Claude Code plugin wrapping xAI Grok CLI: ask, code review, adversarial review, deep research, image/video gen, parallel best-of-N branches, and a multi-LLM aggregate review (codex+gemini+grok). 226 tests, env scrubbing, ANSI sanitization, TOCTOU defenses.
Agent
Use when the main Claude thread wants a multi-LLM consensus on a code review — captures the current diff and dispatches the same review prompt to Codex / Gemini / Grok in parallel, then aggregates verdicts into a unified report. Prefer this over the raw /grok:review when the user asks for "all three opinions" or…
Agent
Proactively use when Claude Code wants a second implementation or diagnosis pass from xAI Grok, needs a deeper root-cause investigation against Grok's 512K-token context, should produce a long-form research report leveraging Grok's distinct training (live web/X search awareness, code-focused models), or should hand…