AI Software Architect MCP server
Commit 9. Nov. 2026Ermöglicht es einem AI-Client, Architektur-Dokumentationen aufzusetzen, ADRs zu erstellen, Reviewer aufzulisten, den Status zu prüfen und Implementierungs-Guidance in Markdown-Projekten zu erhalten.
Auch bekannt als codenamev/ai-software-architect
- Stars
- 80
- Tools
- —
- Downloads, 30 Tage
- —
- Neueste Version
- —
- Letzter Commit
- 9. Nov. 2026
- Lizenz
- —
Was ist AI Software Architect MCP?
Ermöglicht es einem AI-Client, Architektur-Dokumentationen aufzusetzen, ADRs zu erstellen, Reviewer aufzulisten, den Status zu prüfen und Implementierungs-Guidance in Markdown-Projekten zu erhalten.
Zusammenfassung generiert aus dem README des Projekts
Über AI Software Architect MCP server
Software Engineers und Architekten können technische Entscheidungsprozesse direkt in ihren AI-Coding-Umgebungen mithilfe dieses Frameworks verwalten. Es bietet eine strukturierte Möglichkeit, Architektur-Dokumentationen zu pflegen, Architecture Decision Records (ADRs) zu erstellen und den Fortschritt der Implementierung über Markdown-Dateien zu überwachen. Das System ist darauf ausgelegt, mit Claude Code und Cursor via MCP server Installation zu funktionieren, oder über ein traditionelles Setup für Nutzer von GitHub Copilot und Codex.
Nutzer können deterministische Aufgaben wie setup_architecture, das Erstellen von ADRs, das Auflisten von Architektur-Mitgliedern und das Prüfen des aktuellen Status von Architektur-Änderungen durchführen. Der Server unterstützt fortgeschrittene Projektanalysen und programmatische Automatisierung, was ihn ideal für Entwickler macht, die Architektur-Governance in ihre bestehenden Workflows integrieren möchten. Während der MCP server die Kern-Tier-1 Tools bereitstellt, ist er speziell für die Arbeit mit Node.js-Umgebungen konfiguriert, um diese Management-Aufgaben zu erleichtern.
Was du damit machen kannst
- 1Architektur-Entscheidungen dokumentierenEin Engineer kann einen AI-Client anweisen, ein formelles Protokoll für eine spezifische technische Entscheidung zu generieren.
- 2Architektur-Fortschritt überwachenEin Developer kann den aktuellen Stand der architektonischen Implementierung seines Projekts abfragen.
- 3Architektur-Teammitglieder verwaltenNutzer können eine Liste von Personen oder Rollen abrufen, die dem Architekturprozess zugewiesen sind.
- 4Implementierungs-Guidance erhaltenEntwickler können das Framework nutzen, um den Coding-Prozess basierend auf etablierten Architektur-Patterns zu steuern.
Geschrieben aus dem README des Projekts. Jeder Use Case wurde gegen ein Zitat daraus geprüft.
Konfiguration
CLAUDE_PLUGIN_ROOT
| Name | Beschreibung | Typ |
|---|---|---|
| CLAUDE_PLUGIN_ROOT | — |
Automatisierte Checks
Geluften am 14. Nov. 2026Vollständiger Bericht →Noch nicht verifiziert. Ein Server benötigt einen Score von 80, keine kritischen Befunde und genug Daten für unsere Prüfung. Wie die Checks funktionieren · Was du für mehr Punkte verbessern kannst
- Source Repository verknüpft und erreichbarcodenamev/ai-software-architect is public and reachablegithub.com/codenamev/ai-software-architect ↗Bestanden
- Paket nennt dieses Repository als QuelleNicht geprüft
- Build-Provenienz (Sigstore-Attestierung)Nicht geprüft
- Open Source Lizenz (OSI)No licenseBefund
- Commit oder Release im letzten JahrLast commit or release 2026-11-09github.com/codenamev/ai-software-architect ↗Bestanden
- OpenSSF ScorecardNicht geprüft
- Package-Name ähnelt keinem populären PackageNicht geprüft
- Keine kritischen Advisories im Paket oder seinen AbhängigkeitenNicht geprüft
- Keine versteckten Anweisungen an das Modell0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersBestanden
- Destruktive Tools sind markiertNicht geprüft
- Remote-Endpoint beantwortet den MCP-HandshakeNicht geprüft
README
Auf GitHub ansehenAI Software Architect
A markdown-based framework for implementing rigorous software architecture practices in any project, with specialized AI assistant integration.
