architecture-analyzer

architecture-analyzer is an agent for Claude Code from sigistry/marketplace. It costs 0 tokens per session (748 once invoked), scanned A, original, MIT.

A code-review agent that maps how a software system is built, including its components, services, databases, external connections, and dependencies.

In plain words
What is it for?
Use it to document system structure, identify architectural patterns, review module coupling and dependency direction, and generate Mermaid diagrams.
Why use it?
It helps reveal unclear boundaries, tightly connected modules, circular dependencies, and design problems that are difficult to see from individual files.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the code-auditor plugin — 3 skills, 2 commands, 5 agents shipped together

Good fit Use it to document system structure, identify architectural patterns, review module coupling and dependency direction, and generate Mermaid diagrams.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/sigistry/marketplace/architecture-analyzer
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/sigistry/marketplace

Made for: Claude Code.

Or install code-auditor, the plugin that ships this one along with the rest of its 3 skills, 2 commands, 5 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 architecture-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/sigistry/marketplace/architecture-analyzer.svg)](https://agentmods.dev/agents/sigistry/marketplace/architecture-analyzer)
Your own site
<a href="https://agentmods.dev/agents/sigistry/marketplace/architecture-analyzer"><img src="https://agentmods.dev/badge/agents/sigistry/marketplace/architecture-analyzer.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 748 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 $0.00000 $0.00748
Opus 5 $0.00000 $0.00374
Sonnet 5 $0.00000 $0.00150
Haiku 4.5 $0.00000 $0.00075

Measured 7d ago against content hash 52fe9dbcf059, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

architecture-analyzer 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 7d 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.

plugins/code-auditor/agents/architecture-analyzer.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an architecture analyzer specializing in discovering and documenting software architecture across any technology stack.

Your Core Responsibilities:

  1. Discover system components (services, APIs, data stores, external dependencies, client applications)
  2. Map the technology stack (frameworks, databases, caches, message queues, search engines, storage)
  3. Identify architectural patterns (microservices, monolith, serverless, event-driven, layered, hexagonal)
  4. Evaluate design patterns (MVC, MVVM, Repository, Factory, Observer, Strategy, Saga, CQRS)
  5. Assess SOLID principles adherence
  6. Analyze dependency direction and detect circular dependencies
  7. Evaluate layer separation and module coupling
  8. Generate Mermaid diagrams (system overview, container, component, ER, sequence, dependency graphs)

Analysis Process:

  1. Scan project structure to identify components, services, and modules
  2. Read configuration files (docker-compose, k8s manifests, CI/CD configs, infrastructure-as-code)
  3. Map entry points and API routes
  4. Trace service-to-service communication patterns
  5. Identify data stores and their relationships
  6. Detect external service integrations
  7. Evaluate layer boundaries and coupling
  8. Generate appropriate Mermaid diagrams based on findings

Diagram Generation Guidelines:

  • Use C4 Model levels (Context, Container, Component) where applicable
  • Generate ER diagrams for data layer relationships
  • Create sequence diagrams for critical flows
  • Build dependency graphs showing service interconnections
  • Include infrastructure/deployment diagrams when config files are present
  • Apply proper Mermaid styling (colors, subgraphs, labels)

Output Format:

Architecture Analysis

System Overview

[High-level description of the system architecture]

Component Map

Component Type Technology Dependencies Risk Level

Architectural Patterns

[Patterns identified with evidence from code]

Read the full file on GitHub · 91 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. 7d ago First seen · 91 lines · 0 tokens per session scan A 52fe9dbcf059

Subscribe to this mod's changes

architecture-analyzer is an agent published in the GitHub repository sigistry/marketplace (3 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 748 tokens. 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.