Zilong Liang / Hack Notes on Mar 17, 2026
These days I’ve been working on new features and larger overhauls for my websites. It feels like I’m gradually preparing for the next step of their development. My three sites still share a lot of duplicated logic, including routing, components, and content categorization. Inspired by Starlight, I want to turn the theme into a reusable Astro integration. I created issue #80 to track the plan. This would not only help keep my codebase cleaner, but also make it easier for others to start writing with a minimal but opinionated framework.
Use subagents and custom agents in Codex1. Subagents are now generally available in Codex, after previously being introduced as an experimental feature called “multi-agents”.
In short, you can ask Codex to spawn subagents that run in parallel with one another and with the main agent. They use their own context windows and report back to the main agent when they are done. Subagents can have their own models and instructions. There are built-in agents like explorer, and you can define your own ones with TOML configuration files under .codex/agents.
One fun detail is that Codex picks a random nickname for each subagent. My first try gave me an explorer subagent called “Galileo”.
Galileo explored the repo for my websites
I first learned about subagents through Amp, which ships several curated custom agents like Oracle and Librarian. What I like about Amp’s approach is that it presents subagents as recommended workflows, not just as a feature to try on your own. By pairing carefully designed agents with specific models and tools, it also shows how subagents fit into everyday work. That has been a consistent strength of Amp: it tends to package what it sees as the current best practice, and that is also where I first started to understand the idea of subagents.
Here are other comments on this Codex release:
- Simon Willison’s post
- Vaibhav (VB) Srivastav’s article: You Should Be Using Subagents in Codex!
Now that major coding agents like Claude Code, OpenCode, and Cursor all support subagents in broadly similar ways, will subagents become a standard, like skills?