antigravity

antigravity is a skill for Claude Code from Dannykkh/skill-olympus. It costs 54 tokens per session (500 once invoked), scanned A, original, MIT.

A guide for using Google Antigravity CLI, a command-line tool that asks another AI model to review code or plans.

In plain words
What is it for?
Use it for independent code reviews, plan reviews, large-context analysis, and evidence-based findings from a repository.
Why use it?
It gives you a second opinion and helps analyse large amounts of code without relying on the first review alone.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Gemini CLI.

Part of the skill-olympus plugin — 98 skills, 7 commands, 42 agents, 5 MCP servers shipped together

Good fit Use it for independent code reviews, plan reviews, large-context analysis, and evidence-based findings from a repository.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dannykkh/skill-olympus/antigravity
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 Dannykkh/skill-olympus --skill antigravity
Clone the repo
git clone --depth 1 https://github.com/Dannykkh/skill-olympus

Made for: Claude Code.

Or install skill-olympus, the plugin that ships this one along with the rest of its 98 skills, 7 commands, 42 agents, 5 MCP servers.

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 antigravity

README.md
[![agentmods](https://agentmods.dev/badge/skills/dannykkh/skill-olympus/antigravity/github.svg)](https://agentmods.dev/skills/dannykkh/skill-olympus/antigravity)
Your own site
<a href="https://agentmods.dev/skills/dannykkh/skill-olympus/antigravity"><img src="https://agentmods.dev/badge/skills/dannykkh/skill-olympus/antigravity/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 antigravity

Your own site · 80×15
<a href="https://agentmods.dev/skills/dannykkh/skill-olympus/antigravity"><img src="https://agentmods.dev/badge/skills/dannykkh/skill-olympus/antigravity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 500 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 $0.00054 $0.00500
Opus 5 $0.00027 $0.00250
Sonnet 5 $0.00011 $0.00100
Haiku 4.5 $0.00005 $0.00050

Measured 7d ago against content hash 4e56583aa5f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 7d 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/antigravity/SKILL.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Antigravity CLI

Google Antigravity CLI is the Google command-line runtime. Gemini remains a model family; do not invoke the retired gemini executable.

Workflow

  1. Verify the runtime with agy --version. If it is unavailable, report that Antigravity CLI must be installed or repaired; do not fall back to gemini.
  2. Run agy models when model choice matters. Use a currently listed model and never hardcode a preview model from memory.
  3. Give Antigravity a bounded prompt that names the files, question, required evidence, and output format.
  4. Prefer read-only review. Grant write or command permissions only when the user asked Antigravity to modify or execute something.
  5. Capture the result, verify actionable claims against the repository or tests, and distinguish Antigravity findings from confirmed facts.

Headless usage

agy -p "Review the authentication flow. Cite file:line evidence and list only actionable findings." --output-format json

Optional controls:

  • --model <id>: choose an ID returned by agy models.
  • --effort <level>: tune reasoning effort when supported by the selected model.
  • --output-format text|json|stream-json: select machine-readable output for automation.
  • --continue or --conversation <id>: resume an existing Antigravity conversation.

Use a timeout supplied by the host runner for background jobs. Never use obsolete Gemini CLI flags such as --approval-mode, --sandbox, --yolo, or -i.

Permission boundary

Use Antigravity's configured permission policy for routine automation. --dangerously-skip-permissions bypasses safety prompts and is allowed only when the user explicitly authorized unrestricted tool execution for that run. A request for review or analysis alone is not that authorization.

Result contract

Return:

  • the model ID used, when explicitly selected;
  • the useful findings or recommendation;
  • which claims were independently verified;
  • any timeout, authentication, permission, or parse failure.

Read the full file on GitHub · 47 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. 7d ago First seen · 47 lines · 54 tokens per session scan A 4e56583aa5f7

Subscribe to this mod's changes

antigravity is a skill published in the GitHub repository Dannykkh/skill-olympus (5 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 500 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.

Related

Other skills, from other repositories

project-audit

Repository audit for non-website projects (CLI, libs, backend, monorepo). Use when: "project-audit", "project audit", "repo audit", "code audit".

claude-hangar/claude-hangar · 42 tokens

adversarial-review

Critical review (min. 5 findings). Modes: code, audit, plan. Use when: "review", "critical review", "code review", "plan review", "audit review".

claude-hangar/claude-hangar · 44 tokens

inline-review

Quick self-review checklist after code changes. Lightweight alternative to adversarial-review. Use when: "review my changes", "self-review", "quick review", "check my work", or automatically after significant edits.

claude-hangar/claude-hangar · 45 tokens

review-team

Launch parallel code review agents for comprehensive multi-perspective review. Use when: "review team", "full review", "multi-review", "review-team".

claude-hangar/claude-hangar · 34 tokens

factory-ci

CI and pull-request review conventions. One canonical .github/workflows/ci.yml is the merge gate (typecheck, lint, test, build, claude-review); branch protection's required-checks list matches the job list 1:1; anthropics/claude-code-action@v1 reviews every PR against the factory-pitfalls.md checklist as a required…

nonlinear-xyz/factory-kit · 110 tokens

factory-code-reviewer

Use to review a PR, diff, or recently-written code against the factory's conventions. Read-only — outputs structured review, not diffs. Carries the full factory-pitfalls digest as a PR checklist plus the conventions from every other factory-.md skill. Flags anti-patterns, missing conventions, security risks, and…

nonlinear-xyz/factory-kit · 96 tokens