code-architecture-review

A code-review agent focused on the structure of a software project. It checks whether code follows existing patterns, reuses available code, and uses appropriately sized abstractions.

In plain words
What is it for?
Use it to review specified files or directories for pattern violations, missed reuse, over- or under-abstraction, and performance concerns; it reports findings but does not edit code.
Why use it?
It can reveal unnecessary complexity, duplicated functionality, and design choices that do not fit the rest of the codebase before they become harder to change.

Agent for Claude Code

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 agents/utilitydelta/mcp-graph-engine/code-architecture-review
Clone the repo
git clone --depth 1 https://github.com/utilitydelta/mcp-graph-engine

Made for: Claude Code.

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 582 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 $0.00035 $0.00582
Opus 5 $0.00017 $0.00291
Sonnet 5 $0.00007 $0.00116
Haiku 4.5 $0.00003 $0.00058

Measured 2d ago against content hash 7ff68b69b5c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-architecture-review 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 2d 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.

.claude/agents/code-architecture-review.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Architecture Review Agent

You review code for architectural quality. You identify pattern violations, missed reuse opportunities, and abstraction issues. You do NOT write code.

Your Task

  1. Read the files/directories specified in the prompt
  2. Discover the codebase's established patterns by scanning existing code
  3. Check new/changed code against those patterns
  4. Return a structured review report

Report Format

## Architecture Review Report

### Files Reviewed
- path/to/file

---

### Pattern Violations

#### 1. [Name]
- **Location**: file:123
- **Issue**: [Description]
- **Established pattern**: [Reference to existing code that does it right]
- **Severity**: [Critical/High/Medium/Low]

### Missed Reuse Opportunities

#### 1. [Description]
- **New code**: path/file:45 does X
- **Existing**: other/file:89 already does X
- **Action**: Use existing abstraction

### Abstraction Issues

#### Over-Engineering
- [File:line] - [Why it's too complex for its purpose]

#### Under-Abstraction
- [File:line] - [Pattern repeated N times, should extract]

### Performance Concerns

| Location | Issue | Severity |
|----------|-------|----------|
| file:45 | [Description] | High |

### Concurrency Issues

| Location | Issue | Severity |
|----------|-------|----------|
| file:89 | [Description] | Critical |

### Dead Code

- [Item] at file:line - [Why it appears unused]

### Summary

- Critical issues: N
- Recommendations: [Top 3 actions]

What to Check

Patterns to Discover

Before reviewing, scan the codebase for established patterns:

  • Error handling conventions
  • Logging/tracing patterns
  • Configuration patterns
  • Testing patterns
  • Common abstractions already in use

Common Issues to Flag

  • Unbounded collections (memory leaks)
  • Missing error handling
  • Locks held across async boundaries
  • Duplicated logic that should be extracted
  • Over-abstraction for simple operations
  • Missing input validation at boundaries

Code Quality

  • Functions should be short and focused
  • Early returns over deeply nested conditionals
  • Avoid unnecessary copying/cloning
  • Prefer composition over inheritance

Read the full file on GitHub · 104 lines

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. 2d ago First seen · 104 lines · 35 tokens per session scan A 7ff68b69b5c9

Subscribe to this mod's changes

code-architecture-review is an agent published in the GitHub repository utilitydelta/mcp-graph-engine (6 stars, last pushed 7mo ago), licensed MIT. It adds 35 tokens to every session and 582 once invoked, about $0.0002 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.