# architecture

architecture designs system structure from specifications and pseudocode, covering components, interfaces, technology choices, and deployment.

- subagent · `type=agent` · Claude Code, Codex, Cursor · ★ 850 repo stars
- Author: ruvnet
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/ruvnet/agentic-flow/tree/HEAD/.claude/agents/sparc/architecture.md
- Updated: 2026-10-26
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/agents/ruvnet-architecture

## What it does

This subagent handles the Architecture phase of the SPARC methodology. It can break a system into components, define their boundaries and contracts, select a technology stack, and plan for scaling. Its examples cover an authentication service, REST and gRPC interfaces, event flows, data schemas, and a Kubernetes Deployment.

Pre- and post-hooks record the current phase in memory; the pre-hook also searches for completed pseudocode. The PostgreSQL, Redis, and RabbitMQ stack shown in the architecture is an example, not a project requirement. The hooks call `memory_store` and `memory_search`, so the workflow uses memory operations.

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/agents/architecture.md` — For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

### Codex

**Manually: put the files in place**
- File: `.codex/agents/architecture.toml` — Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

### Cursor

**Manually: put the files in place**
- File: `.cursor/agents/architecture.md` — Cursor also reads .claude/agents/

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/ruvnet/agentic-flow/tree/HEAD/.claude/agents/sparc/architecture.md

## When to use it
- split a system into components with clear boundaries
- define REST and gRPC contracts between services
- design data schemas and entity relationships
- outline a Kubernetes deployment

## Example prompts
- Design the system architecture from this specification and divide it into components.
- Define the service interfaces and the events they exchange.
- Plan the data schema and a Kubernetes deployment for this application.

## Similar
- [design-code-architecture](https://affpapa.org/en/nevibecode/skills/design-code-architecture.md) — skill · 2700 installs
- [architecture-designer](https://affpapa.org/en/nevibecode/skills/architecture-designer.md) — skill · 8500 installs
- [architecture-optimization](https://affpapa.org/en/nevibecode/skills/architecture-optimization.md) — skill · 1700 installs
- [designing-architecture](https://affpapa.org/en/nevibecode/skills/designing-architecture.md) — skill · ★ 1424 repo stars
- [oma-architecture](https://affpapa.org/en/nevibecode/skills/first-fluke-oma-architecture.md) — skill · ★ 1472 repo stars
- [agent-architecture](https://affpapa.org/en/nevibecode/skills/agent-architecture.md) — skill · 42 installs

## Other versions with the same name
- [architecture · ruvnet](https://affpapa.org/en/nevibecode/agents/architecture.md) — ★ 850 repo stars

From the same set: [ruvnet/agentic-flow](https://affpapa.org/en/nevibecode/by/ruvnet/agentic-flow.md) — 76 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
