Key Points

Subagents are now generally available for OpenAI Codex, enabling orchestration of coding tasks via specialized agents.\n- OpenAI Codex ships default subagents named \"explorer\", \"worker\", and \"default\", with \"worker\" likely designed for running many small tasks in parallel, though the exact distinction between \"worker\" and \"default\" isn't fully clarified.\n- You can define custom agents as TOML files in ~/.codex/agents/ with custom instructions and bind them to specific models, including speed-focused options like gpt-5.3-codex-spark.\n- Prompts can reference these named subagents to compose complex workflows, exemplified by a sample prompt that investigates a UI failure using browser_debugger, code_mapper, and ui_fixer.\n- The feature is accompanied by cross-platform documentation for subagents across Codex, Claude Code, Gemini CLI, Mistral Vibe, OpenCode, VS Code, and Cursor.

Simon Willison’s Weblog

Sponsored by: CodeRabbit — Planner helps 10x your coding agents while minimizing rework and AI slop. Try Now.

16th March 2026 - Link Blog

Use subagents and custom agents in Codex (via) Subagents were announced in general availability today for OpenAI Codex, after several weeks of preview behind a feature flag.

They're very similar to the Claude Code implementation, with default subagents for "explorer", "worker" and "default". It's unclear to me what the difference between "worker" and "default" is but based on their CSV example I think "worker" is intended for running large numbers of small tasks in parallel.

Codex also lets you define custom agents as TOML files in ~/.codex/agents/. These can have custom instructions and be assigned to use specific models - including gpt-5.3-codex-spark if you want some raw speed. They can then be referenced by name, as demonstrated by this example prompt from the documentation:

Investigate why the settings modal fails to save. Have browser_debugger reproduce it, code_mapper trace the responsible code path, and ui_fixer implement the smallest fix once the failure mode is clear.

The subagents pattern is widely supported in coding agents now. Here's documentation across a number of different platforms: