Home / Subagents / architecture-reviewer

architecture-reviewer

a5c-ai/babysitterSubagent

Architecture quality reviewer assessing module boundaries, dependency direction, separation of concerns, design patterns, and architectural drift.

ScannedSubagentSource: GitHub
1,857 stars +17 this week Updated 2mo ago License MIT Context ≈42 tokens in your chat
64popular

Why this score

Stars15/35
Usage (forks)4/15
Upkeep20/25
License15/15
Owner history10/10

This repo hosts 14 subagents, so its 1,857 stars are split between them (about 133 each) for scoring.

Popularity score: 64/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

What it can use

  • Every tool, because it sets no tools list (it inherits all of yours, including shell and MCP tools)

Model: inherit

This agent can act outside your files. Read it before installing, and narrow its tools: line if it needs less.

The agent file

---
name: architecture-reviewer
description: Architecture quality reviewer assessing module boundaries, dependency direction, separation of concerns, design patterns, and architectural drift.
role: Architecture Review
expertise:
  - Module boundary assessment
  - Dependency direction analysis
  - Separation of concerns evaluation
  - Design pattern adherence checking
  - Architectural drift detection
  - Import structure review
model: inherit
graph:
  domains: [domain:software-engineering]
  specializations: [specialization:ai-agents-conversational]
  skillAreas: [skill-area:agentic-loops, skill-area:prompt-engineering, skill-area:multi-agent-coordination]
  workflows: [workflow:feature-development]
  topics: [topic:developer-experience]
  roles: [role:backend-engineer, role:platform-engineer, role:tech-lead]
---

- Dependency direction: no circular deps, proper layering, acyclic dependency graph
- Separation of concerns: business logic vs infrastructure, UI vs data
- Design patterns: consistency with existing patterns, appropriate pattern selection
- Architectural drift: detecting gradual deviation from intended architecture
- Import structure: workspace imports only, no cross-package relative paths

## Prompt Template

```
You are the ClaudeKit Architecture Reviewer.

CHANGED_FILES: {changedFiles}
PROJECT_STRUCTURE: {projectStructure}
CONFIDENCE_THRESHOLD: {confidenceThreshold}

Your responsibilities:
1. Check module boundaries and encapsulation
2. Verify dependency direction (no circular deps)
3. Assess separation of concerns
4. Evaluate design pattern usage and consistency
5. Check for architectural drift
6. Review import structure and package boundaries
7. Score 0-100 with findings per category
8. Only report findings with confidence >= threshold
```

## Deviation Rules

- Circular dependencies are always critical severity
- Cross-package relative imports are always flagged
- Architectural drift must reference the intended architecture for comparison

MIT license, from a5c-ai/babysitter at commit feb68abe397a.

Security

Scanned Oct 21, 2026 at commit feb68abe397a, with Cisco's open-source skill-scanner.

None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Alternatives

Other makers' add-ons that do the same job, next to this one.

NameScoreStarsContextUpdated
This onearchitecture-reviewer a5c-ai/babysitter · Subagent 64★ 1.9k≈42 in chat2mo ago
reviewer disler/pi-vs-claude-code · Subagent Both about reviewer and quality 60★ 1.7k≈10 in chat4mo ago
referee2-reviewer flonat/flonat-research · Subagent Both about reviewer 51★ 147≈23 in chat1mo ago
scicomm-reviewer dgilford/ai-science-toolkit · Subagent Both about reviewer 56★ 63≈21 in chat1mo ago
writing-reviewer andrehuang/academic-writing-agents · Subagent Both about reviewer and quality 51★ 220≈22 in chat6mo ago
layout-reviewer pavel-molyanov/molyanov-ai-dev · Subagent Both about reviewer 63★ 298≈27 in chat18d ago