antigravity-cli

antigravity-cli is a skill for Claude Code from simplybychris/antigravity-plugin-cc. It costs 32 tokens per session (727 once invoked), scanned A, original, MIT.

A runtime guide for invoking the Antigravity command-line tool from an agy runner.

In plain words
What is it for?
It is for internal agy agents that need to run one Antigravity request through the wrapper script.
Why use it?
It defines how prompts, model choices, authentication, and command-line options are passed safely to the tool.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the agy plugin — 1 skill, 7 commands, 1 agent shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add simplybychris/antigravity-plugin-cc
Claude Code
/plugin install agy

Made for: Claude Code.

Or install agy, the plugin that ships this one along with the rest of its 1 skill, 7 commands, 1 agent.

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-cli

README.md
[![agentmods](https://agentmods.dev/badge/skills/simplybychris/antigravity-plugin-cc/antigravity-cli.svg)](https://agentmods.dev/skills/simplybychris/antigravity-plugin-cc/antigravity-cli)
Your own site
<a href="https://agentmods.dev/skills/simplybychris/antigravity-plugin-cc/antigravity-cli"><img src="https://agentmods.dev/badge/skills/simplybychris/antigravity-plugin-cc/antigravity-cli.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 727 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 5.1 $0.00032 $0.00727
Opus 5 $0.00016 $0.00364
Sonnet 5 $0.00006 $0.00145
Haiku 4.5 $0.00003 $0.00073

Measured 6d ago against content hash 1bcf818b98d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

antigravity-cli 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 6d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

plugins/agy/skills/antigravity-cli/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Antigravity CLI runtime

Use this skill only inside the agy subagent.

Primary helper

bash "${CLAUDE_PLUGIN_ROOT}/scripts/agy-run.sh" ask [--model <alias>] "<prompt>" [agy-flags...]

The wrapper:

  • Locates agy in PATH, ~/.local/bin, /opt/antigravity/bin, or /usr/local/bin.
  • Verifies auth (system keyring OAuth or ANTIGRAVITY_API_KEY).
  • Runs agy -p "<prompt>" non-interactively.
  • If --model <alias> is supplied before the prompt, resolves the alias and applies it for the duration of the call (atomic patch of ~/.gemini/antigravity-cli/settings.json under a lockfile, restored on exit).
  • Forwards any extra arguments after the prompt straight to agy — so … ask "<prompt>" --sandbox becomes agy -p "<prompt>" --sandbox.

Rules of engagement

One wrapper call per task. The subagent is a forwarder, not an orchestrator — keep the user's task text intact and let agy do the work.

Strip flags that belong to the parent slash command (--background) before forwarding. Pass --model <alias> to the wrapper (not to agy directly). Pass agy-native flags through after the prompt argument.

Model aliases (consumed by the wrapper)

flash-low, flash-medium (flash-med), flash (flash-high), pro-low, pro (pro-high), sonnet (claude-sonnet), opus (claude-opus), gpt-oss (gpt-oss-120b). Canonical TUI strings are also accepted verbatim (e.g. "Claude Opus 4.6 (Thinking)").

Run bash "${CLAUDE_PLUGIN_ROOT}/scripts/agy-run.sh" help for the authoritative list.

agy-native flags worth knowing

Run agy --help for the full list. Useful ones that go after the prompt argument:

  • --sandbox — extra-restrictive execution; only when the user asked for it.
  • --print-timeout 10m — extend the default 5min print timeout.
  • --add-dir <path> — add a directory to the workspace (repeatable).

What this skill does NOT do

  • Does not install or authenticate agy. That is /agy:setup's job.
  • Does not retry, summarize, or post-process agy's output.
  • Does not read files, run git, or make HTTP calls outside the wrapper.

Read the full file on GitHub · 73 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. 6d ago First seen · 73 lines · 32 tokens per session scan A 1bcf818b98d7

Subscribe to this mod's changes

antigravity-cli is a skill published in the GitHub repository simplybychris/antigravity-plugin-cc (75 stars, last pushed 3mo ago), licensed MIT. It adds 32 tokens to every session and 727 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.

Related

Other skills, from other repositories

collaborating-with-antigravity

Delegate analytical, sandboxed, or long-running work to the Google Antigravity (agy) CLI through a JSON-bridge wrapper. Use when you need a second opinion, want to isolate side effects in a worktree, or need to run a long agent loop without blocking the main conversation.

Boulea7/agy-mcp · 67 tokens

collaborating-with-antigravity

Delegate analytical, sandboxed, or long-running work to the Google Antigravity (agy) CLI via a JSON-bridge wrapper. Use when you need a second opinion, sandboxed execution, or a detached long-running agent loop. Install location is .agents/skills/collaborating-with-antigravity/.

Boulea7/agy-mcp · 71 tokens

crosstalk

Consult Antigravity (Gemini) from Claude Code without blocking, and route the answer to whichever of your sessions needs it. Use for wide-context reads a second model should carry (large codebase sweeps, long log or transcript analysis, broad web research), for a genuine second opinion on a design or a diagnosis, and…

obeskay/crosstalk · 143 tokens

gemini-3-prompting

Guidance for writing effective prompts for Antigravity (agy) / Gemini 3 models.

Vit129/agy-plugin-cc · 26 tokens

agy-result-handling

Internal guidance for presenting agy output back to the user.

Vit129/agy-plugin-cc · 16 tokens

agy-delegation

Use when analyzing large files (>200 lines), more than 3 files at once, deep git/grep searches, web lookups, or adversarial reviews - delegates to the Antigravity CLI via claude-agy-mcp MCP tools to save context.

PyModel/claude-agy-mcp · 57 tokens