Overview
This framework provides a structured approach to:
- Architecture Documentation - Templates and processes for documenting architectural decisions
- Architecture Reviews - A multi-perspective review process with specialized reviewers
- Architecture Recalibration - Process for translating reviews into concrete implementation plans
- Progress Tracking - Tools for monitoring the implementation of architectural changes
- AI Integration - Seamless collaboration with AI coding assistants
For detailed usage instructions, see USAGE.md. For troubleshooting and advanced usage, see TROUBLESHOOTING.md.
Installation
Choose the installation method for your AI assistant:
Claude Code Installation
Claude Code supports three installation methods:
Option 1: Claude Code Plugin (Recommended) 🆕
Install via the Claude Code plugin system with automatic updates:
# In Claude Code, run these commands:
/plugin marketplace add codenamev/ai-software-architect
/plugin install ai-software-architect@ai-software-architect
That's it! The framework is now available in all your projects — including the seven skills, MCP server, and generated subagents as a single unit.
See USAGE-WITH-CLAUDE-PLUGIN.md for detailed installation guide, troubleshooting, and comparison with other methods.
Benefits: Simplest installation, automatic updates, works across all projects, no manual file management, ships skills + MCP + hooks as a unit
When to use: You use Claude Code and want the most streamlined experience with automatic updates.
Option 2: MCP Server
npm install -g ai-software-architect
Then register it with Claude Code (claude mcp add ai-software-architect -- mcp), or add it to ~/.claude.json (user scope) or your project's .mcp.json:
{
"mcpServers": {
"ai-software-architect": {
"command": "mcp",
"args": []
}
}
}
The npm package carries the server, not the framework tree: setup_architecture installs from the Claude Code plugin if present, otherwise from a clone named by CLAUDE_PLUGIN_ROOT in the server's env (see mcp/README.md). The other five tools read the project's own .architecture/ and need no framework tree.
Benefits: Programmatic automation, external tool integration, advanced project analysis
When to use: You need programmatic access or integration with other MCP-compatible tools.
Option 3: Traditional Setup
Setup architecture using: https://github.com/codenamev/ai-software-architect
See USAGE-WITH-CLAUDE.md for detailed instructions.
Benefits: No installation required, works immediately, maximum flexibility
When to use: Quick experiments, no installation permissions, or maximum customization needs.
Cursor Installation
If you're using Cursor, you have two options:
Option 1: MCP Server (Recommended)
npm install -g ai-software-architect
Then configure in Cursor settings (settings.json), pointing CLAUDE_PLUGIN_ROOT at a clone so setup_architecture has a framework tree to install from (Cursor has no Claude Code plugin to fall back on; the other five tools read the project's own .architecture/ once it exists and need no framework tree):
{
"mcp.servers": {
"ai-software-architect": {
"command": "mcp",
"args": [],
"env": { "CLAUDE_PLUGIN_ROOT": "/path/to/ai-software-architect" }
}
}
}
Option 2: Traditional Setup
Setup architecture using @https://github.com/codenamev/ai-software-architect
See USAGE-WITH-CURSOR.md for detailed traditional setup instructions.
GitHub Copilot / Codex Installation
MCP Support: GitHub Copilot and Codex currently have limited MCP support. Use the traditional setup method:
Setup architecture using: https://github.com/codenamev/ai-software-architect
See USAGE-WITH-CODEX.md for detailed setup instructions. The framework will be configured with context files that GitHub Copilot and Codex can automatically understand.
