Compare a hard question across Grok, Claude Code, and Codex inside one bot
At a glance
Austen Allred packaged three AI systems into a Grok Bot skill that compares answers and can run multiple rounds of debate. This workflow is listed under multi-model, decision-support, reusable-skills.
He turned a practice of showing models one another's assessments into a shared Grok Bot skill. Its public template runs Grok, Claude Code, and Codex on the same question, with quick sanity checks or repeated debate. The template names forecasts, critiques, product requirements, and strategy decisions as applications.
Save ideas in this browser. Upvotes count across the board.
Native macOS app orchestrates official Claude Code, Codex and Grok CLIs as a role-based crew (lead/builder/reviewer/docs/auditor/on-call) on your Mac or VPS with schedules, one-click risky-command approvals (Telegram too), and server screen/browser/terminals—no Bandito cloud for your code.
A builder asked Grok Bot to bridge to Claude Code—Grok does live research/browser work while Claude Code builds, and they ping each other for Playwright and research help.
Product Hunt’s Cronloop lets you describe a recurring job in Markdown, pick Codex or Claude Code, connect tools, and run agents on a loop with durable memory that can self-improve each run.
Docs overview of Coder Agents, Agent Relay, IDE agents, and agents-in-templates—plus Terraform snippet to install Claude Code/Codex modules into a workspace template.
