antigravity

antigravity is a skill for Claude Code from yuting0624/antigravity-for-claude-code. It costs 199 tokens per session (9,296 once invoked), scanned B, original, MIT.

A workflow that lets Claude Code delegate well-defined development tasks to Gemini through the Antigravity command-line tool. Claude remains responsible for requirements, architecture, difficult decisions, verification, and final review.

In plain words
What is it for?
Use it to delegate tasks such as generating tests, editing files, running terminal work, using subagents, or handling larger work split into smaller units.
Why use it?
It separates judgement-heavy work from repetitive or clearly specified work, while providing a second AI model for execution and review.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; positional $N argument; mentions Claude Code.

Part of the antigravity plugin — 2 skills, 10 commands, 1 agent, 2 hooks shipped together

Good fit Use it to delegate tasks such as generating tests, editing files, running terminal work, using subagents, or handling larger work split into smaller units.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yuting0624/antigravity-for-claude-code/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 yuting0624/antigravity-for-claude-code --skill antigravity
Clone the repo
git clone --depth 1 https://github.com/yuting0624/antigravity-for-claude-code

Made for: Claude Code.

Or install antigravity, the plugin that ships this one along with the rest of its 2 skills, 10 commands, 1 agent, 2 hooks.

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/yuting0624/antigravity-for-claude-code/antigravity.svg)](https://agentmods.dev/skills/yuting0624/antigravity-for-claude-code/antigravity)
Your own site
<a href="https://agentmods.dev/skills/yuting0624/antigravity-for-claude-code/antigravity"><img src="https://agentmods.dev/badge/skills/yuting0624/antigravity-for-claude-code/antigravity.svg" alt="Measured on agentmods" height="20"></a>
Per session 199 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,296 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 5 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Agent Snooping · line 401
    Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.
    Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
  • medium Excessive Agency · line 109
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 234
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Rogue Agent · line 111
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 220
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
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 $0.00199 $0.09296
Opus 5 $0.00100 $0.04648
Sonnet 5 $0.00040 $0.01859
Haiku 4.5 $0.00020 $0.00930

Measured 4d ago against content hash 05878f7d06c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

antigravity scanned grade B with 2 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 4d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

`<workspace>/.agents/agents/*.md` and global `~/.gemini/config/agents/`.)

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- `--sandbox` is NOT execution containment. Measured on macOS with agy 1.1.19: with `--yolo`, `--sandbox` changed nothing — a write to an absolute path OUTSIDE `--dir` succeeded (rc 0), `id` ran and returned a real uid,
skills/antigravity/SKILL.md · 524 lines

How it starts

The opening of the file, as written. The whole thing — 524 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Antigravity for Claude Code — hybrid SDLC

Run the Antigravity CLI (agy, Gemini) as a second AI working alongside Claude Code. The organizing idea is intelligent model routing across the SDLC: keep judgement-heavy work on Claude (the frontier model) and route deterministic, high-volume work to Antigravity (cheaper, faster Gemini). Two AIs, one workflow.

  • Claude = conductor / orchestrator — requirements, architecture, the hard 20% (edge cases, integration, correctness), specs, tests/evals, final review.
  • Antigravity = delegated agent — a full terminal agent (file edits, terminal, subagents, MCP, web/Vertex AI Search) that executes well-specified work.

This is agentic engineering, not vibe coding: the value is the structure around the model — routing, shared rules, verification gates — not raw generation. Generation is solved; verification, judgement, and direction are the craft.

Two modes (pick per task)

  • Conductor (sync, inline): you're shaping something in real time; delegate a small, well-scoped chunk to agy mid-flow (e.g. "generate these tests"), use the result immediately.
  • Orchestrator (async, multi-unit): decompose a larger task into units, dispatch to agy (often with --dir, agentic, in parallel), then review and integrate. Best for migrations, bulk implementation against patterns, test suites.

Division of labor across the SDLC

Route each phase to the right model. This is the core policy.

SDLC phase Owner Why
Requirements & planning Claude ambiguity, human-paced judgement
Design & architecture Claude trade-offs; most human-centric
Implementation — complex / architecture-bearing (the 20%) Claude correctness, deep context
Implementation — scaffolding / boilerplate / well-specified agy deterministic, high volume
Test & eval generation agy (Claude defines the contract) cheaper-model territory
First-pass code review agyClaude final AI as first-pass reviewer
Cross-model verification (output + trajectory) both two model families ≠ same failure
Maintenance / migration / modernization agy executes, Claude directs tedious, systematic
Web / Vertex AI Search agyClaude re-checks tools Claude lacks natively
Audio / video understanding agy transcribes + digests · Claude verifies Gemini is natively multimodal; no local ffmpeg/speech stack
Deep research (multi-source) agy fans out search/fetch · Claude plans, verifies ≥2 sources, synthesizes offload bulky pages to cheap Gemini; frontier model judges

Read the full file on GitHub · 524 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. 4d ago Changed · +10 lines 05878f7d06c8
  2. 8d ago First seen · 514 lines · 199 tokens per session scan B 5f1c54b14ba7

Subscribe to this mod's changes

antigravity is a skill published in the GitHub repository yuting0624/antigravity-for-claude-code (315 stars, last pushed yesterday), licensed MIT. It adds 199 tokens to every session and 9,296 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

build-user-persona

Build evidence-backed user personas from research inputs. Creates structured persona documents grounded in evidence, with each attribute clearly labeled as research-validated or inferred. Use this skill when you need personas for an FR, strategy doc, or design brief. Trigger on: "build a persona", "create user…

felipecabargas/gambit · 105 tokens

competitive-analysis

Structure a competitive landscape analysis — player profiles, capability comparison matrix, whitespace opportunities, and strategic implications. Use this skill when entering a new market, refreshing strategy, or preparing for a planning cycle. Trigger on: "do a competitive analysis", "who are our competitors"…

felipecabargas/gambit · 100 tokens

write-product-strategy

Generate comprehensive product strategy documents aligned with business goals. Use this when defining or updating your product's strategic direction, aligning teams on where to play and how to win, or creating a STRATEGY.md that bridges vision and execution. Triggers include: clarifying product strategy, articulating…

felipecabargas/gambit · 120 tokens

synthesize-user-research

Synthesize raw user research (interview notes, survey results, support tickets, NPS verbatims) into structured insights: themes, pain points, jobs-to-be-done, and research gaps. Use this skill when you need to make sense of qualitative research data before writing a feature request or building personas. Trigger on…

felipecabargas/gambit · 126 tokens

write-feature-request

Guided Feature Request (FR) authoring. Assists the user in writing a high-quality FR by collecting structured inputs (problem, solution, outcomes, requirements), then auto-generates Acceptance Criteria for every requirement. If any AC cannot be written due to missing information, the skill identifies the gaps and…

felipecabargas/gambit · 150 tokens

write-okrs

Generate well-structured OKRs from a product strategy. Derives Objectives and Key Results from strategy pillars, challenges vague KRs, distinguishes outputs from outcomes, and links each OKR back to the strategy pillar it serves. Trigger on: "write our OKRs", "help me set OKRs for this quarter", "turn this strategy…

felipecabargas/gambit · 103 tokens