Installation Method Comparison
Choose the right installation method for your workflow:
| Feature | Plugin 🆕 | MCP Server | Traditional | Best For |
|---|---|---|---|---|
| Installation | Two commands | npm install -g | Clone repo | Plugin: SimplestMCP: ProgrammaticTraditional: Quick |
| Setup Complexity | ⭐ Simplest | ⭐⭐ Medium | ⭐ Simple | Plugin easiest |
| AI Assistants | Claude Code | Claude, Cursor | All assistants | Plugin: Claude onlyMCP: Claude, CursorTraditional: Universal |
| Invocation | Automatic (MCP + Skills) | Programmatic tools | Natural language | Plugin: SeamlessMCP: PreciseTraditional: Flexible |
| Dependencies | Node.js ≥22 (auto) | Node.js ≥22 | None | Traditional: No depsPlugin & MCP: Node auto-managed |
| Auto-Updates | ✅ /plugin update |
✅ npm update |
❌ Git pull | Plugin & MCP: Auto-update |
| Offline Use | ⚠️ Needs npm | ⚠️ Needs npm | ✅ Full | Traditional: Offline ready |
| Tier-1 Deterministic Tools | ✅ All 6 | ✅ All 6 | ✅ All 6 | All methods identical |
| Tier-2 Reviews / Enforcement | ✅ Skills | ❌ MCP-only install | ✅ Yes | Plugin & Traditional run reviews |
| Advanced Features | ⚠️ 33% | ⚠️ 33% | ✅ 100% | Traditional most complete |
| Input Validation | ✅ Yes | ⚠️ Basic | ❌ No | Plugin best |
| Pragmatic Mode | ✅ Yes | ⚠️ Config only | ✅ Yes | MCP configures; reviews are Tier 2 |
| Dynamic Members | ✅ Yes | ❌ No | ✅ Yes | Plugin & Traditional auto-create |
| Recalibration | ❌ No | ❌ No | ✅ Yes | Traditional only |
| Project Analysis | ✅ Advanced | ✅ Advanced | ⚠️ Basic | Plugin & MCP: Advanced |
| Error Handling | ✅ Explicit | ✅ Explicit | ⚠️ Implicit | Plugin, MCP clearest |
| Documentation | ✅ Detailed | ✅ Detailed | ✅ Detailed | All well-documented |
| Customization | ⚠️ Fork npm pkg | ⚠️ Fork npm pkg | ✅ Easy | Traditional most flexible |
| Multi-Project | ✅ Automatic | ✅ Automatic | ⚠️ Per-project | Plugin, MCP global |
| Version Control | ❌ External | ❌ External | ✅ In repo | Traditional best for VCS |
Recommendation by Use Case
Choose Plugin if (Recommended for most Claude Code users):
- ✅ You use Claude Code exclusively
- ✅ You want the absolute simplest installation (2 commands)
- ✅ You want automatic updates (
/plugin update) - ✅ You're okay with internet dependency for updates
- ✅ You want zero manual file management
Choose MCP Server if:
- You use Claude Code or Cursor
- You want programmatic automation
- You need advanced project analysis
- You're building integrations
- You prefer npm-based package management
Choose Traditional if:
- You use multiple AI assistants (Copilot, Codex, etc.)
- You want maximum flexibility and customization
- You need recalibration (only the Traditional path implements it)
- You want the framework files in your repository
- You need offline capability with full features
Feature Availability Matrix
| Feature | Plugin 🆕 | MCP Server | Traditional |
|---|---|---|---|
| Setup Architecture (Tier 1) | ✅ | ✅ | ✅ |
| Create ADR (Tier 1) | ✅ | ✅ | ✅ |
| List Members (Tier 1) | ✅ | ✅ | ✅ |
| Get Status (Tier 1) | ✅ | ✅ | ✅ |
| Configure Pragmatic Mode (Tier 1) | ✅ | ✅ | ✅ |
| Implementation Guidance (Tier 1) | ✅ | ✅ | ✅ |
| Architecture Review (Tier 2) | ✅ Skills | ❌ MCP tool | ✅ |
| Specialist Review (Tier 2) | ✅ Skills | ❌ MCP tool | ✅ |
| Pragmatic Enforcement (Tier 2) | ✅ Subagent | ❌ MCP tool | ✅ |
| Dynamic Member Creation | ✅ | ❌ | ✅ |
| Recalibration Process | ❌ | ❌ | ✅ |
| Initial System Analysis | ✅ | ✅ | ✅ |
| Input Validation | ✅ | ⚠️ | ❌ |
| Tool Restrictions | ✅ | N/A | N/A |
| Auto-Update | ✅ | ✅ | ❌ |
Legend: ✅ Fully supported, ⚠️ Partially supported, ❌ Not supported, N/A Not applicable
Note: The Plugin bundles the same npm package as the MCP Server option, plus the seven skills, generated subagents, and ADR-validation hook as a single install unit.
