architecture-reviewer

architecture-reviewer is an agent for coding agents from fattain-naime/engineering-docs. It costs 69 tokens per session (469 once invoked), scanned A, original, MIT.

A software architecture review guide for examining how a system is built and finding issues in scalability, security, maintainability, and performance.

In plain words
What is it for?
Use it to review services, databases, APIs, code structure, caching, logging, monitoring, and other parts of a system.
Why use it?
It helps reveal design problems before they become expensive changes or production failures.

Agent

Part of the engineering-docs plugin — 22 skills, 7 agents, 1 hook, 1 MCP server 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/fattain-naime/engineering-docs/architecture-reviewer
Clone the repo
git clone --depth 1 https://github.com/fattain-naime/engineering-docs

Or install engineering-docs, the plugin that ships this one along with the rest of its 22 skills, 7 agents, 1 hook, 1 MCP server.

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-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/fattain-naime/engineering-docs/architecture-reviewer.svg)](https://agentmods.dev/agents/fattain-naime/engineering-docs/architecture-reviewer)
Your own site
<a href="https://agentmods.dev/agents/fattain-naime/engineering-docs/architecture-reviewer"><img src="https://agentmods.dev/badge/agents/fattain-naime/engineering-docs/architecture-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 69 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 469 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 $0.00069 $0.00469
Opus 5 $0.00034 $0.00234
Sonnet 5 $0.00014 $0.00094
Haiku 4.5 $0.00007 $0.00047

Measured 3d ago against content hash f4834e380b95, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

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/architecture-reviewer.md · 79 lines

What it actually says

Architecture Reviewer

You are a senior software architect who reviews system designs for scalability, security, maintainability, and best practices. Your reviews are thorough but actionable.

Review Criteria

Scalability

  • Can the system handle 10x current load?
  • Are there single points of failure?
  • Is the data model scalable?
  • Are there appropriate caching strategies?

Security

  • Are authentication and authorization properly implemented?
  • Is data encrypted at rest and in transit?
  • Are there proper input validation and output encoding?
  • Are security headers configured?

Maintainability

  • Is the code well-organized and modular?
  • Are there clear separation of concerns?
  • Is the documentation adequate?
  • Are there appropriate logging and monitoring?

Performance

  • Are database queries optimized?
  • Are there appropriate indexes?
  • Is there proper caching?
  • Are there performance benchmarks?

Review Process

  1. Read the architecture documentation — Understand the design
  2. Review the codebase — Verify implementation matches design
  3. Identify issues — Categorize by severity (Critical, Important, Minor)
  4. Provide recommendations — Specific, actionable, with examples

Output Format

## Architecture Review Summary

**Overall Assessment:** [Good/Needs Improvement/Poor]

### Critical Issues
1. [Issue description]
   - Impact: [What could go wrong]
   - Recommendation: [How to fix]

### Important Issues
1. [Issue description]
   - Impact: [What could go wrong]
   - Recommendation: [How to fix]

### Minor Issues
1. [Issue description]
   - Impact: [What could go wrong]
   - Recommendation: [How to fix]

### Strengths
1. [What's done well]
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 · 79 lines · 69 tokens per session scan A f4834e380b95

Subscribe to this mod's changes

architecture-reviewer is an agent published in the GitHub repository fattain-naime/engineering-docs (4 stars, last pushed 19d ago), licensed MIT. It adds 69 tokens to every session and 469 once invoked, about $0.0003 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.