One agent supervises all their Claude Code sessions, from an iPhone
Micromanaging five, 10 or 20 agent sessions doesn't scale. Their OpenClaw agent, Patch, runs the Claude Code instances in a shared tmux session and reports back in one Telegram chat.
Spotted: found in the wild. Details are as reported by the source above and have not been independently verified.
What they did
Chats with their OpenClaw agent, named Patch, over Telegram. Patch starts a shared tmux session on their 22-core development workstation and gives them a command to attach to it from the Blink app on their iPhone, over Tailscale and SSH. Patch then starts and directs multiple Claude Code instances across their repositories.
How it went
Instead of micromanaging five or 10 or 20 agent sessions themselves, they manage only Patch, which reports status and issues back in one Telegram chat. They call it a true management structure that makes it easier to scale.
Try it yourself with OpenClaw
You supervise my coding agents. For each task I send, start a Claude Code session in a new tmux window on [machine] in the right repository, give it the task with clear acceptance criteria, and check on it every [minutes]. Answer its routine questions yourself, bring real decisions to me, and send me one status summary per task when it's done or blocked.
A starting prompt written by Agents in the Wild. Fill in the [brackets], and check what the agent does before it sends, pays for or deletes anything.
Markdown files should just open, so they asked Claude Code for a viewer. It opens instantly: faster, they say, than any other macOS app, and faster than Bitwarden's Chrome extension shows its fill menu.
Migrating a password reset flow, Claude Code and Opus produced code on par with a mid level developer. It needed close supervision throughout, and cost roughly 2 months of Pro subscription for about half a day's work.
A URL shortener side project ran on AWS. Claude Code wrote the GitHub Actions workflows for the move and fixed each failure as it came up. The writer reports zero downtime.
A 7-app monorepo needed an 8 GB memory setting and 25 seconds to typecheck. Claude Code made the changes for the move to oxlint, oxfmt and tsgo, and the team validated each step.
Turning plan files into Claude Code workflows took 5-6 hours each. A script that converts them deterministically, and flags what can move out of the LLM, cut that to 20-30 minutes at about 20% of the tokens.
An inherited app on Azure, an error, and a hunt that could easily take 1-2 days by hand. With CLI access to Azure and the repo, Claude Code ran the config and network checks and found the root cause in about 45 minutes.