AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Architect

skill-arbazkhan971-godmode-architect · by arbazkhan971

Software architecture design — system architecture, monolith/microservices/serverless/event-driven trade-offs, C4 diagrams, ADRs, CQRS, hexagonal.

No reviews yet
0 installs
36 views
0.0% view→install

Install

$ agentstack add skill-arbazkhan971-godmode-architect

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-arbazkhan971-godmode-architect)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
5mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Architect? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Architect — Software Architecture Design

Activate When

  • User invokes /godmode:architect
  • User says "design the architecture", "system architecture", "architectural design", "system design"
  • User asks about monolith vs. microservices, serverless, or event-driven decisions
  • When starting a greenfield project that needs structural decisions
  • When /godmode:think identifies architecture as the primary concern
  • When a system is hitting scaling, reliability, or maintainability walls

Workflow

Step 1: Context & Requirements Gathering

Understand the system before recommending architecture:

ARCHITECTURE CONTEXT:
System: 
Stage: 

Step 2: Architecture Pattern Evaluation

Evaluate candidate patterns against the requirements. Always evaluate at least 3 patterns:

Pattern Evaluation Template

For each candidate (evaluate at least 3), fill:

PATTERN: 
├── Structure: 
├── Strengths: 
├── Weaknesses: 
└── Best when: 

Candidate patterns: Modular Monolith, Microservices, Serverless/FaaS, Event-Driven, CQRS, Hexagonal (Ports & Adapters). Evaluate the top 3-6 for the system.

Step 3: Architecture Comparison Matrix

Present a structured comparison:

  ARCHITECTURE COMPARISON — 

Step 4: C4 Architecture Diagrams

Produce diagrams at all four C4 levels for the chosen architecture:

Level 1: System Context

Who uses the system and what external systems does it interact with?

C4 CONTEXT DIAGRAM:
  Users / Actors
Level 2: Container Diagram

What are the major deployable units?

C4 CONTAINER DIAGRAM:
  > 
Level 3: Component Diagram

What are the major components within each container?

C4 COMPONENT DIAGRAM — :
  > API Service
Level 4: Code Diagram

What are the key classes/modules and their relationships?

C4 CODE DIAGRAM — :
Show key interfaces, classes, and their relationships.
Use the codebase's actual language idioms (classes for Java/C#,

Step 5: Domain-Driven Design — Strategic View

Map bounded contexts and their relationships:

BOUNDED CONTEXT MAP:

Step 6: Quality Attribute Analysis

For the recommended architecture, analyze non-functional requirements:

QUALITY ATTRIBUTES:
| Attribute | How the architecture addresses it |

Step 7: Architecture Decision Record

Document the decision formally:

# ADR-: 

## Status

Step 8: Artifacts & Transition

  1. Save architecture document: docs/architecture/-architecture.md
  2. Save ADR: docs/adr/-.md
  3. Save diagrams inline in the architecture document
  4. Commit: "architect: — architecture with C4 diagrams and ADR"
  5. Suggest next steps:
  • "Architecture designed. Run /godmode:ddd to define domain boundaries and aggregates."
  • "Architecture designed. Run /godmode:plan to decompose into implementation tasks."
  • "Architecture designed. Run /godmode:api to design the API layer."

Key Behaviors

Never ask to continue. Loop autonomously until architecture comparison matrix, C4 diagrams, and ADR are complete.

# Analyze architecture dependencies and coupling
npx madge --circular --extensions ts src/
npx dependency-cruiser --validate .dependency-cruiser.cjs src/

IF team size 10 on any module: refactor to reduce. IF circular dependencies > 0: break cycles before adding features.

  1. Requirements before patterns. Understand scale, team, constraints.
  2. Compare >= 3 options. Comparison matrix forces rigor.
  3. C4 diagrams mandatory. Minimum Level 1 + Level 2.
  4. Trade-offs are honest. Every pattern has real downsides.
  5. ADRs capture the "why." Reasoning, not just decision.
  6. Bounded contexts before microservices. Map first, split second.
  7. Validate against the team. Best arch = team can build it.

Output Format

Print on completion:

ARCHITECTURE: {system_name}
Pattern: {selected_pattern} (scored {weighted_total} vs {runner_up_score} for {runner_up})
C4 diagrams: {levels_produced} levels produced

TSV Logging

Log every architecture session to .godmode/architect-results.tsv:

timestamp	system	pattern_selected	patterns_compared	c4_levels	bounded_contexts	quality_attrs	adr_number	verdict

Append one row per session. Create the file with headers on first run.

Quality Targets

  • Target: 80% code coverage on core modules
  • Target: 0 circular dependencies between bounded contexts
  • Max coupling: 30%: adapt. Document. |

| Vendor lock-in risk | Add adapter/port layer. Abstract behind interface. | | Performance bottleneck | Profile first. Add caching/async before restructuring. |

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.