprint. To validate the idea before investing more time.10 skills · 4-6h
Similar to SaaS but without full BMC (no business model needed for internal tools). Focus on functional UX and efficiency.4 steps · ~1h
Express pipeline: copy strategy, section structure, design system, and deploy. For high-conversion landing pages.7 steps · 2-4h
Specialized pipeline for features using Vercel AI SDK + OpenRouter. Includes pre-configured LEGO templates in .claude/ai_templates/.Mode Comparison
| Mode | Skills / Steps | Time | Use case |
|---|---|---|---|
| Full SaaS | 10+4 skills · 5-8h | 5-8h | Production product with real users |
| MVP to Validate | 7 skills · 2-3h | 2-3h | Validate before investing more time |
| Internal Tool | 10 skills · 4-6h | 4-6h | No business model needed |
| Landing Page | 4 steps · ~1h | ~1h | High-conversion landing page |
| AI Feature | 7 steps · 2-4h | 2-4h | AI-powered features |
Building Blocks
Complete auth with Supabase (Email/Password + OAuth).
InsForge setup — agents-first BaaS alternative.
Polar or Stripe payment integration.
Transactional emails with Resend + React Email.
PWA + push notifications (iOS compatible).
5 Design Systems
Thick borders, vibrant colors, bold typography.
Apple-style layout, asymmetric cards, whitespace.
Soft shadows, extruded elements, tactile feel.
Transparencies, blur, elegant glassmorphism.
Complex gradients, mesh backgrounds, depth.
07Command Reference
Main Pipeline
Complete planning pipeline. 10 skills -> executable Blueprint.
Build from Blueprint. Choose Manual Build or Forge Mode.
Strategic validation — 7 analyses + Build Confidence Score.
Setup & Orientation
Personalized route based on your experience and goal.
Environment diagnostic — MCPs, deps, hooks, credentials.
Load project context from STATE.md. For resuming sessions.
Create high-conversion landing pages with copy and structure.
Implement auth with Supabase (Email/Password) end-to-end.
Audit existing project -> report -> fixes by impact order.
Personalize CLAUDE.md and filter skills by project type.
Reactivate disabled skills from .claude/_inactive/.
InsForge setup — agents-first BaaS alternative.
Design Quality
UX/UI evaluation across 10 dimensions + AI slop detection.
Visual quality micro-refinements. Final pass.
Align UI with the defined design system.
Generate, extract, or sync DESIGN.md — your project's design DNA.
150+ Lighthouse checks: Performance, A11y, SEO, Best Practices.
Product Strategy
Product Vision + 9-section Strategy Canvas.
Pricing and monetization strategy.
North Star Metric — the metric that guides everything.
Competitive analysis + battlecards.
Complete Go-to-Market strategy.
OKRs + Outcome Roadmap.
Business Intelligence
HTML dashboard with SaaS metrics (MRR, CAC, LTV, ROI).
Evaluate MVP -> graduation plan to production-ready SaaS.
Visual Kanban board by User Story (HTML).
Engineering Workflow
Auto ship: merge, test, review, commit, push, PR.
Pre-landing review: 11 Golden Path categories.
Product review with founder mindset.
Retrospective: metrics, sessions, streaks, team-aware.
Security review with 4 attacking agents + Codex.
Token efficiency audit — 8 checks + score + top 5 fixes.
Lifecycle
Update Forge to the latest version.
Remove Forge from the project — leave only your code.
08The Golden Path (Single Stack)
They can have any color they want, as long as it's black.
Henry Ford — No technology choices are made. The perfected stack is executed.
| Layer | Technology | Why |
|---|---|---|
| Framework | Next.js 16 + React 19 + TypeScript | Full-stack, Turbopack 70x faster |
| Styles | Tailwind CSS 3.4 | Utility-first, no context switching |
| Backend | Supabase OR InsForge | Auth + DB + RLS — choose your BaaS |
| AI Engine | Vercel AI SDK v5 + OpenRouter | Native streaming, 300+ models |
| Validation | Zod | Type-safe at runtime and compile-time |
| State | Zustand | Minimal, no Redux boilerplate |
| Testing | Playwright MCP | Automatic visual validation |
| Deploy | Vercel | Zero-config, edge functions |
Backend Choice
What backend do you need?
Supabase
- +Mature ecosystem (6+ years)
- +Enterprise SLAs
- +Extensive documentation
- +Best for human DX
/add-loginInsForge
NEW- +Agents-first design
- +30% fewer tokens on MCP
- +Built-in Model Gateway
- +Self-hosting optimized
/add-insforgeFeature-First Architecture
All the context for a feature lives in one place. You don't jump between 5 folders.
src/
├── app/
│ ├── (auth)/
│ ├── (main)/
│ └── layout.tsx
│
├── features/
│ ├── auth/
│ │ ├── components/
│ │ ├── hooks/
│ │ ├── services/
│ │ ├── types/
│ │ └── store/
│ └── [feature]/
│
└── shared/
├── components/
├── hooks/
├── lib/
└── types/MCPs — Your Senses and Hands
Quality Control
Build/runtime errors in real time. init, nextjs_call, nextjs_docs.Your Eyes
Navigate, capture, and interact with the browser for visual validation.Your Hands
SQL, migrations, RLS policies, table management without CLI.09Specialized Agents
Forge includes 12 agents that activate based on context during the build.
| Agent | Specialty | When it activates |
|---|---|---|
| frontend-specialist | UI/UX implementation | Building interfaces and components |
| backend-specialist | APIs, DB, server logic | Building backend and API routes |
| codebase-analyst | Code analysis | Debugging, refactoring |
| supabase-admin | DB, RLS, migrations | Supabase operations |
| db-architect | Schema design, indexing | Before complex schemas |
| vercel-deployer | Deploy, CI/CD | Deployments to production |
| validacion-calidad | Testing, general QA | Pre-deploy validation |
| testing-engineer | Unit, integration tests | Post-implementation |
| design-critic | UX/UI evaluation | Post-build design review |
| qa-auditor | A11y + Performance + Security | Pre-deploy quality audit |
| observability-engineer | Logging, Sentry, metrics | Pre-deploy to production |
| gestor-documentacion | Docs, changelogs | Project documentation |
Included Design Systems
During UI Design (Skill #8), you can choose one of 5 pre-configured design systems:
Transparencies, blur, elegant glassmorphism.
Thick borders, vibrant colors, bold typography.
Soft shadows, extruded elements, tactile feel.
Apple-style layout, asymmetric cards, whitespace.
Complex gradients, mesh backgrounds, depth.
20 Built-in Skills 20 skills
| Skill | Purpose |
|---|---|
| la-herreria | Planning pipeline orchestrator (10 skills) |
| el-crisol | Strategic validation (7 analyses + dashboard) |
| la-forja | Parallel agent execution in sandboxes |
| impeccable | Design Quality Engine + AI slop detection |
| web-quality | 150+ Lighthouse checks |
| token-auditor | Token efficiency analysis (8 checks + score) |
| karpathy-principles | 4 coding discipline principles |
| memory-manager | Git-versioned memory in .claude/memory/ |
| supabase | Database reference guide |
| insforge | InsForge reference + Model Gateway |
| add-emails | Resend + React Email setup |
| add-payments | Polar or Stripe decision tree |
| add-mobile | PWA + push notifications |
| image-generation | OpenRouter + Gemini text-to-image |
| website-3d | Cinematic landing with scroll-stop |
| video-visuals | Sketchnote branding visuals |
| autoresearch | Karpathy-based auto-optimization |
| skill-creator | Guide for creating custom skills |
| forge-reference | Extended MCPs/hooks/agents reference |
| forge-tips | Progressive contextual tips |
10Security & Auto-Shielding
Security is not an optional step at the end. It's the difference between a product and an attack vector.
Protection Layers
Automatic Hooks (Pre-commit)
Skill #9: Security Audit (during /plan)
Continuous Auto-Shielding (during /build)
7 Fail-Open Hooks
Principle: if a hook fails unexpectedly, it approves the action. It never traps the user.
| Hook | Type | Function |
|---|---|---|
| pre-commit-validation | PreToolUse | TypeScript typecheck before commit |
| security-scan | PreToolUse | Detects secrets, wildcard CORS, debug code |
| auto-format | PostToolUse | Automatic Prettier on file edit |
| test-runner | PostToolUse | Tests related to the edited file |
| cost-tracker | PostToolUse | Usage tracking per session |
| log-tool-usage | PostToolUse | Audit log of tools used |
| stop-hook | Stop | Review Loop when session ends |
claude config set hookMode auto
Adversarial Review v2.6
The /adversarial-review command launches 4 attacking agents that try to break your app from different angles: injection, auth bypass, data exposure, and supply chain. Codex provides a second opinion. Critical findings block deployment.
Critical Security Rules
11Tips System
Forge reveals its capabilities progressively. Instead of showing you 30+ commands at once, it gives you relevant tips based on what you're doing.
Karpathy Principles v2.8
Token Auditor v2.7
The /audit-tokens command analyzes your Forge configuration for token efficiency. It runs 8 checks, generates a 0-100 score, and provides the top 5 fixes to reduce token usage.
3 Types of Tips
System Rules
- —Frequency: every 3-5 messages, not every response
- —Maximum 1 tip per response (of any type)
- —Priority: Security > Git > Tip
- —Don't repeat tips already shown in the session
- —Always actionable — includes the concrete command
- —Read the tone — if you're in a hurry, the tip is omitted
When They Appear
| Moment | Typical Type | Example |
|---|---|---|
| First messages | Tip | /onboarding gives you a personalized route |
| Between /plan skills | Tip | Security Audit coming with ~200 threats |
| Creating DB tables | Security | RLS required from day one |
| Subtask completed | Git | Good time for an atomic commit |
| UI implemented | Tip | /critique evaluates in 10 dimensions |
| Installing package | Security | Verify the package on npmjs.com |
| Feature complete | Git | Create a PR to document the change |
| Long context | Tip | Consider /avivar for a fresh session |
12Cheat Sheet
Your First Project (Quick Start)
# 1. Setup (once) git clone https://github.com/getforja/forge-pro.git ~/forge echo "alias forge='cp -r ~/forge/. .'" >> ~/.zshrc && source ~/.zshrc # 2. New project mkdir my-app && cd my-app forge && npm install cp example.mcp.json .mcp.json # Add your keys # 3. Start with Claude claude . /forge-check # Verify environment /plan # Plan (or /onboarding if first time) /crisol # Strategic validation (optional) /build # Build from Blueprint
Commands by Phase
| Phase | Commands |
|---|---|
| Orientation | /onboarding, /forge-check |
| Strategy | /brujula, /precio, /estrella, /rivales |
| Planning | /plan |
| Construction | /build, /add-login, /add-insforge, /add-payments, /add-emails, /add-mobile, /landing |
| Design Quality | /critique, /polish, /normalize, /design |
| Web Quality | /web-audit |
| Engineering | /inspeccionar, /despachar, /fragua-review, /retro |
| Business Intelligence | /roi, /graduate, /kanban, /metas, /lanzamiento |
| Lifecycle | /update-forge, /eject-forge, /avivar |
| Strategic Validation | /crisol |
Claude Code Keyboard Shortcuts
| Shortcut | Action |
|---|---|
| Ctrl+U | Clear current input |
| @ | Mention a file to include it in context |
| Shift+Enter | New line without sending |
| Esc Esc | Cancel current operation |
| /fork | Create a parallel task |
Git Conventions
# Atomic commit format feat(F1-T1): create auth service with signUp and signIn fix(F1-T3): fix RLS policy for profiles table refactor(F2-T1): extract validation utils test(F3-T2): add permission middleware tests style(F2-T4): align spacing in dashboard # Valid types feat | fix | refactor | test | style | docs | chore
Your next project.
Forged, not generated. Plan first. Forge always.
Ready to start forging?
Get instant access to all 43+ commands, the full planning pipeline, El Crisol strategic validation, and lifetime updates.
Buy Forge — $149