ANTIGRAVITY

A setup guide for running Google's Antigravity, an agent powered by Gemini, inside Coder Eval, a framework for testing coding agents.

In plain words
What is it for?
It is for configuring Antigravity tasks, connecting a Gemini API key, and running those tasks with Coder Eval.
Why use it?
It explains the required installation, sign-in method, model settings, and how the agent's activity is scored in a sandbox.

Agent

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.

agentmods
npx agentmods add agents/uipath/coder_eval/antigravity
Clone the repo
git clone --depth 1 https://github.com/UiPath/coder_eval
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,459 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00040 $0.02459
Opus 5 $0.00020 $0.01229
Sonnet 5 $0.00008 $0.00492
Haiku 4.5 $0.00004 $0.00246

Measured yesterday against content hash 0ac5e36cbda8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ANTIGRAVITY 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 yesterday.

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.

docs/agents/ANTIGRAVITY.md · 221 lines

How it starts

The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Running Google Antigravity (Gemini) in Coder Eval

Overview

Coder Eval can run Google's Antigravity agent — powered by Gemini — as the agent under evaluation. Set agent.type: antigravity in a task and the rest of the framework (sandbox, scoring, telemetry, reports) works unchanged.

Under the hood AntigravityAgent drives the Antigravity SDK's local harness (the localharness binary bundled in the wheel) rather than the branded agy CLI or the remote Interactions API. The local harness is the only surface that can (a) authenticate headlessly with an API key and (b) make edits land in the sandbox working directory — both required for an unattended eval.

Setup

1. Install the Antigravity SDK

pip install 'coder-eval[antigravity]'

This pulls in google-antigravity (pinned to 0.1.7), whose wheel bundles the platform localharness binary. As with the other agents the SDK is imported lazily — a base install without the extra still runs end-to-end; Antigravity tasks fail at dispatch with a clear hint to install the extra.

2. Authentication

Antigravity authenticates against the Gemini Developer API with a single credential:

GEMINI_API_KEY=<your-gemini-api-key>

Set it in .env (or the environment). That is the only credential Antigravity reads — there is no base-URL, project, or region override for this agent (unlike Codex's CODEX_BASE_URL / Azure routing). If GEMINI_API_KEY is unset the SDK raises a clear error on first use.

The --backend flag (direct / bedrock) governs Claude routing only; it has no effect on the Antigravity agent.

Usage

Command line

coder-eval run tasks/agents/antigravity_hello_world.yaml --type antigravity

Or override the agent type for every task in an experiment:

coder-eval run experiments/model-comparison.yaml --type antigravity

Task definition (YAML)

agent:
  type: antigravity
  model: gemini-3.1-pro-preview   # optional; see "Model selection" below
  thinking_level: medium          # minimal | low | medium | high (default: medium)
  plugins:
    - type: local
      path: "$SKILLS_PLUGIN_PATH"  # a directory of skills (SKILL.md), env-expanded

run_limits:
  max_turns: 5
  task_timeout: 360
  turn_timeout: 300

success_criteria:
  - type: file_exists
    path: "hello.py"
    description: "hello.py must be created"

Read the full file on GitHub · 221 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. yesterday First seen · 221 lines · 40 tokens per session scan A 0ac5e36cbda8

Subscribe to this mod's changes

ANTIGRAVITY is an agent published in the GitHub repository UiPath/coder_eval (119 stars, last pushed 3d ago), licensed Apache-2.0. It adds 40 tokens to every session and 2,459 once invoked, about $0.0002 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 2026-08-30.