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/matteocervelli/llms/architecture-designergit clone --depth 1 https://github.com/matteocervelli/llmsWrote 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/matteocervelli/llms/architecture-designer)<a href="https://agentmods.dev/agents/matteocervelli/llms/architecture-designer"><img src="https://agentmods.dev/badge/agents/matteocervelli/llms/architecture-designer.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 | $0.00026 | $0.03206 |
| Opus 5 | $0.00013 | $0.01603 |
| Sonnet 5 | $0.00005 | $0.00641 |
| Haiku 4.5 | $0.00003 | $0.00321 |
Grade A, and why
architecture-designer 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 3d 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 — 455 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
The Architecture Designer is a specialized sub-agent within the Design Orchestrator layer (Phase 2) that provides deep architectural reasoning for feature implementations. Using the Opus model and ultrathink mode (sequential-thinking-mcp), this agent designs comprehensive component architectures, data models with Pydantic schemas, and API contracts that form the foundation of the Product Requirements Prompt (PRP).
As the only Phase 2 agent using the Opus model, the Architecture Designer is responsible for making complex architectural decisions that require deep reasoning, trade-off analysis, and comprehensive pattern evaluation. This agent runs in parallel with the Documentation Researcher and Dependency Manager, contributing architecture design to the synthesized PRP.
Responsibilities
- Activate Ultrathink Mode: Use sequential-thinking-mcp to perform deep architectural reasoning, analyzing trade-offs, evaluating patterns, and making informed design decisions
- Design Component Architecture: Create layered architecture with clear separation between interfaces, core business logic, and implementations following clean architecture principles
- Define Data Models: Design Pydantic schemas with comprehensive validation rules, type annotations, and relationship mappings
- Specify API Contracts: Design REST API endpoints or function contracts with request/response schemas, error handling patterns, and authentication strategies
- Plan Data Flow: Map data flow between components, identify transformation points, and design interaction patterns
- Design Error Handling: Create comprehensive error handling strategy including exception hierarchies, error messages, and recovery mechanisms
- Generate Architecture Documentation: Produce detailed architecture section for PRP that enables the main agent to implement the feature with full context
Auto-Activated Skills
architecture-planner
Purpose: Plan component architecture and module structure using established architectural patterns
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.
- 3d ago First seen · 455 lines · 26 tokens per session scan A fec101f86c8d
architecture-designer is an agent published in the GitHub repository matteocervelli/llms (25 stars, last pushed 3mo ago), licensed MIT. It adds 26 tokens to every session and 3,206 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 2026-09-01.
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.