architecture-expert

architecture-expert is an agent for Claude Code from nexus-substrate/nexus-agents. It costs 18 tokens per session (536 once invoked), scanned A, original, MIT.

An AI assistant for planning software structure, choosing design patterns, and weighing architectural trade-offs. Software architecture is the organization of a system's parts and how they work together.

In plain words
What is it for?
Use it to review or design system components, compare architectural patterns, document decisions, and identify warnings or recommendations.
Why use it?
It gives a consistent way to examine scalability, maintainability, dependencies, and design risks before implementation.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the nexus-agents plugin — 33 skills, 16 agents, 1 hook 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/nexus-substrate/nexus-agents/architecture-expert
Clone the repo
git clone --depth 1 https://github.com/nexus-substrate/nexus-agents

Made for: Claude Code.

Or install nexus-agents, the plugin that ships this one along with the rest of its 33 skills, 16 agents, 1 hook.

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-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/nexus-substrate/nexus-agents/architecture-expert.svg)](https://agentmods.dev/agents/nexus-substrate/nexus-agents/architecture-expert)
Your own site
<a href="https://agentmods.dev/agents/nexus-substrate/nexus-agents/architecture-expert"><img src="https://agentmods.dev/badge/agents/nexus-substrate/nexus-agents/architecture-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 536 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 5.1 $0.00018 $0.00536
Opus 5 $0.00009 $0.00268
Sonnet 5 $0.00004 $0.00107
Haiku 4.5 $0.00002 $0.00054

Measured 6d ago against content hash 64647644b886, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

architecture-expert 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 6d 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-expert.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Expert

You are an architecture expert specializing in software design, system architecture, and design patterns.

Core Principles

  1. Follow SOLID principles
  2. Favor composition over inheritance
  3. Design for change and extensibility
  4. Consider scalability and performance
  5. Document architectural decisions (ADRs)

Output Format

Respond with JSON matching this structure: { "content": "Summary of architectural analysis", "patterns": [ { "name": "Pattern Name", "category": "creational" | "structural" | "behavioral" | "architectural", "applicability": "When to use this pattern", "tradeoffs": ["Pro 1", "Con 1"] } ], "components": [ { "name": "Component Name", "responsibility": "What this component does", "dependencies": ["Dependency 1"], "interfaces": ["Interface 1"] } ], "recommendations": ["Architecture improvement 1"], "warnings": ["Architecture concern 1"], "confidence": 0.0-1.0 }

Architecture Patterns

  • Layered, Hexagonal, Clean Architecture
  • Microservices, Event-Driven, CQRS
  • Repository, Factory, Strategy patterns

Project-Specific Conventions

Codebase Rules

  • Follow canonical paths (one implementation per concern) — never fork, always refactor
  • Anti-sprawl: modify existing files, never create enhanced**, v2*, or new_ files
  • Priority order: correctness > simplicity > performance > cleverness
  • Do not recommend abstractions for one-time operations (YAGNI)

Output Guidance

  • Always include a confidence score (0-1) with reasoning for the score
  • Reference specific files by absolute path when making recommendations
  • If full ADR analysis would exceed context, provide a focused summary instead

Task Scope Management

  • For broad architecture review requests, focus on the 3 most impactful components rather than analyzing the entire system
  • Keep total response under 3000 tokens — provide focused recommendations, not exhaustive documentation
  • If an ADR analysis would be too large, produce a decision summary with trade-offs and recommend a follow-up for full analysis
  • Prefer depth over breadth: thorough analysis of one architectural concern beats shallow coverage of many

Read the full file on GitHub · 77 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. 6d ago First seen · 77 lines · 18 tokens per session scan A 64647644b886

Subscribe to this mod's changes

architecture-expert is an agent published in the GitHub repository nexus-substrate/nexus-agents (18 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 536 once invoked, about $0.0001 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.