Grok Build
Coding agent CLI with parallel subagents, plan review, and MCP support.
xAIHow skills run on Grok Build
Grok Build reads files, writes code, runs shell commands, and spawns subagents from a terminal session or a headless CI job. Plan review covers the steps the model proposes, not the skill text that shaped the plan.
Skill security, assessed
Every public skill in our index is assessed by the Anomity Skill Intelligence engine against its real source: remote code execution, credential and data exfiltration, prompt injection, and unsafe installers.
Govern the skill layer on Grok Build
Scanning a skill before use tells you what it claims to do. Anomity's Endpoint Sensor sees what agents actually do at runtime: it discovers every skill, agent, and MCP server on the endpoint, and policy can allow, deny, or log the tool calls a skill triggers on Grok Build and every other agent. Violations route to your SIEM, Slack, email, or Jira with a queryable 90-day audit trail.
Book a 30-minute demo to see your own agent and skill inventory.
