Skip to main content
subagent CX Codex

architecture · ruvnet, agentic-flow — Claude Code subagent: SPARC system design with memory

A subagent for the Architecture stage of SPARC. It turns pseudocode into a component design, pulls similar patterns from claude-flow memory, and stores what worked.

no license ★ 850 updated 2026-10-26

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/agents/architecture.md
Open on GitHub

What architecture does

This agent covers the Architecture stage of SPARC. It picks up the pseudocode and requirements left by the previous stage and returns a system layout: components, the interfaces between them, a scaling plan, a technology choice. Its priority is high, so SPARC calls it before the implementers.

Two hooks handle the memory side. Before design, the pre hook opens a session and runs npx claude-flow@alpha memory search-patterns "architecture: $TASK" --k=5 --min-reward=0.85. After design, the post hook stores the outcome with a 0.90 reward and, on success, trains a pattern via npx claude-flow@alpha neural train for 50 epochs. The prompt also points at Flash Attention and a GNN search over a component graph for large documents.

Both hooks call the package through npx and swallow failures with 2>/dev/null || true. No network or no package means the memory steps pass silently, with nothing written and no warning in the log. Check the first run yourself to confirm the pattern landed.

What it helps with

  • split a monolith into services with clear interfaces
  • pick a stack before any code exists
  • reuse an architecture that scored well on an earlier task
  • spot coupling problems before implementation starts
  • record scaling decisions next to the pseudocode

Example prompts for the agent

  • Use the architecture subagent to break the pseudocode in pseudo_complete into components and define their interfaces
  • Have architecture pick a pattern for growing load, after searching claude-flow memory for similar designs
  • Review the component diagram for tight coupling and save the result to memory as a pattern

How to install architecture

Manually: put the files in place

.claude/agents/architecture.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about architecture

How do I install architecture in Claude Code?

Put the agent file at .claude/agents/architecture.md inside your project. Claude then loads it as the architecture subagent.

What does the architecture subagent do?

It designs the system during the Architecture stage: splits the task into components, defines interfaces, plans scaling and picks technologies. It also searches and stores architecture patterns in claude-flow memory.

Does it work without claude-flow?

The hooks pull claude-flow@alpha through npx. Without that package the pattern search, the storage and neural train do not run, and the errors are suppressed so the log stays quiet.

Similar subagents

All subagents for Agent setup: memory, context, orchestration →

architecture by other authors comes first.

architecture ruvnet architecture designs system structure from specifications and pseudocode, covering components, interfaces, technology choices, and deployment. CX Codex ★ 850repo stars V3 DDD Architecture ruvnet V3 DDD Architecture splits the claude-flow v3 orchestrator into five bounded contexts and wires them back together through a microkernel and a domain event bus. CX Codex +1 1,100installs design-code-architecture wondelai design-code-architecture — a skill for Claude Code, Cursor, and other platforms that walks you through eight architecture phases — from boundaries and domain model through data choices to resilience. CX Codex +1 2,700installs architecture-optimization wondelai The architecture-optimization Claude Code skill guides architecture, code-quality, and performance work on a live codebase. It records decisions and measurements across eight phases. CX Codex +1 1,700installs architecture-designer https://github.com/Jeffallan architecture-designer designs distributed system architectures, creates Mermaid diagrams, and writes Architecture Decision Records. It helps balance trade-offs before writing service code. CX Codex +1 8,500installs sparc-methodology ruvnet sparc-methodology — a skill for Claude Code, Codex, Cursor, Copilot, Gemini CLI and OpenCode: SPARC development methodology with 17 modes — from specification and architecture to TDD, code review and deployment. CX Codex +1 1,200installs agent-architecture official github Designs AI agent architectures from requirements or audits existing agents for flaws. Focuses purely on architectural decisions and verification without implementing code. CX Codex +1 42installs

From the same set76

The whole set →
reasoning-optimized The reasoning-optimized subagent selects a reasoning strategy based on the task and coordinates five specialist agents. Use it when a task calls for context synthesis, pattern reuse, or curation of results. CX Codex ★ 850repo stars experience-curator experience-curator — a Claude subagent that screens finished task runs and keeps only verified lessons in ReasoningBank memory. CX Codex ★ 850repo stars issue-tracker issue-tracker coordinates GitHub issues and task progress using ReasoningBank pattern storage. Fits projects needing structured triage. CX Codex ★ 850repo stars parallel-execution-guide The parallel-execution-guide prompt guides Claude Code through splitting work into independent tasks, spawning CLI subagents, and combining their results. Use it for parallel research or code review. GP ChatGPT ★ 850repo stars Resource Allocator Resource Allocator manages agent swarm capacity through adaptive resource distribution and predictive scaling across CPU, memory, storage, and network channels. CX Codex ★ 850repo stars release-manager release-manager runs a multi-package release: version bumps, tests, deploy and rollback, then keeps what worked in memory for the next one. CX Codex ★ 850repo stars Performance Monitor Performance Monitor collects system and agent metrics, hunts bottlenecks and watches SLA thresholds. Useful when several agents run at once and it is unclear which one is slow. CX Codex ★ 850repo stars Benchmark Suite Benchmark Suite runs throughput and latency benchmarks, measures resource consumption, and detects performance regressions in agent clusters. CX Codex ★ 850repo stars

Project sponsors

Companies that keep this analytics open