Kuberwastaken/subagentmaxxing

6 stars · Last commit 2026-07-14

Drive OpenAI Codex & Cursor CLI coding agents as subagents with the same ergonomics as native Claude Code subagents (grok-4.5, composer-2.5, gpt-5.5). Uniform run/fanout CLI + Claude Code skill.

README preview

<p align="center"><img src="assets/logo.png" width="160" alt="subagentmaxxing"></p>

# subagentmaxxing

**Drive OpenAI Codex and Cursor coding agents as subagents — with the same ergonomics as a native Claude Code subagent.**

<p align="center">
  <a href="https://www.skills.sh/kuberwastaken/subagentmaxxing/subagentmaxxing"><img src="https://www.skills.sh/b/kuberwastaken/subagentmaxxing" alt="skills.sh"></a>
</p>

One prompt in, one clean answer out. Pick the model (`grok-4.5`, `composer-2.5`,
`gpt-5.5`, or Cursor-hosted Opus/Sonnet/Gemini), the working directory, and the sandbox
level. Get structured JSON if you want it. Fan one prompt out across many models in
parallel for consensus or a second opinion.

The whole thing is a single dependency-free Python CLI, **`subagent`**, plus a Claude Code
skill that teaches an orchestrating agent when and how to use it.

```mermaid
flowchart LR

View full repository on GitHub →