roborev: continuous local code review that drives Grok Build
At a glance
MIT Go daemon + git hook reviews every commit with the CLIs you already pay for—Codex, Claude Code, Cursor, OpenCode, and first-class Grok Build (grok / grok-build). Findings stay in a ledger until closed; agent hooks push open review IDs back into the session for /roborev-fix before context goes cold. Reviews stay on your machine. This workflow is listed under Grok-Bot, coding-agents, code-review, HITL, devtools.
Agents / tools
roborev, Grok Build, Grok Bot, Codex, Claude Code, Cursor
Marc Lou’s MailCheap exposes Streamable HTTP MCP at https://mailcheap.ai/mcp so ChatGPT, Claude and Grok Bot connect with OAuth (no key to copy); Claude Code, Codex and Cursor use a bearer API key. Agents can draft campaigns, send tests, schedule issues and read stats; schedule/send tools are marked destructive and ask before sending. Open-source / self-host option; pay only for SES-style sends vs beehiiv-class plans.
Skysay’s hosted Streamable HTTP MCP (https://api.skysay.ai/mcp) lets Grok Bot check coverage, request numbers, place approved outbound calls through a hosted voice agent, and send SMS—OAuth/PKCE, separate call vs SMS approval, no local Twilio bridge. Start read-only with account_overview; outside US/CA/UK/MX outbound often needs carrier review first.
Night Orders Studio’s Grok Bot Chief of Staff describes the same hybrid SpaceXAI ships: hand coding to Cursor cloud agents and a Grok Build terminal, while a desk of agents (Build, Legal, Tester, App Store) checks every build and one human signs off. Lingxi Li’s Engineer Bot on the Grok Bot Marketplace packages the supervisor lane—board work on the repo you name, launch cloud agents, watch PRs ~every 30 minutes, only ask you to merge.
macOS menu-bar app that finds npm/dev servers and daemons started by Claude Code, Cursor, Codex, OpenCode, or T3 Code—including ghosts after the agent exited—and kills the process tree in one click.