
Agent Repo Architect
Optimize monorepo or multi-repo layout and agent coordination using ruv-swarm hooks with GitHub and claude-flow MCP tools.
Overview
agent-repo-architect is an agent skill most often used in Build (agent-tooling, also Operate infra and Ship launch prep) that optimizes repository structure and multi-repo workflows with ruv-swarm and GitHub MCP coordina
Install
npx skills add https://github.com/ruvnet/ruflo --skill agent-repo-architectWhat is this skill?
- Repository structure optimization and multi-repo management with ruv-swarm pre-task, post-edit, and post-task hooks
- GitHub MCP operations: create/fork repos, search, push files, create_or_update_file
- claude-flow integration: swarm_init, agent_spawn, task_orchestrate, memory_usage
- Pre-task hook analyzes structure; post-edit validates architecture and updates structure documentation
- Post-task generates structure recommendations and stakeholder notification hook
Adoption & trust: 662 installs on skills.sh; 58.5k GitHub stars; 1/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your agent swarm and microservices are stepping on each other because repo boundaries, hooks, and GitHub layout were never designed for orchestrated multi-agent development.
Who is it for?
Advanced solo builders running ruv-swarm / Claude-Flow with GitHub MCP who need deliberate monorepo or multi-repo architecture before scaling agent count.
Skip if: Beginners with a single small app and no MCP stack, or teams that only need a conventional CODEOWNERS tweak without swarm hooks.
When should I use this skill?
User invokes $agent-repo-architect or needs repository structure optimization, multi-repo management, ruv-swarm repo-architect hooks, or GitHub plus claude-flow coordinated architecture work.
What do I get? / Deliverables
You get analyzed, validated repository structure with hook-driven documentation updates and post-task recommendations aligned to ruv-swarm and claude-flow orchestration.
- Validated repository structure with updated architecture documentation after edits
- Post-task structure recommendations and stakeholder notification via hooks
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Repository architecture is decided while you are actively building agent systems and scalable codebases—the canonical shelf is Build agent-tooling. The skill spawns tasks, memory, and swarm orchestration alongside GitHub structure changes, which is core agent-tooling rather than generic PM docs.
Where it fits
Initialize swarm_init and folder conventions before spawning feature agents into separate packages.
Create or fork GitHub repositories and push scaffold files via MCP while keeping service boundaries explicit.
Re-run post-edit structure validation after production hotfixes introduced cross-repo coupling.
Confirm release repos and hook-generated structure docs before tagging a multi-package ship.
How it compares
Use this orchestrated repo-architect skill instead of ad-hoc folder renames in chat when GitHub creation, pushes, and swarm task hooks must stay in sync.
Common Questions / FAQ
Who is agent-repo-architect for?
Indie builders and small teams building agent-native products who use ruv-swarm hooks, GitHub MCP, and claude-flow to manage repositories at scale.
When should I use agent-repo-architect?
During Build when structuring repos for agent workflows; during Operate when architecture drift needs re-analysis; and before Ship when multi-repo boundaries affect release safety—any time you need swarm_init-aligned layout with validated post-edit structure docs.
Is agent-repo-architect safe to install?
It can create repos, push files, and run shell hooks; review the Security Audits panel on this Prism page, scope GitHub tokens minimally, and audit npx ruv-swarm hook commands before autonomous runs.
SKILL.md
READMESKILL.md - Agent Repo Architect
--- name: repo-architect description: Repository structure optimization and multi-repo management with ruv-swarm coordination for scalable project architecture and development workflows type: architecture color: "#9B59B6" tools: - Bash - Read - Write - Edit - LS - Glob - TodoWrite - TodoRead - Task - WebFetch - mcp__github__create_repository - mcp__github__fork_repository - mcp__github__search_repositories - mcp__github__push_files - mcp__github__create_or_update_file - mcp__claude-flow__swarm_init - mcp__claude-flow__agent_spawn - mcp__claude-flow__task_orchestrate - mcp__claude-flow__memory_usage hooks: pre_task: | echo "🏗️ Initializing repository architecture analysis..." npx ruv-swarm hook pre-task --mode repo-architect --analyze-structure post_edit: | echo "📐 Validating architecture changes and updating structure documentation..." npx ruv-swarm hook post-edit --mode repo-architect --validate-structure post_task: | echo "🏛️ Architecture task completed. Generating structure recommendations..." npx ruv-swarm hook post-task --mode repo-architect --generate-recommendations notification: | echo "📋 Notifying stakeholders of architecture improvements..." npx ruv-swarm hook notification --mode repo-architect --- # GitHub Repository Architect ## Purpose Repository structure optimization and multi-repo management with ruv-swarm coordination for scalable project architecture and development workflows. ## Capabilities - **Repository structure optimization** with best practices - **Multi-repository coordination** and synchronization - **Template management** for consistent project setup - **Architecture analysis** and improvement recommendations - **Cross-repo workflow** coordination and management ## Usage Patterns ### 1. Repository Structure Analysis and Optimization ```javascript // Initialize architecture analysis swarm mcp__claude-flow__swarm_init { topology: "mesh", maxAgents: 4 } mcp__claude-flow__agent_spawn { type: "analyst", name: "Structure Analyzer" } mcp__claude-flow__agent_spawn { type: "architect", name: "Repository Architect" } mcp__claude-flow__agent_spawn { type: "optimizer", name: "Structure Optimizer" } mcp__claude-flow__agent_spawn { type: "coordinator", name: "Multi-Repo Coordinator" } // Analyze current repository structure LS("$workspaces$ruv-FANN$claude-code-flow$claude-code-flow") LS("$workspaces$ruv-FANN$ruv-swarm$npm") // Search for related repositories mcp__github__search_repositories { query: "user:ruvnet claude", sort: "updated", order: "desc" } // Orchestrate structure optimization mcp__claude-flow__task_orchestrate { task: "Analyze and optimize repository structure for scalability and maintainability", strategy: "adaptive", priority: "medium" } ``` ### 2. Multi-Repository Template Creation ```javascript // Create standardized repository template mcp__github__create_repository { name: "claude-project-template", description: "Standardized template for Claude Code projects with ruv-swarm integration", private: false, autoInit: true } // Push template structure mcp__github__push_files { owner: "ruvnet", repo: "claude-project-template", branch: "main", files: [ { path: ".claude$commands$github$github-modes.md", content: "[GitHub modes template]" }, { path: ".claude$commands$sparc$sparc-modes.md", content: "[SPARC modes template]" }, { path: ".claude$config.json", content: JSON.stringify({ version: "1.0", mcp_servers: { "ruv-swarm": { command: "npx", args: ["ruv-swarm", "mcp", "start"], stdio: true } }, hooks: { pre_task: "npx ruv-swarm hook pre-task", post_edit: "npx ruv-swarm hook post-edit", notificati