@lawrencecchen: I adopted @steipete's coding workflow last year. You just have to just talk to your agents. So it's super important to …
Summary
Lawrence Chen shares his adoption of Peter Steinberger's coding workflow, highlighting cmux, a tool he built to manage multiple codex agents and notify him when they finish, improving multitasking in terminal environments.
View Cached Full Text
Cached at: 05/23/26, 04:14 PM
I adopted @steipete’s coding workflow last year. You just have to just talk to your agents.
So it’s super important to know when and where an agent wants to talk to you! This is what I built cmux around.
When you have a lot of codexes/claudes side by side, having the blue pane flash around terminals when codex is done is really nice to have.
cmux is intentionally unopinionated, so you can bring worktrees, multiple checkouts, whatever workflow you want…
Peter Steinberger 🦞 (@steipete): I’m late to the party, but cmux is great. https://t.co/8uuStvqwcm
current split: codex mac app: knowledege work, learning, reading cmux + codex cli: coding
Similar Articles
@steipete: I'm late to the party, but cmux is great. https://github.com/manaflow-ai/cmux… current split: codex mac app: knowledege…
cmux is a Ghostty-based macOS terminal with vertical tabs and notifications designed for AI coding agents, featuring SSH support, in-app browser, and Claude Code Teams integration.
@PaulSolt: https://x.com/PaulSolt/status/2073470146115490230
Paul Solt shares a detailed workflow for using Codex agents in a loop to autonomously build features overnight, including a manager thread, heartbeat, and automated PR review. The technique shifts from single prompts to designed agent loops, enabling continuous development with minimal human intervention.
@jxnlco: https://x.com/jxnlco/status/2057153744630890620
This tweet thread discusses best practices for using the Codex coding agent, focusing on durable threads, voice input, steering, queuing, and its expanding capabilities beyond code generation to full computer workflow automation.
@svpino: I'm now *subagent-pilled* with Claude Code. This is the biggest update I've made in the way I work over the last 2 week…
Shares a workflow tip for Claude Code: use subagents to keep context windows separate, mix different models, and assign specific tools to each subagent.
@jasonzhou1993: I gave my coding agent a map across 3 of my repos: - Reduce ~50% token - a grep hook so every grep call has much richer…
Jason Zhou shares a technique to give coding agents a map across repos, reducing token usage by ~50% and enabling richer grep and call chain tracing. He also releases a Claude Code plugin marketplace called AI Builder Club Skills for setting up codebase harness and compounding agent loops.