Two-tier capability model (see ADR-015): Tier-1 operations are deterministic file/config tasks available on every channel, including the MCP server. Tier-2 capabilities — orchestrated architecture reviews, specialist reviews, and pragmatic enforcement — require LLM reasoning and are delivered only through the plugin/Skills (architecture-review, specialist-review, and the pragmatic-enforcer subagent), not as MCP tools. The Plugin gets Tier 2 via its bundled Skills; an MCP-only install does not.
See Feature Parity Analysis for detailed comparison.
Quick Installation Decision Tree
Do you use Claude Code?
├─ Yes → ✅ Choose Plugin (simplest, ships skills + MCP + hooks together)
│
└─ No → Do you use Cursor?
├─ Yes → ✅ Choose MCP Server (Cursor compatible)
└─ No → Choose Traditional (universal — Copilot, Codex, etc.)
Still unsure? Start with Plugin if you use Claude Code. It's the easiest to set up and you can always switch later. All methods provide identical core functionality.
Getting Started
After installation, start using the framework with these standardized commands:
Standard Commands
Setup:
Setup ai-software-architect
Create ADR:
Create ADR for [decision topic]
Example: "Create ADR for PostgreSQL database choice"
Architecture Review:
Start architecture review for [version/feature]
Examples: "Start architecture review for version 2.0.0" or "Start architecture review for authentication feature"
Specialist Review:
Ask [Specialist Name] to review [target]
Example: "Ask Security Specialist to review API authentication"
List Members:
List architecture members
Check Status:
What's our architecture status?
Enable Pragmatic Mode (Optional):
Enable pragmatic mode
Example: "Enable pragmatic mode with balanced intensity"
Implement with Methodology:
Implement [feature] as the architects
Examples: "Implement authentication as the architects" or "Implement user registration as the architects"
Recalibration (Traditional method):
Start architecture recalibration for [target]
See USAGE.md for detailed workflow instructions and platform-specific variations.
Upgrading
Already have AI Software Architect installed? Update to get the latest features and improvements.
Quick Update (Recommended)
For any AI assistant, simply ask:
Update the software architect framework from https://github.com/codenamev/ai-software-architect
Your AI assistant will fetch the latest framework files from the main branch while preserving your project's architecture artifacts (ADRs, reviews, recalibration plans).
Manual Update Methods
If using the Claude Code Plugin:
# In Claude Code:
/plugin update ai-software-architect@ai-software-architect
This updates the plugin wrapper and everything it bundles (skills, MCP server, generated subagents, ADR-validation hook) as one unit. The standalone ~/.claude/skills/ copy was retired in 1.4.0 (ADR-012); if you still have one, remove it and install the plugin.
If using MCP Server:
# Update to latest version
npm update -g ai-software-architect
# Or reinstall
npm install -g ai-software-architect
If using Traditional Setup: follow UPGRADE.md. Do not run git fetch / git reset --hard inside .architecture/ — setup removes that directory's .git, so those commands resolve to your own project repository and reset --hard discards your uncommitted work.
Note: Updates preserve your project's custom architecture artifacts (ADRs, reviews, member customizations) while updating framework files (templates, base configuration, scripts).
What Gets Updated
✅ Updated Files:
.architecture/templates/- Templates for ADRs, reviews, AGENTS.md.architecture/principles.md- Core architectural principles (if not customized)- Framework scripts and helper files
- MCP server (if using MCP installation)
- Plugin skills, subagents, and hook (if using the plugin installation)
✅ Preserved Files:
.architecture/decisions/adrs/- Your architectural decision records.architecture/reviews/- Your architecture review documents.architecture/recalibration/- Your recalibration plans.architecture/members.yml- Your customized team members.architecture/config.yml- Your configuration settings- All your project-specific customizations
See UPGRADE.md for detailed upgrade instructions and troubleshooting.
Directory Structure
.architecture/
├── decisions/
│ ├── adrs/ # Architectural Decision Records
│ └── principles.md # Architectural principles document
├── reviews/ # Architecture review documents
├── recalibration/ # Recalibration plans and tracking
├── comparisons/ # Version-to-version comparisons
├── docs/ # General architecture documentation
├── agent_docs/ # Detailed AI assistant guidance (progressive disclosure)
├── templates/ # Templates for various documents
└── members.yml # Architecture review team members
Usage with AI Assistants
This framework is designed to work seamlessly with AI assistants. Each assistant has specialized instructions in the .coding-assistants directory.
