review
Get an independent cross-model review of the current diff from Antigravity (Gemini), then reconcile as the final judge.
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/yuting0624/antigravity-for-claude-code/HEAD/commands/review.md -o ~/.claude/commands/review.mdreview.md
Use Antigravity (`agy` / Gemini) as an **independent, different-model reviewer** of the current changes, then reconcile the findings yourself (you are the final judge). Scope/flags: $ARGUMENTS Do this: 1. Capture the diff: `git diff` (or the range/paths in the scope above; default to uncommitted + last commit if unspecified). 2. Delegate the review to agy (pro tier) — pipe the diff in on stdin: `git diff | agy-delegate --tier pro -` (This runs as YOU, the conductor. The `antigravity-delegate` subagent cannot pipe — its PreToolUse gate refuses every pipeline since GHSA-hwv2-vjgj-8rcv, because `git` with arbitrary arguments executes arbitrary commands and `cat` feeding the wrapper ships any file to the external model. If you delegate this step, pass `--dir`.) with an instruction to find correctness/security/performance bugs, be skeptical, and list each as `file:line — issue`. If `--adversarial` is set, also have it challenge the design decisions and tradeoffs, not just line bugs. 3. **Reconcile**: for each finding, corroborate it against the actual code. Drop false positives; keep what's real. Agreement across two model families is a stronger signal; disagreement is a prompt to look closer. 4. Report the reconciled findings (most severe first) and your verdict.
Run the Antigravity CLI (Gemini) as a collaborating AI inside Claude Code, with intelligent model routing across the software development lifecycle. Claude is the conductor/orchestrator — requirements, architecture, the hard 20%, verification, and review — and routes deterministic, high-volume work (scaffolding, boilerplate, test generation, first-pass review, migrations, web/Vertex AI Search) to Antigravity (Gemini), the cheaper, faster model. Use when the user wants to "use Antigravity / agy", "vibe code / agentic engineering", "accelerate the SDLC", "delegate to Gemini", "scaffold / generate tests / migrate", "first-pass code review", "search web or internal/company data", "deep research / multi-source research report", "second-model cross-check", or "lower token cost on a big job". Claude always verifies Antigravity's output and re-checks itself if unsatisfied.
|
Cancel a running background Antigravity (agy) delegation job.
Diagnose a failing Cloud Run service — Antigravity (agy/Gemini) digests the error logs cheaply, Claude infers the root cause and proposes a fix. Read-only by default; --apply writes the fix to a branch.
Delegate a well-scoped subtask to Antigravity (agy/Gemini) under cost discipline, then verify.
Understand an audio / video / image file — Antigravity (agy/Gemini) transcribes and analyzes it, returning a timestamped digest while the full transcript goes to a file.
Migrate an existing Claude Code setup (skills, memory, CLAUDE.md, MCP, plugins, permissions) to the Antigravity CLI.
Move an existing Claude Code setup onto the Antigravity CLI (agy) — user skills, CLAUDE.md, auto-memory, MCP servers, installed plugins, permissions and trusted workspaces. Use when the user says "migrate to Antigravity", "move my Claude Code config to agy", "bring my skills/memory/MCP over", "set up agy like my Claude Code", "agy plugin import claude found nothing", or asks what can and cannot be carried across. Also use to explain the two config layouts, or to reverse a migration.