orchestrator
✓Automated multi-agent orchestrator that spawns CLI subagents in parallel, coordinates via Serena Memory, and monitors progress
Installation
SKILL.md
Important This skill orchestrates CLI subagents via gemini -p "..." --approval-mode=yolo. It uses Serena Memory as a shared state bus. Each subagent runs as an independent process.
| MAXPARALLEL | 3 | Max concurrent subagents | | MAXRETRIES | 2 | Retry attempts per failed task | | POLLINTERVAL | 30s | Status check interval | | MAXTURNS (impl) | 20 | Turn limit for backend/frontend/mobile | | MAXTURNS (review) | 15 | Turn limit for qa/debug | | MAXTURNS (plan) | 10 | Turn limit for pm |
PHASE 1 - Plan: Analyze request -> decompose tasks -> generate session ID PHASE 2 - Setup: writememory("orchestrator-session.md") + writememory("task-board.md") PHASE 3 - Execute: Spawn agents by priority tier (never exceed MAXPARALLEL) PHASE 4 - Monitor: Poll every POLLINTERVAL; handle completed/failed/crashed agents
Facts (cite-ready)
Stable fields and commands for AI/search citations.
- Install command
npx skills add https://github.com/first-fluke/fullstack-starter --skill orchestrator- Category
- </>Dev Tools
- Verified
- ✓
- First Seen
- 2026-02-01
- Updated
- 2026-02-18
Quick answers
What is orchestrator?
Automated multi-agent orchestrator that spawns CLI subagents in parallel, coordinates via Serena Memory, and monitors progress Source: first-fluke/fullstack-starter.
How do I install orchestrator?
Open your terminal or command line tool (Terminal, iTerm, Windows Terminal, etc.) Copy and run this command: npx skills add https://github.com/first-fluke/fullstack-starter --skill orchestrator Once installed, the skill will be automatically configured in your AI coding environment and ready to use in Claude Code or Cursor
Where is the source repository?
https://github.com/first-fluke/fullstack-starter
Details
- Category
- </>Dev Tools
- Source
- skills.sh
- First Seen
- 2026-02-01