Grok Build /goal: Long-Running Autonomous Tasks with Subagents
Melvin Vivas · X video post · 2026-06-23 · Open on X
Topics: AI Agents, Tool Use & MCP, AI Dev Tools & Productivity · Level: intermediate
Summary
xAI added a /goal command to Grok Build. It runs long tasks on its own, using several rounds of subagents to implement and then verify a single goal.
Key points
- /goal runs long-running tasks autonomously
- It uses multiple rounds of subagents to implement and verify one goal
- Pattern: split the work into implementation and verification subagents for each objective
Resources mentioned
- Grok Build · tool · x.ai · free
xAI's agentic coding CLI; data sharing is on by default and can be turned off with /privacy.
Also in: Setting up Grok Bot for coding with Grok Build and Cursor CLI (Melvin Vivas on X · notes), Reusable GPU devbox: PyTorch/CUDA plus six coding agents (Melvin Vivas on X · notes), Handing off an unfinished Codex session to Grok Build (Melvin Vivas on X · notes), Grok Build finishes a task Codex left hanging (Melvin Vivas on X · notes) and 10 more
More in AI Agents, Tool Use & MCP
- OpenRouter MCP: Pick, Price, and Test LLMs from Inside Your Coding Agent
- NVIDIA Agent Toolkit: open Nemotron models for domain-specific agents
- Qwen-AgentWorld: a single world model simulating 7 agent environments
- Building a basic MCP server with GLM 5.2 in Claude Code
- Testing free GLM 5.2 in Devin Desktop to create an MCP server
- Sakana Fugu: Multi-Agent Orchestration Behind a Single Model API