google-antigravity-sdk-rust

google-antigravity-sdk-rust is a skill for Claude Code, Codex from Bilal140202/the-lord-of-the-skills. It costs 60 tokens per session (1,907 once invoked), scanned A, original, MIT.

A Rust software kit and set of instructions for building autonomous AI agents and teams of agents with Google Antigravity.

In plain words
What is it for?
Use it to create, configure, orchestrate, or debug Google Antigravity agents in Rust.
Why use it?
It brings setup, configuration, event handling, and WebAssembly build guidance together for this specific Rust SDK.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to create, configure, orchestrate, or debug Google Antigravity agents in Rust.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bilal140202/the-lord-of-the-skills/codeitlikemiley__antigravity-sdk-rust
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Bilal140202/the-lord-of-the-skills --skill codeitlikemiley__antigravity-sdk-rust
Clone the repo
git clone --depth 1 https://github.com/Bilal140202/the-lord-of-the-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for google-antigravity-sdk-rust

README.md
[![agentmods](https://agentmods.dev/badge/skills/bilal140202/the-lord-of-the-skills/codeitlikemiley__antigravity-sdk-rust/github.svg)](https://agentmods.dev/skills/bilal140202/the-lord-of-the-skills/codeitlikemiley__antigravity-sdk-rust)
Your own site
<a href="https://agentmods.dev/skills/bilal140202/the-lord-of-the-skills/codeitlikemiley__antigravity-sdk-rust"><img src="https://agentmods.dev/badge/skills/bilal140202/the-lord-of-the-skills/codeitlikemiley__antigravity-sdk-rust/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for google-antigravity-sdk-rust

Your own site · 80×15
<a href="https://agentmods.dev/skills/bilal140202/the-lord-of-the-skills/codeitlikemiley__antigravity-sdk-rust"><img src="https://agentmods.dev/badge/skills/bilal140202/the-lord-of-the-skills/codeitlikemiley__antigravity-sdk-rust.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,907 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00060 $0.01907
Opus 5 $0.00030 $0.00954
Sonnet 5 $0.00012 $0.00381
Haiku 4.5 $0.00006 $0.00191

Measured 9d ago against content hash 3aea5e0d055b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

google-antigravity-sdk-rust scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/gondor/claude-code/codeitlikemiley__antigravity-sdk-rust/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Google Antigravity Rust SDK

This skill provides comprehensive instructions, architectural guidelines, and reference examples for building autonomous AI agents in Rust using the Google Antigravity SDK.

Installation & Setup

Ensure the following prerequisites are met before building or running agents:

  1. Cargo Configuration: Include the SDK dependency in your Cargo.toml:
    [dependencies]
    antigravity-sdk-rust = { path = "path/to/antigravity-sdk-rust" }
    tokio = { version = "1", features = ["full"] }
    
  2. API Credentials: Set the GEMINI_API_KEY environment variable or supply it programmatically via GeminiConfig:
  3. Subprocess Harness: Ensure the localharness binary is accessible either on your system PATH or configured via AgentConfig::binary_path.

WebAssembly (wasm32-wasip1) Target Guidelines

When designing and deploying agents to WebAssembly targets such as wasm32-wasip1 (e.g., inside Spin or standard WASI runtimes):

  1. Compilation Check: Always verify clean target compilation:
    cargo check --target wasm32-wasip1
    
  2. Connection Protocol: Be aware that process spawning is not supported inside WebAssembly sandboxes. Instead of native subprocess IPC, use the direct network socket strategy (WasmConnectionStrategy / WasmConnection) to connect to a host-side localharness WebSocket server.
  3. Core Async Traits: Do NOT use the #[async_trait] attribute macro. The SDK uses native async traits (stable since Rust 1.75 / Rust 2024). Standard traits like Connection, Hook, Tool, and Trigger are implemented as native async traits (using impl Future + Send returns for trait-level Send bounds). For dynamic dispatch and runtime storage (e.g. Arc<dyn DynHook>), the SDK provides companion object-safe traits (DynHook, DynTool, DynTrigger) which are automatically implemented via blanket implementations for any type implementing the base trait.
  4. Mock Test Suite Guidelines: To test connection, event loops, and tool extractions under simulated WebSocket messaging, run:
    cargo test wasm::tests
    
    • Writing Mock Tests: Mock tests should spin up a local WebSocket listener, bind to port 0 to allocate a free TCP port dynamically, record that port, configure WasmConnectionStrategy to point to it, and mock standard JSON frames (StepUpdate, TrajectoryStateUpdate, etc.) to verify client state transitions.

Read the full file on GitHub · 95 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 95 lines · 60 tokens per session scan A 3aea5e0d055b

Subscribe to this mod's changes

google-antigravity-sdk-rust is a skill published in the GitHub repository Bilal140202/the-lord-of-the-skills (4 stars, last pushed 6d ago), licensed MIT. It adds 60 tokens to every session and 1,907 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.