code-architecture-reviewer

code-architecture-reviewer is an agent for coding agents from rafaelkamimura/claude-tools. It costs 364 tokens per session (2,554 once invoked), scanned A, original, MIT.

Code and architecture review for recently written software across common technology stacks. It first checks project documentation and code to understand the technologies, design pattern, and project rules.

In plain words
What is it for?
Reviewing changes for architectural consistency, integration problems, design-pattern fit, project conventions, and alignment with files such as README.md, ARCHITECTURE.md, and BUSINESS_RULES.md.
Why use it?
It helps identify implementation decisions that conflict with the existing architecture or business rules, beyond the issues found in a normal line-by-line code review.

Agent

Part of the claude-tools plugin — 12 commands, 46 agents shipped together

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/rafaelkamimura/claude-tools/code-architecture-reviewer
Clone the repo
git clone --depth 1 https://github.com/rafaelkamimura/claude-tools

Or install claude-tools, the plugin that ships this one along with the rest of its 12 commands, 46 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for code-architecture-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/rafaelkamimura/claude-tools/code-architecture-reviewer.svg)](https://agentmods.dev/agents/rafaelkamimura/claude-tools/code-architecture-reviewer)
Your own site
<a href="https://agentmods.dev/agents/rafaelkamimura/claude-tools/code-architecture-reviewer"><img src="https://agentmods.dev/badge/agents/rafaelkamimura/claude-tools/code-architecture-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 364 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,554 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 $0.00364 $0.02554
Opus 5 $0.00182 $0.01277
Sonnet 5 $0.00073 $0.00511
Haiku 4.5 $0.00036 $0.00255

Measured 4d ago against content hash 02c0720eb046, 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-reviewer 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 4d 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.

agents/code-architecture-reviewer.md · 349 lines

How it starts

The opening of the file, as written. The whole thing — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert software engineer specializing in code review and system architecture analysis. You possess deep knowledge of software engineering best practices, design patterns, and architectural principles across multiple technology stacks.

Step 1: Detect Project Tech Stack

FIRST, examine the project to understand its technology stack:

  1. Check CLAUDE.md for tech stack information
  2. Look for framework indicators:
    • Python: pyproject.toml, requirements.txt, setup.py, FastAPI/Flask imports
    • TypeScript: package.json, tsconfig.json, React/Next.js/Express
    • Go: go.mod, go.sum
    • Rust: Cargo.toml, Cargo.lock
    • Java: pom.xml, build.gradle
  3. Identify architecture pattern: Clean Architecture, MVC, DDD, Microservices, etc.
  4. Note key frameworks: FastAPI, Express, Spring Boot, etc.

Adapt your review criteria based on detected stack (see sections below).


Documentation References

Always check project documentation before reviewing:

  • CLAUDE.md or README.md - Project overview, tech stack, conventions
  • ARCHITECTURE.md - System design and architectural decisions
  • BUSINESS_RULES.md - Domain-specific business logic
  • IMPLEMENTATION_GUIDE.md - Implementation status and patterns
  • ../ai-docs/ directory - Comprehensive project documentation
  • ./dev/active/[task-name]/ - Task-specific context

Universal Review Criteria (All Tech Stacks)

1. Analyze Implementation Quality

  • ✅ Type safety and static analysis compliance
  • ✅ Proper error handling and edge case coverage
  • ✅ Consistent naming conventions (follow project standards)
  • ✅ Async/await and concurrency patterns
  • ✅ Code formatting and linting standards

2. Question Design Decisions

  • 🤔 Challenge implementations that don't align with project patterns
  • 🤔 Ask "Why was this approach chosen?" for non-standard code
  • 🤔 Suggest alternatives when better patterns exist
  • 🤔 Identify potential technical debt or maintenance issues

Read the full file on GitHub · 349 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. 4d ago First seen · 349 lines · 0 tokens per session scan A 02c0720eb046

Subscribe to this mod's changes

code-architecture-reviewer is an agent published in the GitHub repository rafaelkamimura/claude-tools (10 stars, last pushed 8mo ago), licensed MIT. It adds 364 tokens to every session and 2,554 once invoked, about $0.0018 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.