← ClaudeAtlas

orchestratorlisted

Full orchestration workflow with swarm mode: evaluate -> clarify -> classify -> persist -> plan mode -> spawn teammates -> execute -> validate -> retrospective. Use when: (1) implementing features, (2) complex refactoring, (3) multi-file changes, (4) tasks requiring coordination. Triggers: /orchestrator, /orch, 'orchestrate', 'full workflow', 'implement feature'.
alfredolopez80/multi-agent-ralph-loop · ★ 146 · AI & Automation · score 80
Install: claude install-skill alfredolopez80/multi-agent-ralph-loop
# Orchestrator - Multi-Agent Ralph v3.0 **Smart Memory-Driven Orchestration** with swarm mode, parallel memory search, RLM-inspired routing, and quality-first validation. Based on @PerceptualPeak Smart Forking concept: > "Why not utilize the knowledge gained from your hundreds/thousands of other Claude code sessions? Don't let that valuable context go to waste!!" ## Quick Start ```bash # Via skill invocation /orchestrator Implement OAuth2 authentication with Google # Via CLI ralph orch "Migrate database from MySQL to PostgreSQL" # With specific teammates /orchestrator "Refactor database layer" --teammates coder,reviewer ``` ## v2.88 Key Changes (MODEL-AGNOSTIC) - **Model-agnostic**: Uses model configured in `~/.claude/settings.json` or CLI/env vars - **No flags required**: All teammates use the configured default model - **Flexible**: Works with GLM-5, Claude, Minimax, or any configured model - **Settings-driven**: Model selection via `ANTHROPIC_DEFAULT_*_MODEL` env vars ## v2.87 Key Changes (UNIFIED SKILLS MODEL) - **Skills/Commands unification**: All commands now use SKILL.md format - **Single source of truth**: Skills live in repo, symlinked globally - **Version alignment**: All skills updated to v2.87.0 - **Documentation consolidated**: Architecture docs in `docs/architecture/` ## v2.81 Key Changes (SWARM MODE) **Swarm mode is now ENABLED by default** using native Claude Code multi-agent features: 1. **Team Creation**: Orchestrator creates team "orchestration