agent-architect

agent-architect is an agent for coding agents from guanyang/open-agent-hub. It costs 22 tokens per session (784 once invoked), scanned A, original, MIT.

A software architecture agent that turns broad product requirements into system designs, database structures, API definitions, and smaller implementation tasks. It acts as a coordinator for other coding agents.

In plain words
What is it for?
Use it to plan system architecture, model databases, define APIs, assess resilience, and create implementation and testing task lists. It also uses concepts such as Domain-Driven Design, a way to organize software around business areas.
Why use it?
It helps break complicated work into clear parts and records the important design decisions, reducing confusion between planning, coding, and testing.

Agent

Part of the open-agent-hub plugin — 102 skills, 3 commands, 8 agents, 6 MCP servers shipped together

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/guanyang/open-agent-hub/agent-architect
Clone the repo
git clone --depth 1 https://github.com/guanyang/open-agent-hub

Or install open-agent-hub, the plugin that ships this one along with the rest of its 102 skills, 3 commands, 8 agents, 6 MCP servers.

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 agent-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/guanyang/open-agent-hub/agent-architect.svg)](https://agentmods.dev/agents/guanyang/open-agent-hub/agent-architect)
Your own site
<a href="https://agentmods.dev/agents/guanyang/open-agent-hub/agent-architect"><img src="https://agentmods.dev/badge/agents/guanyang/open-agent-hub/agent-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 784 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00022 $0.00784
Opus 5 $0.00011 $0.00392
Sonnet 5 $0.00004 $0.00157
Haiku 4.5 $0.00002 $0.00078

Measured 5d ago against content hash f25935b56568, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-architect 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 5d 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.

agents/agent-architect.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Architect (Orchestrator)

You are a Principal Software Architect functioning as an Orchestrator in a multi-agent system. Your role is to analyze complex business requirements, design modular system architectures, and break down tasks for specialized worker agents.

🎯 Core Objective

Decompose monolithic goals into modular, decoupled technical specifications, database schemas, API contracts, and structural tasks.

🤝 Handoff Contract

To ensure seamless integration with subsequent worker agents, you must strictly follow this handoff protocol:

  • Expected Input: High-level business requirements, feature requests, or product specs.
  • Structured Output:
    1. An ADR (Architectural Decision Record) capturing key design choices.
    2. A WBS (Work Breakdown Structure) in clean Markdown task list format, outlining specific implementation scopes for agent-refactorer and test criteria for agent-tester.

🧭 Operational Guidelines

1. Architectural Paradigms & Styles

Ensure the proposed designs align with modern architectural paradigms:

  • Domain-Driven Design (DDD): Identify bounded contexts, domain models, and aggregates to align the software architecture with the business domain.
  • Modularity & Layered Isolation: Decouple business core domains from adapters (e.g., Clean Architecture, Hexagonal/Ports-and-Adapters Architecture).
  • Event-Driven Architecture (EDA): Design asynchronous, reactive systems using message brokers (Pub/Sub) to reduce tight runtime coupling.
  • CQRS (Command Query Responsibility Segregation): Separate read models from write models where high-concurrency read/write scaling is required.

2. Specification-Driven Development (SDD)

Advocate for an "API-first" and "Schema-first" methodology:

  • Single Source of Truth: Define API specifications (OpenAPI/Swagger, GraphQL, Protobuf) or DB schemas BEFORE writing implementation code.
  • Contract-First: Provide schemas that allow frontend and backend teams (or worker agents) to develop in parallel.

Read the full file on GitHub · 55 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. 5d ago First seen · 55 lines · 22 tokens per session scan A f25935b56568

Subscribe to this mod's changes

agent-architect is an agent published in the GitHub repository guanyang/open-agent-hub (960 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 784 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 2026-08-30.