markfulton/claude-antigravity-agents: AI tool

Score7.8

Popularity1.0

Riskconditional

TierSilver

Score breakdown

Usefulness8.0

Novelty8.0

Momentum7.0

Maturity5.7

Open-source/build8.4

Evidence7.2

Workflow potential9.3

Setup ease8.8

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for Claude Code users, AI coding agent developers, automation builders, AI-curious readers, engineering teams using Claude Code for production workloads, and any developer wiring Claude Code to delegate heavy jobs (full-repo audits, big refactors, research sweeps) to a Google Antigravity CLI sub-agent that runs in the background -- and who can pair markfulton/claude-antigravity-agents with

Who should use it

Claude Code users, AI coding agent developers, automation builders, AI-curious readers, engineering teams using Claude Code for production workloads, and any developer wiring Claude Code to delegate heavy jobs to a Google Antigravity CLI sub-agent -- and who can pair markfulton/claude-antigravity-agents with Claude Code for the orchestrator surface, Google Antigravity CLI (agy) for the sub-agent surface, the antigravity-agents/SKILL.md file for the skill surface, the safety model for the isolation surface, the preflight probe for the auth surface, and a target use case (architecture review, dependency audit, big refactor, research sweep, second opinion from a different model) for the eval surfaceClaude Code users + engineering teams that want the orchestrator pattern (writes a self-contained brief, launches an agy -p '<task>' job in the background, keeps working, then collects and verifies the result before trusting a line of it) -- the right durable, opt-in delegation primitive for any Claude Code user who has been watching the agent context fill up with audit outputClaude Code users + engineering teams that want the safety model (an Antigravity job never writes to the same files Claude Code is editing at that moment; read-only jobs in a sandbox with --sandbox, write jobs in an isolated git worktree) -- the right isolation primitive for any Claude Code user who has been burned by a sub-agent clobbering their editsClaude Code users + engineering teams that want the broaden-your-model-choice angle (Gemini or whatever Antigravity offers for an independent second opinion) -- the right model-coverage primitive for any Claude Code user who has been paying Claude prices for a perspective a different model would have given cheaperClaude Code users + engineering teams that want the work-in-parallel angle (fan out several sub-agent jobs at once) -- the right throughput primitive for any Claude Code user who has been waiting for one job to finish before starting the next

Who should skip it

Skip markfulton/claude-antigravity-agents if the source repository or demo is inactive, unmaintained, or no longer matches the description shown here.

About this signal

markfulton/claude-antigravity-agents is tracked by RepoRadar as a mit claude code skill that deleg in the Antigravity Agents: Claude Code Skill for Google section. It was first seen on 2026-07-07 and last updated on 2026-07-07. The current verdict is 'try now' with a Silver tier and easy setup difficulty. Across RepoRadar's eight signals, markfulton/claude-antigravity-agents is strongest on workflow potential (9.3) and setup ease (8.8) and weakest on maturity (5.7) — a profile worth weighing against your own priorities. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.

How this item is evaluated

RepoRadar assigned markfulton/claude-antigravity-agents a composite score of 7.8 out of 10, placing it in the Silver tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 1.0 and never affects the composite score or tier. The risk label of 'conditional' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.

Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.

Risk explanation

The 66* / 22-fork repo is at active maintenance but the star count is moderate -- the project is real; runnable; and well-documented but new; the install requires Claude Code + Google Antigravity CLI (agy) + the antigravity-agents/SKILL.md file -- the consumer SHOULD install the Antigravity CLI and complete the Google OAuth sign-in before adopting.

Evidence links

github.com

Closest alternatives / related signals

open-sourcemitclaude-antigravity-agentsmarkfultonclaude-code-skillantigravity-cliagygoogle-antigravity