Claude Code Antigravity Agents

Turn Claude Code into an orchestrator — delegate heavy jobs to Google Antigravity sub-agents while it keeps building.

Created by Mark Fulton · Founder of the Vibe Coding is Life community (316k+ members)

Co-authored by Claude Fable 5

---

A single Claude Code skill — one markdown instruction file (SKILL.md) named antigravity-agents. Skills are capabilities Claude Code loads on demand. This one teaches it to hand off work to the Google Antigravity CLI (agy), an autonomous terminal coding agent powered by Gemini and other models.

With the skill loaded, Claude Code stops being a single worker and becomes an orchestrator: it writes a self-contained brief, launches an agy job in the background, keeps working on your task, then collects and verifies the result before trusting a line of it.

Contents

• Why you'd want this
• How it works
• Prerequisites
• Install the skill
• Usage
• Safety model
• Attribution

Why you'd want this

• Save your tokens. Full-repo audits, big refactors, and research sweeps are expensive to run inside a Claude session. Offload them to Antigravity instead of burning your Claude context and subscription tokens on the grind work.
• Broaden your model choice. Run a job on Gemini (or whatever Antigravity offers) for a genuinely independent second opinion — or just to put the right model on the right task.
• Work in parallel. Fan out several sub-agent jobs at once while Claude Code stays responsive to you. More gets done per unit of wall-clock time.

	Solo Claude Code session	With antigravity-agents
Long audits / refactors	Run inline, spending your context	Handed off to a background sub-agent
Second opinion	Same model, same session	An independent model reviews the work
Throughput	One task at a time	Multiple jobs run while Claude stays responsive
Your Claude tokens	Spent on the heavy lifting	Spent on orchestration and verification

How it works

Claude writes the brief, launches the job non-interactively (agy -p "<task>"), and immediately returns to your work. The sub-agent runs on its own. When it finishes, Claude reads the output and verifies it — git diff, typecheck, build — before any of it is trusted or merged.

flowchart LR
    A[Claude Codeorchestrator] -->|writes self-contained brief| B["agy -p '<task>'"]
    B -->|launched in background| C{Job type}
    C -->|read-only| D[Sandbox moderuns concurrently]
    C -->|writes files| E[Isolated worktreeor separate repo]
    A -. keeps building your task .-> A
    D --> F[Result]
    E --> F[Result]
    F -->|git diff · typecheck · build| G[Claude verifies]
    G -->|trusted| H[Folded into your work]

Prerequisites

Two one-time steps.

1. Install the Antigravity CLI.

On macOS / Linux:

curl -fsSL https://antigravity.google/cli/install.sh | bash

On Windows (PowerShell):

irm https://antigravity.google/cli/install.ps1 | iex

Full details are in the official guide: https://antigravity.google/docs/cli/getting-started

2. Sign in to Google.