A skill for delegating coding work to Google Antigravity CLI, a command-line tool that runs other AI agents. It explains how to launch these agents and why their results still need checking.

Use it when someone asks to use Antigravity, agy, or Gemini for a second opinion or delegated coding work. It covers headless runs, background execution, model selection, and verifying the returned work.

It lets a coding agent hand off longer or separate tasks while avoiding common command-line mistakes that can cause the wrong prompt to run or a task to stall.

use-agy — Skill for Claude Code and Codex by contains-studio

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 contains-studio/fable-delegator --skill use-agy

Clone the repo

git clone --depth 1 https://github.com/contains-studio/fable-delegator

Made for: Claude Code, Codex.

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/contains-studio/fable-delegator/use-agy.svg)](https://agentmods.dev/skills/contains-studio/fable-delegator/use-agy)

Your own site

<a href="https://agentmods.dev/skills/contains-studio/fable-delegator/use-agy"><img src="https://agentmods.dev/badge/skills/contains-studio/fable-delegator/use-agy.svg" alt="Measured on agentmods" height="20"></a>

Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,189 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	$0.00089	$0.01189
Opus 5	$0.00044	$0.00594
Sonnet 5	$0.00018	$0.00238
Haiku 4.5	$0.00009	$0.00119

Measured 8d ago against content hash 2a418e568015, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

use-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 8d 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.

skills/use-agy/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Antigravity (agy) Subagent Skill

Spawn autonomous Antigravity CLI (agy) subagents. Same delegation philosophy as use-codex / use-grok / use-cursor: subagents burn their own quota; the parent verifies and synthesizes. Agy is the Google-side bench slot (Gemini models) and also carries Claude models.

Canonical headless invocation

agy --dangerously-skip-permissions --model "<model>" --print-timeout 30m \
  -p "$(cat /path/to/prompt.md)"

Run in background (run_in_background: true) for anything non-trivial.

Flag gotchas (learned the hard way, agy 1.1.1)

The prompt is the VALUE of -p/--print, not a positional argument. agy -p --flag "prompt" silently consumes the next token (--flag) as the prompt and the model answers a greeting or nonsense while your real prompt is ignored — with exit 0. Always put -p "<prompt>" LAST. If the response looks like a generic greeting, this is why.
--dangerously-skip-permissions is the headless auto-approve (equivalent of grok's --always-approve, cursor's --force). Without it, tool calls prompt and headless runs stall.
--print-timeout defaults to only 5m — raise it (30m+) for implementation tasks or the run dies mid-task.
--model takes the display string with parentheses, e.g. --model "Gemini 3.1 Pro (High)" — quote it. List with agy models.
--mode plan = read-only planning mode (good for second opinions without write risk); --mode accept-edits auto-accepts edits.
--add-dir <path> (repeatable) to widen the workspace; -c/--continue resumes the latest conversation.

Model selection

No hard default — run agy models at invocation time and choose per task (match model cost to task difficulty). Example list from one verified install (2026-07; account-dependent), effort baked into the display name:

Gemini 3.5 Flash (Low/Medium/High) — cheap/fast tier (Low probe-verified headless, ~4s)
Gemini 3.1 Pro (Low/High) — Google frontier tier
Claude Sonnet 4.6 (Thinking) / Claude Opus 4.6 (Thinking) — Anthropic models (Opus probe-verified headless)
GPT-OSS 120B (Medium) — open-weights option

Read the full file on GitHub · 72 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.

8d ago First seen · 72 lines · 89 tokens per session scan A 2a418e568015

Subscribe to this mod's changes

use-agy is a skill published in the GitHub repository contains-studio/fable-delegator (13 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 1,189 once invoked, about $0.0004 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 2026-08-31.

Building agents

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens