ForgeCraft

Production engineering standards for any AI coding assistant.

AI coding assistants work better with clear engineering standards. Most start with a generic instruction file — ForgeCraft replaces that with production-grade standards: SOLID principles, testing pyramids, architecture patterns, CI/CD pipelines, domain-specific rules, and quality-gate hooks — all composed from 116 curated template blocks matched to your actual stack.

Supports: Claude (CLAUDE.md) · Cursor (.cursor/rules/) · GitHub Copilot (.github/copilot-instructions.md) · Windsurf (.windsurfrules) · Cline (.clinerules) · Aider (CONVENTIONS.md)

npx forgecraft-mcp setup .

That's it. ForgeCraft scans your project, auto-detects your stack, and generates tailored instruction files in seconds.

claude init vs ForgeCraft

How It Works

# First-time setup — auto-detects your stack
npx forgecraft-mcp setup .

# → scans your code → detects [API] + [WEB-REACT]
# → creates forgecraft.yaml
# → generates CLAUDE.md, .cursor/rules/, etc.
# → adds quality-gate hooks
# → done

ForgeCraft is a setup-time CLI tool. Run it once to configure your project, then remove it — it has no runtime footprint.

optional: add the MCP sentinel to let your AI assistant diagnose and recommend commands:

claude mcp add forgecraft -- npx -y forgecraft-mcp

The sentinel is a single lightweight tool (~200 tokens) that checks your project state and tells your AI what CLI command to run next. Remove it after initial setup to save tokens.

What You Get

After npx forgecraft-mcp setup, your project has:

your-project/
├── forgecraft.yaml        ← Your config (tags, tier, customizations)
├── CLAUDE.md              ← Engineering standards (Claude)
├── .cursor/rules/         ← Engineering standards (Cursor)
├── .github/copilot-instructions.md  ← Engineering standards (Copilot)
├── Status.md              ← Session continuity tracker
├── .claude/hooks/         ← Pre-commit quality gates
├── docs/
│   ├── PRD.md             ← Requirements skeleton
│   └── TechSpec.md        ← Architecture + NFR sections
└── src/shared/            ← Config, errors, logger starters

The Instruction Files

This is the core value. Assembled from curated blocks covering:

• SOLID principles — concrete rules, not platitudes
• Hexagonal architecture — ports, adapters, DTOs, layer boundaries
• Testing pyramid — unit/integration/E2E targets, test doubles taxonomy
• Clean code — CQS, guard clauses, immutability, pure functions
• CI/CD & deployment — pipeline stages, environments, preview deploys
• Domain patterns — DDD, CQRS, event sourcing (when your project needs it)
• 12-Factor ops — config, statelessness, disposability, logging

Every block is sourced from established engineering literature (Martin, Evans, Wiggins) and adapted for AI-assisted development.

24 Tags — Pick What Fits

Tags are domain classifiers. ForgeCraft auto-detects them from your code, or you choose manually. Combine freely — blocks merge without conflicts.

Content Tiers

Not every project needs DDD on day one.

Set in forgecraft.yaml:

projectName: my-api
tags: [UNIVERSAL, API]
tier: recommended

CLI Commands

npx forgecraft-mcp <command> [dir] [flags]

Common flags

--tags UNIVERSAL API     Project classification tags (or read from forgecraft.yaml)
--tier core|recommended  Content depth (default: recommended)
--targets claude cursor  AI assistant targets (default: claude)
--dry-run                Preview without writing files
--compact                Strip explanatory bullet tails and deduplicate lines (~20-40% smaller output)
--apply                  Apply changes (for refresh)
--language typescript    typescript | python (default: typescript)
--scope focused          comprehensive | focused (for review)

MCP Sentinel

Optionally add the ForgeCraft MCP sentinel to let your AI assistant diagnose your project and suggest the right CLI command:

claude mcp add forgecraft -- npx -y forgecraft-mcp

The sentinel is a single minimal tool (~200 tokens per request, vs ~1,500 for a full MCP tool suite). It checks whether forgecraft.yaml, CLAUDE.md, and .claude/hooks exist, then returns targeted CLI commands to run.

Recommended workflow:

1. Add the sentinel temporarily
2. Let Claude run npx forgecraft-mcp setup .
3. Remove the sentinel: claude mcp remove forgecraft
4. Re-add it when you need to refresh or audit

{
  "mcpServers": {
    "forgecraft": {
      "command": "npx",
      "args": ["-y", "forgecraft-mcp"]
    }
  }
}

Already ran claude init? Use npx forgecraft-mcp generate . --merge to merge with your existing CLAUDE.md, keeping your custom sections while adding production standards.

Configuration

Fine-tune what your AI assistant sees

# forgecraft.yaml
projectName: my-api
tags: [UNIVERSAL, API, FINTECH]
tier: recommended
outputTargets: [claude, cursor, copilot]  # Generate for multiple assistants
compact: true                             # Slim output (~20-40% fewer tokens)

exclude:
  - cqrs-event-patterns    # Don't need this yet

variables:
  coverage_minimum: 90      # Override defaults
  max_file_length: 400

Community template packs

templateDirs:
  - ./my-company-standards
  - node_modules/@my-org/forgecraft-flutter/templates

Keeping Standards Fresh

Audit (run anytime, or in CI)

Score: 72/100  Grade: C

✅ Instruction files exist
✅ Hooks installed (3/3)
✅ Test script configured
🔴 hardcoded_url: src/auth/service.ts
🔴 status_md_current: not updated in 12 days
🟡 lock_file: not committed

Refresh (project scope changed?)

npx forgecraft-mcp refresh . --apply

Or in preview mode first (default):

npx forgecraft-mcp refresh .   # shows before/after diff without writing

Contributing

Templates are YAML, not code. You can add patterns without writing TypeScript.

templates/your-tag/
├── instructions.yaml   # Instruction file blocks (with tier metadata)
├── structure.yaml      # Folder structure
├── nfr.yaml            # Non-functional requirements
├── hooks.yaml          # Quality gate scripts
├── review.yaml         # Code review checklists
└── mcp-servers.yaml    # Recommended MCP servers for this tag

PRs welcome. See templates/universal/ for the format.

MCP Server Discovery

npx forgecraft-mcp configure-mcp dynamically discovers recommended MCP servers matching your project tags. Servers are curated in mcp-servers.yaml per tag — community-contributable via PRs.

Built-in recommendations include Context7 (docs), Playwright (testing), Chrome DevTools (debugging), Stripe (fintech), Docker/K8s (infra), and more across all 24 tags.

Optionally fetch from a remote registry at setup time:

# In forgecraft.yaml or via tool parameter
include_remote: true
remote_registry_url: https://your-org.com/mcp-registry.json

Development

git clone https://github.com/jghiringhelli/forgecraft-mcp.git
cd forgecraft-mcp
npm install
npm run build
npm test   # 237 tests, 16 suites

License

MIT