What is delegate-to-antigravity?

A procedure for sending a bounded coding, research, review, debugging, or implementation task to the local Google Antigravity command-line tool as a second agent.

Use it to check whether Antigravity is available, delegate a clearly defined task, review its response, inspect any workspace changes, and run tests independently.

It gives you another analysis or implementation result while keeping verification and responsibility with the main agent.

delegate-to-antigravity — Skill for Codex by IlleJiViN

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 IlleJiViN/codex-antigravity-subagent --skill delegate-to-antigravity

Clone the repo

git clone --depth 1 https://github.com/IlleJiViN/codex-antigravity-subagent

Made for: 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/illejivin/codex-antigravity-subagent/delegate-to-antigravity/github.svg)](https://agentmods.dev/skills/illejivin/codex-antigravity-subagent/delegate-to-antigravity)

Your own site

<a href="https://agentmods.dev/skills/illejivin/codex-antigravity-subagent/delegate-to-antigravity"><img src="https://agentmods.dev/badge/skills/illejivin/codex-antigravity-subagent/delegate-to-antigravity/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/illejivin/codex-antigravity-subagent/delegate-to-antigravity"><img src="https://agentmods.dev/badge/skills/illejivin/codex-antigravity-subagent/delegate-to-antigravity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 569 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	$0.00080	$0.00569
Opus 5	$0.00040	$0.00284
Sonnet 5	$0.00016	$0.00114
Haiku 4.5	$0.00008	$0.00057

Measured 10d ago against content hash 1ddbfc4be7a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

delegate-to-antigravity 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 10d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/agy-delegate.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/antigravity-subagent/skills/delegate-to-antigravity/SKILL.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Delegate to Antigravity

Treat Antigravity as an external delegated worker. It is not a native Codex collaboration agent: collect its output, verify it, and remain responsible for the final answer and workspace changes.

Workflow

Prefer the agy_check and agy_delegate MCP tools when they are available.
Otherwise use the bundled scripts/agy-delegate.mjs runner. It requires Node.js 20 or newer and a locally installed, authenticated agy CLI.
Establish availability with agy_check or node <skill-dir>/scripts/agy-delegate.mjs --check.
Make the task concrete and bounded. Include the goal, constraints, expected output, and relevant absolute paths.
Default to mode: plan. Use accept-edits only when the user requested implementation and authorized changes to that workspace.
Inspect Antigravity's response and the workspace diff. Run relevant tests independently when it made changes.
Report its contribution as delegated analysis, not independently verified fact.

Bundled runner

For the Skills-only path, write the complete prompt to a temporary UTF-8 file and pass its absolute path to the runner. Do not interpolate an untrusted prompt into shell syntax.

node <skill-dir>/scripts/agy-delegate.mjs --cwd <absolute-workspace> --mode plan --prompt-file <absolute-prompt-file>

Delete the temporary prompt file after the runner finishes. The runner accepts --output-format text|json, --timeout-seconds 1..1800, --agent, and --model. Do not add or emulate dangerous permission-bypass flags.

If neither the MCP tools nor local process execution is available, explain that this plugin requires a local Codex environment with Node.js and an authenticated agy installation.

Safety

Never weaken the user's persisted sandbox or permission policy.
Do not delegate secrets, credentials, private data, destructive operations, releases, deployments, purchases, or external messages without explicit authorization for that scope.
Use one invocation per independent task. Do not create recursive delegation loops or ask Antigravity to invoke Codex.
If authentication or interactive approval is required, return control to the user rather than bypassing it.
Use a finite timeoutSeconds; split oversized work into bounded tasks.

Read the full file on GitHub · 39 lines

Files

What ships with it

2 files 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.

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.

10d ago First seen · 39 lines · 80 tokens per session scan A 1ddbfc4be7a8

Subscribe to this mod's changes

delegate-to-antigravity is a skill published in the GitHub repository IlleJiViN/codex-antigravity-subagent (10 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 569 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 ai-agents antigravity codex developer-tools model-context-protocol

email-notification-expert

Expert guide for transactional email (Resend, Postmark, SES), React Email templates, in-app notifications, and unified communication pipelines / Panduan ahli untuk email transaksional (Resend, Postmark, SES), template React Email, notifikasi in-app, dan pipeline komunikasi terpadu.

roedyrustam/vibes-plug · 65 tokens

file-upload-media-expert

Expert guide for file uploads (S3, R2, Supabase Storage), presigned URLs, image/video processing, CDN optimization, and media pipeline architecture / Panduan ahli untuk upload file (S3, R2, Supabase Storage), presigned URL, pemrosesan gambar/video, optimasi CDN, dan arsitektur pipeline media.

roedyrustam/vibes-plug · 76 tokens

design-system-architect

Expert guide for designing, building, and maintaining scalable UI design systems with design tokens, headless primitives, Material Design 3 (M3), Tailwind v4 @theme, and WCAG 2.2 accessibility.

roedyrustam/vibes-plug · 50 tokens

firebase-security-expert

Firebase security expert to audit Security Rules (Firestore/Realtime Database/Storage), authentication, API keys, data leakage prevention, and App Check configuration / Ahli keamanan Firebase untuk audit Security Rules (Firestore/Realtime Database/Storage), autentikasi, API keys, pencegahan kebocoran data, dan…

roedyrustam/vibes-plug · 72 tokens

state-management-expert

Expert guide for modern client-side state management: Zustand, Jotai, Valtio, TanStack Store, Redux Toolkit, and server state patterns with TanStack Query / Panduan ahli untuk manajemen state client-side modern: Zustand, Jotai, Valtio, TanStack Store, Redux Toolkit, dan pola server state dengan TanStack Query.

roedyrustam/vibes-plug · 77 tokens

typescript-expert

Expert guide for TypeScript 5.8+ advanced type system, strict mode, generics, utility types, branded types, inferred type predicates, isolated declarations, and type-safe architectural patterns / Panduan ahli untuk sistem tipe TypeScript 5.8+, mode strict, generics, utility types, branded types, inferred type…

roedyrustam/vibes-plug · 83 tokens