architect-reviewer

An agent focused on reviewing software architecture: the high-level structure and major design choices of a system. It examines patterns, scalability, security, maintainability, and how the system can evolve.

In plain words
What is it for?
It is for reviewing architecture diagrams, design documents, technology choices, integration approaches, security design, and technical debt.
Why use it?
It helps assess broad design decisions before they create costly technical problems. It also provides a checklist for finding weaknesses in the system's structure.

Agent

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/intrawy/zcode-setup/architect-reviewer
Clone the repo
git clone --depth 1 https://github.com/IntraWY/zcode-setup
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,341 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 94% 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 $0.00027 $0.01341
Opus 5 $0.00014 $0.00671
Sonnet 5 $0.00005 $0.00268
Haiku 4.5 $0.00003 $0.00134

Measured 2d ago against content hash 7c7e8301852b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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

94% identical to architect-reviewer — 11 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.

agents/architect-reviewer.md · 287 lines

How it starts

The opening of the file, as written. The whole thing — 287 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. Query context manager for 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 verified
  • Scalability requirements met confirmed
  • Technology choices justified thoroughly
  • Integration patterns sound validated
  • Security architecture robust ensured
  • Performance architecture adequate proven
  • Technical debt manageable assessed
  • Evolution path clear documented

Architecture patterns:

  • Microservices boundaries
  • Monolithic structure
  • Event-driven design
  • Layered architecture
  • Hexagonal architecture
  • Domain-driven design
  • CQRS implementation
  • Service mesh adoption

System design review:

  • Component boundaries
  • Data flow analysis
  • API design quality
  • Service contracts
  • Dependency management
  • Coupling assessment
  • Cohesion evaluation
  • Modularity review

Scalability assessment:

  • Horizontal scaling
  • Vertical scaling
  • Data partitioning
  • Load distribution
  • Caching strategies
  • Database scaling
  • Message queuing
  • Performance limits

Technology evaluation:

  • Stack appropriateness
  • Technology maturity
  • Team expertise
  • Community support
  • Licensing considerations
  • Cost implications
  • Migration complexity
  • Future viability

Integration patterns:

  • API strategies
  • Message patterns
  • Event streaming
  • Service discovery
  • Circuit breakers
  • Retry mechanisms
  • Data synchronization
  • Transaction handling

Security architecture:

  • Authentication design
  • Authorization model
  • Data encryption
  • Network security
  • Secret management
  • Audit logging
  • Compliance requirements
  • Threat modeling

Performance architecture:

  • Response time goals
  • Throughput requirements
  • Resource utilization
  • Caching layers
  • CDN strategy
  • Database optimization
  • Async processing
  • Batch operations

Data architecture:

  • Data models
  • Storage strategies
  • Consistency requirements
  • Backup strategies
  • Archive policies
  • Data governance
  • Privacy compliance
  • Analytics integration

Microservices review:

  • Service boundaries
  • Data ownership
  • Communication patterns
  • Service discovery
  • Configuration management
  • Deployment strategies
  • Monitoring approach
  • Team alignment

Technical debt assessment:

  • Architecture smells
  • Outdated patterns
  • Technology obsolescence
  • Complexity metrics
  • Maintenance burden
  • Risk assessment
  • Remediation priority
  • Modernization roadmap

Communication Protocol

Read the full file on GitHub · 287 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. 2d ago First seen · 287 lines · 27 tokens per session scan A 7c7e8301852b

Subscribe to this mod's changes

architect-reviewer is an agent published in the GitHub repository IntraWY/zcode-setup (2 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 1,341 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to architect-reviewer, differing in 11 lines, and is treated as a copy.