Subagents with mixed models: a strong planner and a fast executor
Melvin Vivas · X post · 2026-09-13 · Open on X
Topics: AI Agents, Tool Use & MCP, AI Dev Tools & Productivity · Level: intermediate
Summary
The creator shares a post saying fx.sh can now run subagents that use different models and reasoning efforts. The example uses Fable as the planner and Grok as the fast executor. You can set this up in AGENTS.md or in your prompt, and you can steer the agents while they run.
Key points
- fx.sh can run subagents, each with its own model and reasoning effort.
- Pattern: a strong reasoning model plans and a fast, cheaper model does the work (e.g., Fable plans, Grok executes).
- You can set the model preference in an AGENTS.md file or directly in your prompt.
- You can steer the subagents while they run.
Resources mentioned
- fx.sh · tool · fx.sh · free
Coding-agent tool that runs subagents with different models and reasoning efforts. - AGENTS.md · docs · agents.md · free
Instruction file format that gives coding agents project context such as the tech stack, skills and MCP servers.
Also in: Claude Code Now Reads AGENTS.md When CLAUDE.md Is Missing (Melvin Vivas on X · notes), Updating Skills and AGENTS.md for Astra with OpenAI's Guidance (Melvin Vivas on X · notes), How to Prompt GPT-6 Astra in Codex: Simpler Instructions, Leaner AGENTS.md (Melvin Vivas on X · notes), OpenAI Guide: Rethinking Skills and Prompts for GPT-6 Astra (Melvin Vivas on X · notes) and 5 more - Fable · tool · anthropic.com · paid
Named as what the creator used with Devin for this build; the post gives no details about what it is.
Also in: Is AI Getting Cheaper? How to Measure LLM Cost Per Task and Per Intelligence Level (Melvin Vivas on X · notes), Demo: One-Shotting a Flappy Bird iPhone App with Devin and Fable 5.1 (Melvin Vivas on X · notes), Cognition's SWE-2 Coding Model Now in Devin (Melvin Vivas on X · notes), GPT-6 Astra Access Across Plans vs Fable on Claude Max (Melvin Vivas on X · notes) and 11 more - Grok · tool · x.com · free
xAI's LLM chatbot; the creator runs a custom 'ML Grok Bot' on it to help debug and improve the pipeline.
Also in: Grok Bot Turns an X Post into a Shareable Dashboard (Melvin Vivas on X · notes), Demo: Grok Turns Your X Post Data into a Dashboard (Melvin Vivas on X · notes), Using a Custom Grok Bot Persona to Learn Arduino (Melvin Vivas on X · notes), Using a Grok Custom Bot Template as an Arduino Tutor (Melvin Vivas on X · notes) and 32 more
Try this
- Try having a strong model plan and a fast model execute in your coding-agent setup.
- Write your model preferences in AGENTS.md or in your prompt.
More in AI Agents, Tool Use & MCP
- Agent Skill to Analyze Your X (Twitter) Analytics Export
- Frontier Model as Orchestrator, Local Open Models as Subagents
- One-Shot Agent Management UI with DeepSeek Harness for $0.19
- Codex orchestrator repo: Astra/Sol orchestrate, Luna runs subagents
- OpenAI Agents API with Bring Your Own Sandbox as a backend for a 'software factory'
- Claude Code mockup: a UI for managing agents in sandboxes