All Topics
All Topics
Technology
Technology
Design
Design
Programming
Programming
Science
Science
News
News
Gaming
Gaming
Entertainment
Entertainment
Business
Business
Finance
Finance
Sports
Sports
Health
Health
Food
Food
Travel
Travel
Art
Art
Music
Music
Books
Books
Education
Education
Politics
Politics
Personal
Personal
No algorithm. No AI slop. No ads. Just RSS. Pro-human. Indie writers. Real journalism. Open web. Chronological. Hand toasted.

A Practical Workflow for Running 4-8 Parallel Coding Agents with tmux and Markdown Specifications

By

schipperai

3mo ago· 14 min readen

Summary

The article describes a practical workflow for running 4-8 parallel coding agents using a lightweight setup with tmux, Markdown files, bash aliases, and Claude Code. The author explains their system of using Feature Designs (FDs) - Markdown files that serve as specifications for coding tasks. The workflow enables parallel development with multiple AI coding agents without complex orchestration tools, using a role naming convention per tmux window. The author notes that beyond 8 agents, it becomes difficult to maintain quality and keep up with the work.

Key quotes

· 4 pulled
I've been running parallel coding agents with a lightweight setup for a few months now with tmux, Markdown files, bash aliases, and six slash commands.
Most actual code writing happens from a finished spec I call Feature Designs (FDs). An FD is just an md file that has...
Since I adopted this, I am able to work in parallel with 4 to 8 agents. After 8+ agents it's hard to keep up and the quality of my decisions suffer.
These are vanilla agents - no subagent profiles or orchestrators, but I do use a role naming convention per tmux window.
Snippet from the RSS feed
A practical workflow for running 4–8 parallel coding agents using Claude Code, tmux, and a Markdown-based feature design system.

You might also wanna read

ClawTab: macOS App for Managing Multiple AI Coding Agents with tmux Interface

ClawTab is a macOS desktop application designed to help developers manage multiple AI coding agents simultaneously. It provides a graphical

Product Hunt·1mo ago

Mantel: A macOS terminal tool for managing multiple Claude Code sessions with per-project visual cues

A developer describes switching from IDEs to Claude Code sessions in macOS Terminal in early 2026, running multiple sessions simultaneously.

Product Hunt·17d ago

Building a Personal AI Agent with Markdown-Based Skills and Local Models

The article describes a personal AI agent built on Pi that manages the author's inbox, calendar, deal pipeline, blog publishing, and researc

tomtunguz.com·2d ago

Mozzie: Open-Source Desktop Tool for Orchestrating Parallel AI Coding Agents

Mozzie is an open-source, local-first desktop tool that enables parallel orchestration of multiple AI coding agents. It allows users to crea

Product Hunt·2mo ago

Stagent: A state-machine tool to keep Claude Code on track for long tasks

Stagent is a tool designed to solve the problem of Claude Code (and similar AI coding assistants) failing to complete long, multi-step tasks

Product Hunt·19d ago

Building a Software Factory with Claude Code: From AI-Assisted Coding to Agentic Development

This article provides a comprehensive guide on building a software factory using Claude Code and other AI coding tools. It covers the evolut

freecodecamp.org·4d ago

Building a Software Factory with Claude Code: From AI-Assisted Coding to Agentic Development

This article provides a comprehensive guide on building a software factory using Claude Code and other AI coding tools. It covers the evolut

freecodecamp.org·4d ago