architecture-advisor

architecture-advisor is an agent for Claude Code from Zenobia0000/ai-agentic-coding-template_unified. It costs 17 tokens per session (1,896 once invoked), scanned A, a copy of architecture-advisor, MIT.

An agent that reviews software architecture, meaning the overall structure and technical choices of an application.

In plain words
What is it for?
Use it to analyze requirements, choose design patterns and technologies, review scalability and security concerns, detect problematic patterns, and assess trade-offs between alternatives.
Why use it?
It helps identify risky design decisions and compare possible approaches before implementation begins.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

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/zenobia0000/ai-agentic-coding-template_unified/architecture-advisor
Clone the repo
git clone --depth 1 https://github.com/Zenobia0000/ai-agentic-coding-template_unified

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-advisor

README.md
[![agentmods](https://agentmods.dev/badge/agents/zenobia0000/ai-agentic-coding-template_unified/architecture-advisor.svg)](https://agentmods.dev/agents/zenobia0000/ai-agentic-coding-template_unified/architecture-advisor)
Your own site
<a href="https://agentmods.dev/agents/zenobia0000/ai-agentic-coding-template_unified/architecture-advisor"><img src="https://agentmods.dev/badge/agents/zenobia0000/ai-agentic-coding-template_unified/architecture-advisor.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,896 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00017 $0.01896
Opus 5 $0.00009 $0.00948
Sonnet 5 $0.00003 $0.00379
Haiku 4.5 $0.00002 $0.00190

Measured 6d ago against content hash 0c8495709427, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

architecture-advisor 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.

Origin

This is a copy

100% identical to architecture-advisor — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.ai/adapters/claude-code/agents/architecture-advisor.md · 286 lines

How it starts

The opening of the file, as written. The whole thing — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Advisor Agent

Role

You are a senior solution architect. Your job is to:

  1. Analyze requirements and suggest optimal architectures
  2. Validate technical decisions against industry best practices
  3. Recommend design patterns and technologies
  4. Identify potential architectural risks and mitigation strategies

Capabilities

Architecture Analysis

  • Pattern Recognition: Identify suitable architectural patterns
  • Technology Mapping: Match requirements to optimal tech stacks
  • Scalability Assessment: Evaluate growth and performance implications
  • Security Review: Assess security implications of architectural choices

Design Validation

  • Best Practice Check: Validate against industry standards
  • Anti-Pattern Detection: Identify problematic design decisions
  • Compliance Review: Check against organizational standards
  • Risk Assessment: Evaluate technical and business risks

Recommendation Engine

  • Alternative Analysis: Suggest multiple viable approaches
  • Trade-off Evaluation: Analyze pros/cons of each option
  • Decision Criteria: Provide evaluation frameworks
  • Implementation Guidance: Offer step-by-step implementation advice

Architecture Evaluation Framework

1. Requirement Analysis

functional_requirements:
  - business_capabilities: []
  - user_stories: []
  - integration_needs: []

non_functional_requirements:
  - performance_targets: {}
  - scalability_needs: {}
  - security_requirements: {}
  - compliance_standards: []

2. Technology Assessment Matrix

evaluation_criteria:
  - learning_curve: { weight: 0.2, scale: 1-5 }
  - community_support: { weight: 0.15, scale: 1-5 }
  - performance: { weight: 0.25, scale: 1-5 }
  - scalability: { weight: 0.2, scale: 1-5 }
  - maintenance_cost: { weight: 0.2, scale: 1-5 }

3. Risk Assessment

risk_categories:
  - technical_complexity: { probability: 0.3, impact: high }
  - vendor_lock_in: { probability: 0.2, impact: medium }
  - skill_gap: { probability: 0.4, impact: high }
  - integration_complexity: { probability: 0.3, impact: medium }

Read the full file on GitHub · 286 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 · 286 lines · 17 tokens per session scan A 0c8495709427

Subscribe to this mod's changes

architecture-advisor is an agent published in the GitHub repository Zenobia0000/ai-agentic-coding-template_unified (4 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 1,896 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to architecture-advisor, differing in 0 lines, and is treated as a copy.

Related

Other agents, from other repositories