I shipped 706 commits in 5 days with Taskwarrior and Claude Code
8 comments
What did you make?
I believe this is the most pragmatic approach for real production-ready multi-agent software engineering. Most frameworks are either theoretical or over-engineered—they try to automate humans away instead of augmenting them.
The key difference: on-demand human-in-the-loop. Agents never block waiting for you. They pick up work, execute, commit, and exit. You make decisions asynchronously when ready.
This eliminates the biggest bottleneck in agent systems—the human becoming a serial dependency.
Proof isn't in benchmarks or simulation. It's 706 commits shipped in 5 days using standard tools (Taskwarrior, Zellij, Claude Code). System got rate-limited, not me.
The key difference: on-demand human-in-the-loop. Agents never block waiting for you. They pick up work, execute, commit, and exit. You make decisions asynchronously when ready.
This eliminates the biggest bottleneck in agent systems—the human becoming a serial dependency.
Proof isn't in benchmarks or simulation. It's 706 commits shipped in 5 days using standard tools (Taskwarrior, Zellij, Claude Code). System got rate-limited, not me.
Did you create anything useful though?
Yes. I've built hook scripts, Claude Code skills, and OpenClaw agents to make this work.
https://ttal.guion.io gets updated daily with guides. Still incomplete, but shows the actual patterns.
If you want to dive deeper or integrate this into your workflow: [email protected]
https://ttal.guion.io gets updated daily with guides. Still incomplete, but shows the actual patterns.
If you want to dive deeper or integrate this into your workflow: [email protected]
See https://ttal.guion.io. The daily-update guide is the best intro to how it actually works and how you can integrate it into your own workflow.
I don't he knows.
706 commits, 38 PRs merged, 5 repos, 5 days. One person with max 5 Claude Code sessions.
The stack: Taskwarrior as the task queue, Zellij as the session manager, Claude Code as the worker. Each CC session runs in a Zellij pane with a task assigned. When a session finishes, the next highest-urgency task auto-starts via Taskwarrior hooks. You manage tasks, not sessions.
Thursday I got API rate-limited and throughput dropped 75%. That's the proof - the system was the bottleneck, not me.
The key design: on-demand human-in-the-loop. Agents never block waiting for me. They pick up tasks, do the work, commit, and move on. I review PRs and make decisions when I'm ready - not when the agent needs me. That's what eliminates the human-as-bottleneck problem. 5 sessions is plenty when none of them are waiting on you.
The full setup is documented on the site. Architecture isn't locked to Claude Code - Zellij sessions don't care what CLI agent runs inside them.