realspqrk/harness-subagent

README preview

# harness-subagent

**Hand a bounded task to another coding-agent CLI, then judge what comes back.**

[![License: MIT][mit-badge]][mit]
[![Agent Skills][skills-badge]][agentskills]
[![Claude Code][claude-badge]][claude]
[![Codex][codex-badge]][codex]
[![Grok Build][grok-badge]][grok]
[![Cursor CLI][cursor-badge]][cursor]

Ever wanted to call **Codex** from **Claude Code**?  
Ever wanted **Grok Build** to invoke **Claude Code**?  
Ever wanted **Claude Code** to send a diff to **GPT** for a second opinion?

That is this skill. You stay in the agent you already use. It becomes the parent: it writes a short brief, starts another CLI in the background, reads that CLI's report, and tells you what it agrees with, what it does not, and what it will do next.

The child is not an oracle. A model that reviews its own work repeats its own blind spots. A model trained by a different vendor may not. That value is lost if the parent forwards the answer without judging it.

Supported child CLIs: Claude Code (`claude`), Codex (`codex`), Grok Build (`grok`), Antigravity (`agy`), and the Cursor CLI (`cursor-agent`). The host picks the CLI, the model, and the effort. The skill does not rank jobs or assign personas.

View full repository on GitHub →