Orchestrator/Subagent Patterns: Astra-Luna Skill vs Fusion and Advisor
Melvin Vivas · X post · 2026-09-22 · Open on X
Topics: AI Agents, Tool Use & MCP, AI Dev Tools & Productivity, AI System Design & Architecture · Level: advanced
Summary
The creator compares his Codex Astra-Luna orchestration skill with Devin's Fusion pattern and Anthropic's Advisor pattern. In his skill, a strong model (Astra or Sol) orchestrates and a cheaper model (Luna) runs the subagents. He plans to combine the best parts of these patterns and is thinking about using the Pi harness to experiment.
Key points
- Orchestrator/worker pattern: a strong, expensive model plans and hands off work, and cheaper models carry it out as subagents.
- The codex-astra-luna-orchestrator repo uses Astra or Sol as the orchestrator and Luna for subagents in Codex.
- Devin Fusion and the Claude Advisor tool solve the same problem in different ways and are worth comparing.
- A customizable agent harness (Pi) could be used to try out mixed patterns. The creator asks whether Pi supports subagents natively.
Resources mentioned
- donvito/codex-astra-luna-orchestrator · repo · github.com · free
The creator's Codex skill for an orchestrator-plus-subagents setup (Astra orchestrator, Luna subagents), configured through config.toml.
Also in: Codex Orchestrator Pattern: Astra/Sol Orchestrator with Luna Subagents (Melvin Vivas on X · notes), Open-source Codex skill: Astra/Sol orchestrator with Luna subagents (Melvin Vivas on X · notes), Cost-Efficient Codex Subagents: Astra/Sol Orchestrator + Luna Workers (Melvin Vivas on X · notes), Codex Orchestrator v0.2.1: GPT-6 Sol orchestrator with Luna subagents (Melvin Vivas on X · notes) and 27 more - Devin Fusion · tool · cognition.com · free
Cognition's write-up of the approach and architecture behind Devin Fusion, its multi-model routing for agentic coding.
Also in: Pointer: How Devin Fusion Works (Melvin Vivas on X · notes), Devin Fusion: Multi-Model Routing to Cut Agentic Coding Costs (Melvin Vivas on X · notes), Devin Fusion: A Hybrid-Model Harness for Agentic Coding (Melvin Vivas on X · notes), Devin Fusion: A Hybrid-Model Harness for Agentic Coding (Melvin Vivas on X · notes) - Claude Advisor tool · docs · platform.claude.com · free
Official documentation for Anthropic's Advisor tool, where an advisor model guides cheaper executor models.
Also in: Claude Advisor Pattern: Routing Work to Cheaper Executor Models (Melvin Vivas on X · notes) - Pi · tool · x.com · free
A customizable coding agent that can be extended through its Extensions API and connected to several model providers.
Also in: Sign in with ChatGPT: Setting Usage Limits for Each App (Melvin Vivas on X · notes), Pi reaches v1.0 (Melvin Vivas on X · notes), Claude Code mods: customize behavior and UI with plugins (Melvin Vivas on X · notes), Customizing Your Coding Setup with Pi Coding Agent Extensions (Melvin Vivas on X · notes) and 39 more - OpenAI Codex · tool · openai.com · paid
OpenAI's coding agent. In the diagram it writes code, fixes review findings and drives the build loop. The creator also used it to make this video.
Also in: An agent bot that installs and drives Codex on its own (Melvin Vivas on X · notes), Asking a Coder bot to install Codex (Melvin Vivas on X · notes), Sign in with ChatGPT: Setting Usage Limits for Each App (Melvin Vivas on X · notes), Codex Cloud Environments Must Be Saved & Published Before Use (Melvin Vivas on X · notes) and 240 more
Try this
- Read about the Devin Fusion and Claude Advisor patterns and compare them.
- Study the Astra-Luna orchestrator repo.
- Build a more advanced orchestration skill that combines the best parts of the Fusion, Advisor and orchestrator/subagent patterns, possibly on the Pi harness.
More in AI Agents, Tool Use & MCP
- Codex Orchestrator v0.2.1: GPT-6 Sol orchestrator with Luna subagents
- Why LLM data agents need solid data foundations (Runpod)
- Pointer: Subagents in Devin CLI
- Claude Advisor Pattern: Routing Work to Cheaper Executor Models
- Pointer: How Devin Fusion Works
- The complete arXiv corpus as a Hugging Face dataset