For general usage instructions, see USAGE.md.
Claude Code
For Claude Code users, see USAGE-WITH-CLAUDE-PLUGIN.md (recommended plugin-based install) or USAGE-WITH-CLAUDE.md (traditional clone-based path) for detailed instructions.
Available Skills (installed with the Claude Code plugin):
- setup-architect: Automatically sets up and customizes the framework
- create-adr: Creates Architectural Decision Records
- architecture-review: Conducts comprehensive multi-perspective reviews
- specialist-review: Gets focused reviews from specific experts
- list-members: Shows your architecture team
- architecture-status: Displays current documentation state
- pragmatic-guard: Enables Pragmatic Guard Mode (YAGNI enforcement)
Standard Commands:
- Setup: "Setup ai-software-architect"
- Create ADR: "Create ADR for [topic]"
- Architecture Review: "Start architecture review for [version/feature]"
- Specialist Review: "Ask [Specialist Name] to review [target]"
- List Members: "List architecture members"
- Check Status: "What's our architecture status?"
- Recalibration: "Start architecture recalibration for [target]" (Traditional method)
Alternative Phrases:
- Setup: "Setup .architecture", "Initialize architecture framework"
- Create ADR: "Document architectural decision for [topic]", "Write ADR about [topic]"
- Reviews: "Conduct architecture review", "Review architecture for [scope]"
- Specialist: "Get [specialist]'s opinion on [topic]", "Have [role] review [component]"
Adding new specialists: edit .architecture/members.yml directly and run node tools/cli.js generate-subagents to refresh the corresponding agents/<id>.md subagent. Auto-creation during specialist-review was removed in 1.5.0 (see ADR-013) — the trade-off keeps the generated subagents and members.yml in sync at all times.
Cursor
For Cursor users, see USAGE-WITH-CURSOR.md for detailed instructions.
Standard Commands:
- Setup: "Setup ai-software-architect"
- Create ADR: "Create ADR for [topic]"
- Architecture Review: "Start architecture review for [version/feature]"
- Specialist Review: "Ask [Specialist Name] to review [target]"
- List Members: "List architecture members"
- Check Status: "What's our architecture status?"
Natural Alternatives (Cursor also understands):
- "Review this architecture"
- "Analyze this from a security perspective"
- "Create an ADR for this decision"
Cursor uses .mdc rule files in the .coding-assistants/cursor/ directory to understand the framework.
GitHub Copilot / Codex
For GitHub Copilot and OpenAI Codex users, see USAGE-WITH-CODEX.md for detailed instructions.
Natural Language Commands (context-based recognition):
- Setup: "Setup architecture"
- Create ADR: "Create an ADR for [decision]"
- Architecture Review: "Review this architecture", "Start architecture review for [target]"
- Specialist Review: "Review this for security issues", "Analyze this for performance"
- Check Status: "Summarize our architectural decisions"
Key Features:
- No need to mention the framework explicitly
- Context-based recognition from project files
- Inline architectural guidance in your IDE
- Code generation following established patterns
- Natural conversation about architecture
Example Commands:
- "What are the architectural implications of this change?"
- "Review this database schema for performance"
- "Does this code follow our architectural principles?"
Other AI Assistants
Support for additional AI assistants can be added by creating appropriate configuration files in the .coding-assistants directory following the established patterns.
Key Features
Architectural Wisdom
The framework incorporates wisdom from influential software architects including Martin Fowler, Sandi Metz, Robert C. Martin, Eric Evans, Sarah Mei, Obie Fernandez, and others. These principles are embedded in the architectural documentation.
Externalizing Senior Thinking: The framework systematically captures "senior engineering thinking"—the invisible architectural reasoning about blast radius, reversibility, timing, and social cost that typically stays undocumented. By forcing explicit documentation of these considerations, we're creating the corpus of senior architectural thinking that the industry lacks.
