A skill for sending reviews, adversarial reviews, setup checks, rescue tasks, status requests, and result lookups to the Antigravity CLI. Antigravity, or AGY, is a separate command-line service for these delegated tasks.

Delegating code reviews, stricter code reviews, bug-rescue tasks, setup checks, job status checks, result retrieval, and cancellations.

It gives the coding agent a defined way to ask AGY for another review, investigate a bounded problem, or check an existing job.

agy — Skill for Claude Code by iicmaster/antigravity-plugins

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 iicmaster/antigravity-plugins --skill agy

Clone the repo

git clone --depth 1 https://github.com/iicmaster/antigravity-plugins

Made for: Claude Code.

Or install agy, the plugin that ships this one along with the rest of its 5 skills, 7 commands, 1 agent, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/iicmaster/antigravity-plugins/agy/github.svg)](https://agentmods.dev/skills/iicmaster/antigravity-plugins/agy)

Your own site

<a href="https://agentmods.dev/skills/iicmaster/antigravity-plugins/agy"><img src="https://agentmods.dev/badge/skills/iicmaster/antigravity-plugins/agy/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/iicmaster/antigravity-plugins/agy"><img src="https://agentmods.dev/badge/skills/iicmaster/antigravity-plugins/agy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 630 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.

Model	Per session	Once invoked
Fable 5.1	$0.00037	$0.00630
Opus 5.5	$0.00015	$0.00252
Sonnet 5.5	$0.00007	$0.00126
Haiku 4.5	$0.00004	$0.00063

Measured 2mo ago against content hash a7484a19e4e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agy 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 2mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/agy-codex.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/agy/skills/agy/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGY

Use this skill when the user asks Codex to use agy, Antigravity, or AGY-backed review/rescue workflows.

Invocation Contract

Prefer the MCP tools exposed by this plugin when they are available:

agy_setup
agy_status
agy_result
agy_cancel
agy_review
agy_adversarial_review
agy_rescue

Use the script wrapper only as a fallback when MCP tools are not available.

Resolve commands relative to this skill directory. The wrapper script lives at:

node "<path-to-this-skill>/scripts/agy-codex.mjs" <command> "<raw arguments>"

Supported commands:

setup checks whether AGY 1.1.1 or newer is available with the required capabilities. Use setup --smoke or MCP agy_setup with smoke: true to run a minimal implicit-stdin completion check.
review sends current git status and diff to AGY for review.
adversarial-review sends current git status and diff to AGY for a stricter review.
rescue delegates a bounded task to AGY. The Codex MCP tool intentionally keeps AGY sandboxing on and does not expose dangerous permission-bypass flags.
status shows recent AGY jobs for the current workspace.
result <job-id> prints captured output for a job.
cancel <job-id> cancels a queued or running job.

Examples:

node "<path-to-this-skill>/scripts/agy-codex.mjs" setup
node "<path-to-this-skill>/scripts/agy-codex.mjs" review "--base main security focus"
node "<path-to-this-skill>/scripts/agy-codex.mjs" rescue "--background --timeout 30s investigate the failing test"
node "<path-to-this-skill>/scripts/agy-codex.mjs" status
node "<path-to-this-skill>/scripts/agy-codex.mjs" result "<job-id>"

Safety Rules

Do not use shell interpolation for user text. Pass raw arguments through the wrapper.
Do not pass sandbox-disable or dangerous permission-bypass flags through Codex MCP. They are intentionally unavailable there.
Prefer foreground mode for small bounded checks and background mode for long-running rescue work.
Use short timeouts for smoke tests; the companion runtime gives AGY --print-timeout a grace window before enforcing its own hard timeout.
Treat partial jobs as timed-out print-mode runs that still captured stdout.
Treat rescue as no-edit by default. File changes should happen only when the user explicitly asks for edits.
Return companion stdout/stderr faithfully and distinguish AGY output from Codex conclusions.

Read the full file on GitHub · 59 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

scripts/agy-codex.mjs 663 B runs code

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.

2mo ago First seen · 59 lines · 37 tokens per session scan A a7484a19e4e7

Subscribe to this mod's changes

agy is a skill published in the GitHub repository iicmaster/antigravity-plugins (7 stars, last pushed 9d ago), licensed MIT. It adds 37 tokens to every session and 630 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.

Building agents

agy next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agyiicmaster/antigravity-plugins	Skill	7	9d ago	MIT	A	37	Claude Code
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	2d ago	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	100k	today	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	315k	5d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code