code-review-architecture

A code-review checklist for software architecture, including hexagonal design, domain-driven design, CQRS, and microservices. These are ways of organizing software and its business logic.

In plain words
What is it for?
Use it to review architecture-focused changes when the project has a project map describing its layers and modules.
Why use it?
It helps identify design problems that may not appear as ordinary coding errors, such as tangled boundaries or tightly coupled services.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/soulcodex/agentic/code-review-architecture
Any agent
npx skills add soulcodex/agentic --skill code-review-architecture
Clone the repo
git clone --depth 1 https://github.com/soulcodex/agentic

Made for: Claude Code, Codex.

Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 812 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00063 $0.00812
Opus 5 $0.00032 $0.00406
Sonnet 5 $0.00013 $0.00162
Haiku 4.5 $0.00006 $0.00081

Measured 3d ago against content hash 57bb3cf0916c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-review-architecture scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/development/code-review-architecture/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review — Architecture

Apply architecture-focused review using the checklist in this skill directory.

Step 0 — Load Project Map

Check for .agentic/project-map.md (this is essential for architecture review):

  • If present: read it. Use the layer structure, key modules table, and non-obvious conventions as the core concern. Architecture reviews depend heavily on knowing which directories map to which layers.
  • If absent: abort this specialized review and suggest running the project-map skill first.

Step 1 — Load Checklist

Read checklist.md in this skill directory and apply every item to the codebase.

Step 2 — Determine Scope

  • If the user specifies files, review those.
  • Otherwise review the current diff: git diff HEAD or staged changes.
  • Do not review files outside stated scope.

Step 3 — Analyze with Architecture-specific Lenses

Work through the checklist systematically. For each issue found, note:

  • File path and line number
  • Risk level: critical / high / medium / low
  • Description of the issue
  • Why it matters
  • Verifiable source reference when the finding is non-obvious

Architecture concerns to focus on:

  • Hexagonal/Clean architecture boundary violations
  • Anemic domain model (DDD anti-pattern)
  • God Aggregate violations
  • CQRS command/query leakage
  • Microservice coupling and shared databases

For aggregate lifecycle violations or async state machine bugs that are too complex for prose, emit a Mermaid stateDiagram-v2 diagram.

Step 4 — Write the Review

Output the review in this exact format:

## Code Review — Architecture

### What Works Well
- [At least one specific positive observation with file reference]

### Findings

#### Critical
- `path/to/domain/order.go:42` [critical] Description. Why it must change. *Source: [Hexagonal Architecture — Alistair Cockburn](https://alistair.cockburn.us/hexagonal-architecture/)*

#### High
- `path/to/application/service.go:18` [high] Description. Why it matters. *Source: ...*

#### Medium
- `path/to/infrastructure/repository.go:7` [medium] Description.

#### Low
- `path/to/pkg/foo.go:5` [low] Minor note.

### Suggested Improvements
[Concrete alternatives and solutions for the most impactful findings]

### Summary
[One paragraph: overall quality, main risks, merge recommendation]

Read the full file on GitHub · 106 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 106 lines · 63 tokens per session scan A 57bb3cf0916c

Subscribe to this mod's changes

code-review-architecture is a skill published in the GitHub repository soulcodex/agentic (10 stars, last pushed 3d ago), licensed MIT. It adds 63 tokens to every session and 812 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.