Multi-Perspective Reviews
Architecture reviews consider multiple specialized perspectives:
- Systems Architecture
- Domain Expertise
- Security
- Performance
- Maintainability
- Implementation Strategy (HOW and WHEN)
- AI Engineering
- And dynamically created specialists as needed
Pragmatic Mode (YAGNI Enforcement)
Pragmatic Mode helps prevent over-engineering by adding a "Pragmatic Enforcer" who:
- Challenges complexity - Questions abstractions, patterns, and "best practices" that may not be needed yet
- Proposes simpler alternatives - Suggests minimal implementations that meet current requirements
- Calculates trade-offs - Scores necessity vs. complexity (target ratio <1.5)
- Tracks deferrals - Documents decisions to defer features with clear trigger conditions
When to use:
- New projects or MVPs
- Teams prone to over-engineering
- Resource-constrained environments
- Projects with tight deadlines
Configurable intensity:
- Strict: Challenges aggressively, requires strong justification
- Balanced: Thoughtful challenges, accepts justified complexity (recommended)
- Lenient: Raises concerns without blocking
Exemptions for Critical Areas: Pragmatic Mode maintains rigorous standards for:
- Security-critical features: Authentication, authorization, encryption, input validation
- Data integrity: Database transactions, data validation, backup strategies
- Compliance requirements: GDPR, HIPAA, PCI-DSS, audit logging
- Accessibility: WCAG compliance, screen reader support
Enable with:
Enable pragmatic mode
See ADR-002 and Pragmatic Mode Summary for details.
Using with Implementation Guidance: When using both Pragmatic Mode and Implementation Guidance together, pragmatic mode respects your configured security practices and methodological choices while challenging unnecessary complexity in other areas. The pragmatic enforcer ensures implementations remain simple while still following your team's documented standards for security, testing, and code quality.
Implementation Guidance
Configuration-driven implementation that applies your team's methodology and best practices automatically:
Configure once:
implementation:
enabled: true
methodology: "TDD"
influences:
- "Kent Beck - TDD by Example"
- "Sandi Metz - POODR"
- "Martin Fowler - Refactoring"
Then simply say:
Implement authentication as the architects
Benefits:
- 90% prompt reduction¹: 4 words instead of 40+
- Consistent quality: Methodology applied systematically
- Team standards: Documented practices in version control
- Cross-session persistence: Configuration always applied
Supports:
- Multiple methodologies (TDD, BDD, DDD, Test-Last, Exploratory)
- Coding influences (Kent Beck, Sandi Metz, Martin Fowler, Gary Bernhardt, etc.)
- Language-specific practices and style guides
- Security practices (always applied, exempt from YAGNI)
- Quality standards and refactoring guidelines
Use with:
Implement [feature] as the architects
¹ Measurement methodology documented in ADR-004 § Validation
See ADR-004 for details.
Feature-Based Architecture Management
The framework now supports:
- Version-based reviews and recalibration (e.g., for v2.1.0)
- Feature-based reviews and recalibration (e.g., for "payment processing")
- Component-specific reviews (e.g., for "authentication system")
License
MIT
AI Software Architect MCP Fragen
Wie installiere ich AI Software Architect als MCP server?
Führe npm install -g ai-software-architect aus und registriere ihn anschließend mit deinem Client über den mcp command, zum Beispiel claude mcp add ai-software-architect -- mcp. Du kannst ihn auch zu deiner .mcp.json oder deinen Cursor Settings hinzufügen.
Unterstützt der MCP server Architektur-Reviews?
Nein. Reviews, Specialist Reviews und pragmatische Durchsetzung sind Tier-2 Capabilities, die LLM-Reasoning erfordern und nur über die Skills des Claude Code Plugins verfügbar sind, nicht als MCP tools.
Was kann der MCP server für mein Projekt tun?
Er stellt sechs deterministische Tools bereit: setup_architecture, create ADR, list members, get status, configure pragmatic mode und implementation guidance. Die fünf Tools außer setup_architecture lesen das projektinterne .architecture/ Verzeichnis aus.
Welche AI Clients können diesen Server nutzen?
Er funktioniert mit Claude Code und Cursor, mit eingeschränktem MCP Support in GitHub Copilot und Codex. Für Copilot und Codex empfiehlt das README das traditionelle Setup.
Welche Konfiguration benötigt setup_architecture in Cursor?
Setze die Umgebungsvariable CLAUDE_PLUGIN_ROOT auf einen Clone des Repositorys, da Cursor kein Claude Code Plugin als Fallback hat. Die anderen Tools benötigen dies nicht, sobald .architecture/ existiert.