By yuting0624
Route judgment-heavy SDLC work to Claude while delegating deterministic high-volume tasks like scaffolding, test generation, migrations, and first-pass code review to Antigravity (Gemini), reducing token costs and enabling hybrid agentic engineering.
Cancel a running background Antigravity (agy) delegation job.
Delegate a well-scoped subtask to Antigravity (agy/Gemini) under cost discipline, then verify.
Claude-orchestrated deep research — Antigravity (agy/Gemini) does the grounded web legwork; Claude plans, verifies the citations, and synthesizes.
Fetch the output of a finished background Antigravity (agy) job, then verify it.
Get an independent cross-model review of the current diff from Antigravity (Gemini), then reconcile as the final judge.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
This plugin requires configuration values that are prompted when the plugin is enabled. Sensitive values are stored in your system keychain.
timeoutDefault agy print-mode timeout when --timeout is not passed, e.g. 5m, 10m, 300s.
${user_config.timeout}default_tierTier used by agy-delegate.sh when --tier is not passed. One of: flash (Gemini 3.5 Flash High, default — bulk work), flash-lo (Flash Low, cheapest/trivial), pro (Gemini 3.1 Pro High, harder reasoning).
${user_config.default_tier}coding_policyWhen on, a SessionStart hook injects this plugin's cost-aware routing policy (delegate above the break-even, keep Claude's context lean, always verify agy's output) as session context, so the discipline applies without invoking the skill. Set to off/false/0/no to suppress.
${user_config.coding_policy}Run the Antigravity CLI (Gemini) as a collaborating sub-agent, right inside Claude Code.
Claude conducts the judgement; Gemini does the heavy lifting — intelligent model routing across the SDLC.

Claude stays the conductor; the bulk, token-heavy read ran on cheaper Gemini, and Claude verified the result.
| Claude (conductor) | Gemini / agy (executor) | |
|---|---|---|
| Owns | requirements · architecture · the hard 20% · verification · review | scaffold · implementation · test generation · search |
| Strength | judgement | cheap, fast throughput |
you → Claude Code (conduct: design / verify / review)
└── agy → Gemini (execute: implement / test / search)
Generation is solved; verification, judgement, and direction are the craft.
AGENTS.md.SessionStart hook injects the cost-aware
routing policy automatically (toggle in plugin settings), and the antigravity-delegate
subagent does file writing on Gemini, so Claude spends no tokens generating file contents.On a large ADK multi-agent build (+ adk eval), same task / same model, 3 ways:
| Claude solo @high | solo @max | hybrid | |
|---|---|---|---|
| frontier cost (COST-WEIGHTED) | 2.62M | 5.34M | 1.91M |
quality (adk eval) | ✅ 3/3 | ✅ 3/3 | ✅ 3/3 |
→ −27% vs solo@high, −64% vs solo@max, at equal quality — and the cheap Gemini work isn't even counted. Savings scale with task size; tiny one-off tasks are cheaper to just run on Claude. Full A/B: docs/AB-RESULTS.md.
Note on cost figures: numbers are estimates — token counts are approximated and rates live in
prices.json. Set your real Vertex rates there before quoting any figure.
In Claude Code:
/plugin marketplace add yuting0624/antigravity-for-claude-code
/plugin install antigravity@antigravity-for-claude-code
/antigravity:setup # verifies agy is installed + authenticated
Prerequisites: the Antigravity CLI (agy) installed & authenticated (agy models lists Gemini models), and Claude Code. For the same-bill cost benefit, run Claude Code on Vertex too.
The plugin's commands show up natively in Claude Code's / menu.
| command | what it does |
|---|---|
/antigravity:setup | health check — agy installed + authenticated, scripts ready |
/antigravity:delegate [--tier flash|pro] <task> | delegate a subtask to agy under cost discipline, then verify |
/antigravity:review [--adversarial] | independent cross-model review of the current diff; Claude reconciles |
/antigravity:research <topic> | Claude-orchestrated deep research — agy does grounded web legwork, Claude verifies citations across ≥2 sources |
/antigravity:status [id] · :result <id> · :cancel <id> | manage background delegation jobs |
Background jobs are for interactive sessions (fire-and-collect). In headless
claude -p(one-shot), delegate synchronously — there's no later turn to collect a result.
# one-shot delegation (plain text on stdout)
scripts/agy-delegate.sh --tier flash "Summarize this changelog in 3 bullets: ..."
# give Antigravity a workspace for multi-file agentic work
scripts/agy-delegate.sh --tier pro --dir ./src "List every TODO with file:line"
npx claudepluginhub yuting0624/antigravity-for-claude-code --plugin antigravityv9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Multi-agent orchestration framework for Claude Code. Routes tasks to specialized Haiku/Sonnet subagents while Opus orchestrates — inspired by speculative decoding. Includes 10 specialized heads, environment preflight checks, and ~50% API cost reduction.
Sub-agent runner — runs agent definitions on Codex, Claude Code, Cursor CLI, or Gemini CLI from any host AI tool.
HelloAGENTS — The orchestration kernel that makes any AI CLI smarter. Adds intelligent routing, unified QA gates, safety guards, and notifications.
This skill should be used when the model's ROLE_TYPE is orchestrator and needs to delegate tasks to specialist sub-agents. Provides scientific delegation framework ensuring world-building context (WHERE, WHAT, WHY) while preserving agent autonomy in implementation decisions (HOW). Use when planning task delegation, structuring sub-agent prompts, or coordinating multi-agent workflows.
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use