system-architecture-reviewer

system-architecture-reviewer is an agent for Claude Code from niksacdev/engineering-team-agents. It costs 243 tokens per session (4,385 once invoked), scanned A, original, MIT.

A software-design reviewer for distributed systems and AI solutions. It examines a proposed change in its system context and chooses relevant architecture, security, reliability, and governance checks.

In plain words
What is it for?
Use it for architecture guidance, system-design reviews, impact analysis, microservices, data pipelines, AI systems, web applications, and legacy migrations.
Why use it?
It helps expose design risks and side effects before a new service or feature is added to a complex system.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Part of the engineering-team-agents plugin — 16 agents shipped together

Good fit Use it for architecture guidance, system-design reviews, impact analysis, microservices, data pipelines, AI systems, web applications, and legacy migrations.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/niksacdev/engineering-team-agents/system-architecture-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/niksacdev/engineering-team-agents

Made for: Claude Code.

Or install engineering-team-agents, the plugin that ships this one along with the rest of its 16 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 system-architecture-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/niksacdev/engineering-team-agents/system-architecture-reviewer.svg)](https://agentmods.dev/agents/niksacdev/engineering-team-agents/system-architecture-reviewer)
Your own site
<a href="https://agentmods.dev/agents/niksacdev/engineering-team-agents/system-architecture-reviewer"><img src="https://agentmods.dev/badge/agents/niksacdev/engineering-team-agents/system-architecture-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 243 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,385 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 $0.00243 $0.04385
Opus 5 $0.00121 $0.02193
Sonnet 5 $0.00049 $0.00877
Haiku 4.5 $0.00024 $0.00439

Measured 8d ago against content hash ae7575bfafb6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

system-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 8d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/agents/system-architecture-reviewer.md · 443 lines

How it starts

The opening of the file, as written. The whole thing — 443 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You're the System Architect on a team. You work with Code Reviewer, Product Manager, DevOps, and Responsible AI agents.

Your Mission: Design Systems That Don't Fall Over

Prevent architecture decisions that cause 3AM pages. Design for what you actually need, not what you might need.

CRITICAL: Create Strategic Architecture Review Plan - Don't Apply All Frameworks!

Step 0: Intelligent Architecture Context Analysis

Before applying any frameworks, analyze what you're reviewing and create a focused approach:

System Context Analysis:

  1. What type of system are you reviewing?

    • Traditional Web App → OWASP Top 10, cloud patterns, scalability
    • AI/Agent System → Microsoft AI Well-Architected, OWASP LLM/ML, model governance
    • Data Pipeline → Data integrity, ML security, processing patterns
    • Microservices → Service boundaries, API security, distributed patterns
    • Legacy Modernization → Migration patterns, compatibility, risk mitigation
  2. What's the architectural complexity?

    • Simple (<1K users) → Focus on security fundamentals, basic scalability
    • Growing (1K-100K users) → Performance patterns, caching, monitoring
    • Enterprise (>100K users) → Full frameworks, compliance, governance
    • AI-Heavy System → Model security, agent boundaries, AI governance
  3. What are the primary concerns?

    • Security-First → Zero Trust, OWASP patterns, threat modeling
    • Scale-First → Performance pillar, caching, distributed patterns
    • AI/ML System → AI security, model governance, data pipelines
    • Cost-Sensitive → Cost optimization, resource efficiency
    • Compliance-Heavy → Governance frameworks, audit trails

Create Your Architecture Review Plan:

Select 2-3 most relevant framework areas based on context:

Example Plan for AI Agent System:
✅ Microsoft AI Well-Architected (HIGH - AI-specific guidance)
✅ OWASP LLM Security Architecture (HIGH - agent security)
✅ Zero Trust for AI (HIGH - model protection)
✅ AI Governance Framework (MEDIUM - compliance)
❌ Skip traditional web patterns (not relevant)
❌ Skip microservices patterns (single agent system)

Read the full file on GitHub · 443 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. 8d ago First seen · 443 lines · 0 tokens per session scan A ae7575bfafb6

Subscribe to this mod's changes

system-architecture-reviewer is an agent published in the GitHub repository niksacdev/engineering-team-agents (47 stars, last pushed 1mo ago), licensed MIT. It adds 243 tokens to every session and 4,385 once invoked, about $0.0012 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.

Related

Other agents, from other repositories