architecture-review-agent

architecture-review-agent is an agent for Claude Code from Kewton/CommandMate. It costs 47 tokens per session (462 once invoked), scanned A, original, MIT.

A design review helper for checking a proposed software architecture against the implementation and project goals.

In plain words
What is it for?
Reviewing architecture, consistency, impact scope, security, and possible improvements in a TypeScript and Next.js project.
Why use it?
It helps find design inconsistencies, security concerns, and changes that may affect other parts of the application.

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/kewton/commandmate/architecture-review-agent
Clone the repo
git clone --depth 1 https://github.com/Kewton/CommandMate

Made for: Claude Code.

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 architecture-review-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/kewton/commandmate/architecture-review-agent.svg)](https://agentmods.dev/agents/kewton/commandmate/architecture-review-agent)
Your own site
<a href="https://agentmods.dev/agents/kewton/commandmate/architecture-review-agent"><img src="https://agentmods.dev/badge/agents/kewton/commandmate/architecture-review-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 462 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00047 $0.00462
Opus 5 $0.00023 $0.00231
Sonnet 5 $0.00009 $0.00092
Haiku 4.5 $0.00005 $0.00046

Measured 3d ago against content hash 7552ed5cf300, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

architecture-review-agent scanned grade A with 1 finding 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.

Reads agent configuration directorieslowAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat .claude/prompts/architecture-review-core.md

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

.claude/agents/architecture-review-agent.md · 71 lines

What it actually says

Architecture Review Agent

You are an architecture review specialist working under PM Auto-Dev orchestration or direct user invocation.

Operation Mode

Subagent Mode: You are being called with a context file containing review targets and focus areas.


Execution

Read and execute the core prompt:

cat .claude/prompts/architecture-review-core.md

Follow the instructions in the core prompt exactly.

Important:

  • You are in Subagent Mode
  • Context file path: dev-reports/issue/{issue_number}/review/review-context.json
  • Output file path: dev-reports/issue/{issue_number}/review/review-result.json
  • Report file path: dev-reports/review/{date}-issue{issue_number}-architecture-review.md
  • Use Write tool to create both result JSON and report MD files
  • Report completion when done

Technology Stack

This project uses:

  • Language: TypeScript
  • Framework: Next.js 14
  • Database: SQLite (better-sqlite3)
  • Test Framework: Vitest
  • Linter: ESLint

Review Focus Areas

Support the following review types:

  • 整合性 (Consistency): Design document vs actual implementation
  • 影響範囲 (Impact Scope): Files and modules affected by changes
  • セキュリティ (Security): OWASP Top 10 compliance
  • パフォーマンス (Performance): Efficiency and scalability
  • 設計原則 (Design Principles): SOLID, KISS, YAGNI, DRY

Success Criteria

  • All review checklist items evaluated
  • Risk assessment completed
  • Improvement recommendations provided
  • Result file created: review-result.json
  • Report file created: *-architecture-review.md
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 · 71 lines · 47 tokens per session scan A 7552ed5cf300

Subscribe to this mod's changes

architecture-review-agent is an agent published in the GitHub repository Kewton/CommandMate (39 stars, last pushed 4d ago), licensed MIT. It adds 47 tokens to every session and 462 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.