NodeSpaceAI/nodespace-core
Local-first knowledge base with semantic search for AI coding assistants. Fewer tokens, faster context.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit NodeSpaceAI/nodespace-core/.claude ./rig-nodespace-core # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit NodeSpaceAI/nodespace-core/.claude/skills/github-issue-management .claude/skills/github-issue-management $ npx degit NodeSpaceAI/nodespace-core/.claude/skills/run-app .claude/skills/run-app
$ curl -fsSL --create-dirs -o .claude/agents/ai-ml-engineer.md https://raw.githubusercontent.com/NodeSpaceAI/nodespace-core/main/.claude/agents/ai-ml-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/frontend-architect.md https://raw.githubusercontent.com/NodeSpaceAI/nodespace-core/main/.claude/agents/frontend-architect.md $ curl -fsSL --create-dirs -o .claude/agents/frontend-expert.md https://raw.githubusercontent.com/NodeSpaceAI/nodespace-core/main/.claude/agents/frontend-expert.md $ curl -fsSL --create-dirs -o .claude/agents/performance-engineer.md https://raw.githubusercontent.com/NodeSpaceAI/nodespace-core/main/.claude/agents/performance-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/pragmatic-code-reviewer.md https://raw.githubusercontent.com/NodeSpaceAI/nodespace-core/main/.claude/agents/pragmatic-code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/senior-architect-reviewer.md https://raw.githubusercontent.com/NodeSpaceAI/nodespace-core/main/.claude/agents/senior-architect-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/ux-design-expert.md https://raw.githubusercontent.com/NodeSpaceAI/nodespace-core/main/.claude/agents/ux-design-expert.md
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"hooks": {
"PreToolUse": [
{
"matcher": "Edit|Write",
"hooks": [
{
"type": "command",
"command": "bun run .claude/hooks/check-feature-branch.ts"
}
]
},
{
"matcher": "EnterPlanMode",
"hooks": [
{
"type": "command",
"command": "bun run .claude/hooks/remind-plan-startup-sequence.ts"
}
]
}
]
}
} Skills (2)
Subagents (7)
| ai-ml-engineer model: sonnet | Use this agent when you need expert guidance on AI/ML implementation, local LLM integration, or Rust-based AI application development. Examples: <example>Context: User is building a local NLP applicat |
| frontend-architect model: sonnet | Use this agent when you need to design, implement, or review frontend systems and components. This includes architecting new frontend applications, implementing UI components, establishing frontend pa |
| frontend-expert model: sonnet | Use this agent when you need expert guidance on modern frontend development, including HTML/CSS/JavaScript/TypeScript, modern frameworks like Svelte, desktop app development with Tauri, DOM manipulati |
| performance-engineer model: sonnet | Use this agent when you need to optimize application performance, analyze bundle sizes, identify performance bottlenecks, or set up performance monitoring. Examples: <example>Context: User has impleme |
| pragmatic-code-reviewer model: inherit | Use this agent when you need a thorough code review that balances engineering excellence with development velocity. This agent should be invoked after completing a logical chunk of code, implementing |
| senior-architect-reviewer | Use this agent when you need expert software architecture guidance, AI system design consultation, team task coordination, or comprehensive code review. Examples: <example>Context: User has completed |
| ux-design-expert model: sonnet | Use this agent when you need expert guidance on user experience design, interface design patterns, usability research, or design system decisions. This agent excels at analyzing user workflows, recomm |
Hooks (2)
| event | matcher | runs |
|---|---|---|
| PreToolUse | Edit|Write | bun run .claude/hooks/check-feature-branch.ts |
| PreToolUse | EnterPlanMode | bun run .claude/hooks/remind-plan-startup-sequence.ts |
Slash commands (2)
/address-review/pragmatic-code-review
Permissions
deny (0)
—
ask (0)
—
allow (2)
Bash(gh:*)
Bash(bun:*)
Similar rigs
edmund-io/edmunds-claude-code
—
Orchestrator 469 tok · · Q0
Hayashi-Takuto/edmonds-claude-code
"Edmund's personal Claude Code setup with 14 productivity commands and 11 specialized AI agents for modern web development"
Orchestrator 469 tok · · Q0
mariogmz/agentic-claude-template
Multi-agent orchestration template for Claude Code. Accelerate development 10x with 4 specialized AI agents working in parallel via git worktrees. Includes 12 workflow commands, contract-driven coordination, and automated quality checks.
Fort Knox 187 tok · · Q39
tugayerdogan-mkz/claude-agent-kit
Portable Claude Code agent workflow: /feature pipeline (build→test→security→performance→ship), 5 specialist sub-agents, doc-sync Stop hook, CI + health-check + scheduled-job templates
Orchestrator 179 tok · · Q15