If you follow Theo on YouTube or X then you know about t3 code (If not then I recommend checking it out. maybe you'll like it. AND interestingly, the code is open source: https://github.com/pingdotgg/t3code) The thing is, t3 code isn't for me. As you know, I use and love CLI agents + tmux (claude code, codex cli, etc..). And t3 code is GUI only. BUT I've recently been feeling the pain of managing many agents SO I created my own version of t3 code. I called it tmux-agent-plane. It's a CLI + agent skill The way it works is with a CLI (called `tmux-agent-plane`) and an agent skill The CLI sits on top of tmux, i.e. its basically an opinionated wrapper around the `tmux` CLI. The agent skill teaches my agents how to use the CLI. There's some additional overhead, since the agents are often now needing to load this skill and use the CLI in order to do their everyday work. But for me, its completely worth it. This has really been life changing! Here's where you can get it and try it out: https://github.com/zazencodes/tmux-agent-plane There's also another video demo in the README that shows how it works Fair warning: I'm shipping a lot of changes for this, and I haven't got it working yet with Pi or OpenCode. Of course, I'd encourage you to play around with it. And I'm happy to (have my agents) review and merge in your PRs on the project!

I like this mental model best: brain = LLM body = agent harness brain + body = agent key thing to understand is that tools like Claude Code and Codex are not JUST the agent harness they CONTAIN the agent harness the harness is the software that implements and manages the agent loop. here's a concrete example: Codex (the app/CLI) is built on the Codex Core agent harness, which is open source. The agent runtime is implemented in Rust in openai/codex/codex-rs/core (on github) Claude Code's underlying agent harness is not open source. However, the Claude Agent SDK is open source and provides programmatic access to the same underlying runtime used by Claude Code The Codex or Claude Code App (or CLI) actually bundle both the AGENT HARNESS and the INTERFACE into the agent The "agent" here is the combination of HARNESS + LLM This is all jargon, at the end of the day. But as an educator its important for me to know what I'm talking about when I say "agent" or "agent harness" This was inspired by Theo's recent content explaining harnesses, which GREATLY helped develop my thinking around this topic: https://x.com/theo/status/2117213872348348429

Hello, yesterday we had a workshop at work about KIro, the AWS AI Harness, and was wondering if anyone have tried it or has any experience on it. I tried mostly the Kiro Crew flavor and it has some really good features.

We pointed an agent pipeline (intake, spec, build, gate, review, approve) at our whole SQL audit backlog, 45 findings in one go. We also adapted the factory to our way of working as we went: • Scope control: we agreed up front to skip the DBA and infra items and run only the findings that touch our code, two jobs at a time. • Ticket hygiene: we held rejected and duplicate findings back so they didn't each open a Jira ticket. • Ticket and branch reuse: the factory can now continue a ticket's existing branch. When that branch turned out to carry other tickets' commits, we cut a clean one from develop with only the new work, and added a command to repoint the job. • Rollback rule: the DDL reviewer pointed out that our deployment runs every .sql file, so rollback copies there were dangerous. We kept a single canonical rollback and taught the lint to accept it. • Human decisions: the pipeline stops and asks whenever evidence is thin, a ticket is shared, or the risk is high. The result: a strong filter and reviewer that is shaped around our process, with a human decision before anything ships.

Looking forward to Wednesday’s Software Factory update! I’ve really enjoyed the last release and have been putting it to work on a couple of small projects. I’ve even customized it a bit, including some UI changes of my own. Excited to see what’s next. Added API token cost report.