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.
npx agentmods add agents/rcdelacruz/claude-code-agents/architecture-agentsgit clone --depth 1 https://github.com/rcdelacruz/claude-code-agentsWrote 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.
[](https://agentmods.dev/agents/rcdelacruz/claude-code-agents/architecture-agents)<a href="https://agentmods.dev/agents/rcdelacruz/claude-code-agents/architecture-agents"><img src="https://agentmods.dev/badge/agents/rcdelacruz/claude-code-agents/architecture-agents.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.04280 |
| Opus 5 | $0.00000 | $0.02140 |
| Sonnet 5 | $0.00000 | $0.00856 |
| Haiku 4.5 | $0.00000 | $0.00428 |
Grade A, and why
architecture-agents 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 584 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Agents
Architecture agents are specialized experts that handle design decisions at different levels of abstraction. The three-tier system separates enterprise-level, detailed design, and application-level concerns to provide focused, expert guidance at each layer.
Overview
The architecture agent system consists of three specialized agents:
- solution-architect - Enterprise-level, multi-system architecture and cloud platform selection
- solution-designer - Detailed technical design, API specifications, and database schemas
- software-architect - Application-level architecture, design patterns, and code structure
The Three-Tier Architecture Model
graph TD
SA[solution-architect<br/>30,000 ft view] --> SD[solution-designer<br/>10,000 ft view]
SD --> SWA[software-architect<br/>1,000 ft view]
SA --> |Enterprise Strategy| Decision1[Cloud Platform Selection<br/>Multi-System Integration<br/>Compliance & Security]
SD --> |Technical Design| Decision2[API Specifications<br/>Database Schemas<br/>Interface Contracts]
SWA --> |Implementation| Decision3[Code Structure<br/>Design Patterns<br/>Component Architecture]
style SA fill:#e3f2fd
style SD fill:#fff3e0
style SWA fill:#e8f5e9
When to Use Which Agent
flowchart TD
Start[Architecture Decision] --> Q1{Spans Multiple<br/>Systems?}
Q1 -->|Yes| SolutionArch[solution-architect]
Q1 -->|No| Q2{Need Detailed<br/>Specs?}
Q2 -->|Yes| Designer[solution-designer]
Q2 -->|No| Q3{Application-Level<br/>Design?}
Q3 -->|Yes| SoftwareArch[software-architect]
Q3 -->|No| Clarify[Clarify Requirement]
style SolutionArch fill:#a5d6a7
style Designer fill:#ffcc80
style SoftwareArch fill:#90caf9
solution-architect
Name: solution-architect
Description: Expert in enterprise-level architecture, multi-system integration, cloud platform selection, technology stack decisions, and cross-cutting concerns that span multiple applications or external systems.
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.
- 4d ago First seen · 584 lines · 0 tokens per session scan A 389533188ad0
architecture-agents is an agent published in the GitHub repository rcdelacruz/claude-code-agents (2 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,280 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.