Sponsor Suno AI Music arrow_forward
Slash Command

Arch Init

Initialize projects with architecture-aware templates using paradigm research and selection guidance for the target domain.

Type
Slash Command
GitHub stars
339
License
MIT
Repo last updated
Sep 24, 2026

What Arch Init is

Arch Init is a slash command published in the athola/claude-night-market repository on GitHub, which has about 339 stars. The repository describes itself as: “23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project lifecycle, fix-from-error, maintenance automation, context optimization, research, and multi-LLM delegation. 186 skills, 128 commands, 54 agents.”

A slash command is a reusable prompt saved as a markdown file and run by typing its name after a slash. In Claude Code, custom commands have been merged into skills: a file in .claude/commands/ and a skill folder in .claude/skills/ both create the same kind of command, and existing command files keep working.

Arch Init gives you a repeatable way to run the same instructions without retyping them, optionally with arguments.

How to install Arch Init

Claude Code

  1. Download arch-init.md from the repository.
  2. Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md.
  3. Run it by typing / followed by its name.

Claude Cowork

  1. Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it.
  2. In Customize → Skills, click +, then upload the ZIP.
  3. Run it from any task with / and the skill name.

New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.

Inside the source file

An excerpt from plugins/attune/commands/arch-init.md, shared under the repository's MIT license. Read the full file on GitHub.

Research-driven project initialization that selects appropriate architectural paradigms based on project needs.

When To Use

Use this command when you need to:

  • Start a new project with architecture guidance
  • Choose between architectural paradigms (hexagonal, clean, etc.)
  • Get research-backed architecture recommendations
  • Initialize project with paradigm-specific templates
  • Understand trade-offs of different architectures

When NOT To Use

Avoid this command if:

  • Architecture already decided (use /attune:project-init directly)
  • Simple project without architectural complexity
  • Modifying existing project structure
  • Standard patterns sufficient without special architecture

Usage

# Interactive mode (recommended) - guides through architecture selection
/attune:arch-init --name my-project

# Specify language and let it recommend architecture
/attune:arch-init --name my-project --lang python

# Specify both language and architecture
/attune:arch-init --name my-project --lang python --arch hexagonal

# Accept recommended architecture without prompting
/attune:arch-init --name my-project --lang python --accept-recommendation

What This Command Does

  1. Gathers project context:
  • Project type (Web API, CLI, data pipeline, etc.)
  • Domain complexity
  • Team size and experience
  • Non-functional requirements
  • Timeline constraints
  1. Researches best practices:
  • Searches for current industry standards (2026)
  • Identifies emerging patterns
  • Notes anti-patterns to avoid
  • Finds technology-specific considerations
  1. Recommends architecture paradigm from 14 available options:
  • Layered Architecture
  • Functional Core, Imperative Shell
  • Hexagonal (Ports & Adapters)
  • Modular Monolith
  • Microservices
  • Service-Based Architecture
  • Event-Driven Architecture
  • CQRS + Event Sourcing
  • Serverless
  • Space-Based Architecture
  • Pipeline Architecture
  • Microkernel Architecture
  1. Customizes templates based on chosen paradigm
  1. Creates Architecture Decision Record (ADR) documenting the choice

When to Use This vs project-init

Workflow

# 1. Invoke skill to guide architecture-aware initialization
Skill(attune:architecture-aware-init)

# 2. The skill will:
#    - Gather project context
#    - Research best practices online
#    - Recommend paradigm based on decision matrix
#    - Customize templates for chosen paradigm
#    - Create ADR

# 3. After architecture selected, initializes project
python3 plugins/attune/scripts/attune_arch_init.py \
  --name my-project \
  --lang python \
  --arch hexagonal

Arguments

  • --name - Project name
  • --lang - Project language (python, rust, typescript)
  • --arch - Architecture paradigm (e.g., hexagonal, functional-core, cqrs-es)
  • --accept-recommendation - Accept recommended architecture without prompting
  • --skip-research - Skip online research phase (use decision matrix only)

Architecture Decision Matrix

The command uses a decision matrix based on team size and domain complexity:

Examples

Example 1: Web API for Fintech

/attune:arch-init --name payment-service --lang python

Interactive flow:

Project type: Web API
Domain complexity: Highly Complex (fintech regulations)
Team size: 8 engineers
Requirements: Audit trails, security, compliance

Research results:
- CQRS/Event Sourcing recommended for audit requirements
- Hexagonal also suitable for clean separation

Recommended: CQRS + Event Sourcing
Rationale: Complete audit trail via event log, complex business rules...

Accept recommendation? [Y/n]: y

Creating project structure for CQRS/ES architecture...

Example 2: CLI Tool with Explicit Architecture

/attune:arch-init --name my-cli --lang python --arch functional-core

Creates Functional Core, Imperative Shell structure:

my-cli/
├── src/
│   └── my_cli/
│       ├── core/           # Pure business logic
│       │   ├── domain.py
│       │   ├── operations.py
│       │   └── commands.py
│       └── adapters/       # Side effects
│           ├── cli.py
│           ├── filesystem.py
│           └── config.py
├── tests/
├── docs/
│   └── adr/
│       └── 001-functional-core-architecture.md
└── ...

Output

After completion, you'll have:

  1. Project structure customized to chosen architecture
  2. Configuration files with architecture-appropriate settings
  3. ADR document explaining the architecture choice
  4. Links to paradigm skill for implementation guidance

Before you install

  • Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
  • Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
  • Try it in a test project or a copy of your files before pointing it at real work.
  • Pin the version you tested, and review changes before updating.
  • Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.

FAQ

What is Arch Init?

Arch Init is a slash command for Claude Code and Claude Cowork from the athola/claude-night-market repository on GitHub. Initialize projects with architecture-aware templates using paradigm research and selection guidance for the target domain.

How do I install Arch Init in Claude Code?

Download arch-init.md from the repository. Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md. Run it by typing / followed by its name.

Can I use Arch Init in Claude Cowork?

Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it. In Customize → Skills, click +, then upload the ZIP. Run it from any task with / and the skill name.

Is Arch Init safe to install?

It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.

Similar resources

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under MIT. This directory is independent and not affiliated with Anthropic or the resource's authors.