# Architecture Reviewer

> Perform focused architecture and modularity reviews. Identify boundary violations, god objects, tangled dependencies, and propose the smallest reversible improvements. Use the repo-graph MCP when available. Trigger with "architecture review", "check the boundaries", "is this modular enough?".

- **Type:** Skill
- **Install:** `agentstack add skill-cobusgreyling-grok-build-arsenal-architecture-reviewer`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [cobusgreyling](https://agentstack.voostack.com/s/cobusgreyling)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [cobusgreyling](https://github.com/cobusgreyling)
- **Source:** https://github.com/cobusgreyling/grok-build-arsenal/tree/main/skills/architecture-reviewer

## Install

```sh
agentstack add skill-cobusgreyling-grok-build-arsenal-architecture-reviewer
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Architecture Reviewer

Keeps large codebases from turning into big balls of mud.

## Process

1. Get a structural view (use `repo-graph` MCP or manual exploration + subagents).
2. Map current modules and data flow.
3. Identify:
   - Unclear or violated boundaries
   - High coupling / low cohesion
   - Missing abstractions
   - Opportunities for ports/adapters or domain-driven splits
4. Propose the *smallest* change that meaningfully improves the situation.
5. Always pair recommendations with a plan (hand off to `plan-mode-orchestrator`).

## Output Format

- Current state summary (with diagram if possible)
- Specific problems with file/line evidence
- Recommended improvement + rationale
- Risk of the change
- How to verify the improvement (usually via tests + `repo-graph` diff)

## Ties to Other Skills
- Works extremely well after or with `subagent-arena`.
- Feeds directly into `plan-mode-orchestrator`.
- Use `security-audit` in parallel for security-relevant architecture work.

## Source & license

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

- **Author:** [cobusgreyling](https://github.com/cobusgreyling)
- **Source:** [cobusgreyling/grok-build-arsenal](https://github.com/cobusgreyling/grok-build-arsenal)
- **License:** MIT

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

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-cobusgreyling-grok-build-arsenal-architecture-reviewer
- Seller: https://agentstack.voostack.com/s/cobusgreyling
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.