Parallel Agents

This orchestrates multiple specialized agents through AG Kit's native agent system to tackle complex tasks that need different domains of expertise. You've got 17 agents to work with, from security auditors to frontend specialists, and you can chain them sequentially or run comprehensive analyses from multiple angles. The real value is in the synthesis step where findings from all agents get consolidated into prioritized recommendations instead of scattered reports. It's overkill for simple tasks, but when you need a security audit plus performance review plus test coverage analysis, having everything happen in one session with shared context beats coordinating separate reviews. The explorer agent mapping structure before domain specialists dig in is a solid pattern.

skills.sh installs: 122
GitHub stars: 7.6K
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add vudovn/antigravity-kit --skill parallel-agents --agent claude-code

Installs into .claude/skills of the current project.

Files

Safe Parallel Agents

Antigravity-first patterns for bounded delegation, isolation, and evidence-based synthesis.

Use parallel agents only when work is independent

Good candidates:

separate read-only reviews of security, performance, architecture, or tests;
implementation tasks with non-overlapping file ownership;
research lanes that can return independent artifacts;
verification that should be performed by a different specialist.

Do not parallelize:

two writers touching the same file or migration sequence;
tasks with unresolved requirements or shared mutable state;
consequential operations awaiting approval;
work that cannot be isolated by paths, worktrees, sandboxes, or sequencing;
a simple task that one specialist can complete safely.

Runtime-neutral capability discovery

Google Antigravity is the primary production runtime. Use its native agent/task views and controls when available. Do not assume Claude-specific model names, built-in agents, or hidden tools.

Before delegation, confirm support for:

SKILL.md on GitHub