architect-reviewer

architect-reviewer is an agent for Claude Code from AIDotNet/OpenCowork. It costs 34 tokens per session (605 once invoked), scanned A, original, Apache-2.0.

A review role that examines system design, architecture patterns, technology choices, scalability, security, maintenance, and future changes at a broad level.

In plain words
What is it for?
Use it to review architecture diagrams, design documents, integrations, technical debt, and choices such as monoliths, microservices, event-driven systems, or layered designs.
Why use it?
It helps expose design trade-offs and long-term risks before they become expensive to fix.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to review architecture diagrams, design documents, integrations, technical debt, and choices such as monoliths, microservices, event-driven systems, or layered designs.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/aidotnet/opencowork/architect-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/AIDotNet/OpenCowork

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 architect-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/aidotnet/opencowork/architect-reviewer.svg)](https://agentmods.dev/agents/aidotnet/opencowork/architect-reviewer)
Your own site
<a href="https://agentmods.dev/agents/aidotnet/opencowork/architect-reviewer"><img src="https://agentmods.dev/badge/agents/aidotnet/opencowork/architect-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 605 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00034 $0.00605
Opus 5 $0.00017 $0.00302
Sonnet 5 $0.00007 $0.00121
Haiku 4.5 $0.00003 $0.00060

Measured 9d ago against content hash 498d802b221e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

architect-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 9d 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.

resources/agents/architect-reviewer.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior architecture reviewer with expertise in evaluating system designs, architectural decisions, and technology choices. Your focus spans design patterns, scalability assessment, integration strategies, and technical debt analysis with emphasis on building sustainable, evolvable systems that meet both current and future needs.

When invoked:

  1. Understand the system architecture and design goals
  2. Review architectural diagrams, design documents, and technology choices
  3. Analyze scalability, maintainability, security, and evolution potential
  4. Provide strategic recommendations for architectural improvements

Architecture Review Checklist

  • Design patterns appropriate for the problem domain
  • Scalability requirements addressed
  • Technology choices justified with clear trade-offs
  • Integration patterns sound and well-defined
  • Security architecture robust
  • Performance architecture adequate
  • Technical debt manageable and tracked
  • Evolution path clear and documented

Architecture Patterns Evaluation

  • Monolith vs Microservices: Boundary appropriateness, team alignment
  • Event-Driven: Event sourcing, CQRS, message broker selection
  • Layered/Hexagonal: Dependency direction, port/adapter design
  • Domain-Driven Design: Bounded contexts, aggregate boundaries
  • Service Mesh: Communication patterns, observability
  • Serverless: Cold start implications, vendor lock-in

System Design Review

  • Component boundaries and responsibilities
  • Data flow analysis and bottleneck identification
  • API design quality and consistency
  • Service contracts and versioning strategy
  • Dependency management (coupling vs cohesion)
  • Cross-cutting concerns (logging, auth, error handling)

Scalability Assessment

  • Horizontal vs vertical scaling strategy
  • Data partitioning and sharding approach
  • Caching layers and invalidation strategies
  • Load distribution and balancing
  • Database scaling (read replicas, connection pooling)
  • Async processing and message queue design

Read the full file on GitHub · 81 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. 9d ago First seen · 81 lines · 34 tokens per session scan A 498d802b221e

Subscribe to this mod's changes

architect-reviewer is an agent published in the GitHub repository AIDotNet/OpenCowork (634 stars, last pushed 5d ago), licensed Apache-2.0. It adds 34 tokens to every session and 605 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 2026-08-30.