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.
npx skills add ZorIgn/sub-antigravity --skill delegate-to-antigravitygit clone --depth 1 https://github.com/ZorIgn/sub-antigravityWrote 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.
[](https://agentmods.dev/skills/zorign/sub-antigravity/delegate-to-antigravity)<a href="https://agentmods.dev/skills/zorign/sub-antigravity/delegate-to-antigravity"><img src="https://agentmods.dev/badge/skills/zorign/sub-antigravity/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.
<a href="https://agentmods.dev/skills/zorign/sub-antigravity/delegate-to-antigravity"><img src="https://agentmods.dev/badge/skills/zorign/sub-antigravity/delegate-to-antigravity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00062 | $0.00711 |
| Opus 5 | $0.00031 | $0.00356 |
| Sonnet 5 | $0.00012 | $0.00142 |
| Haiku 4.5 | $0.00006 | $0.00071 |
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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delegate to Antigravity
Keep the current harness as the coordinator. Send the actual work directly to the local AGY runtime. Delegate before doing the expensive work yourself when the user wants to save host tokens.
Choose the available entry
- If this harness has
antigravity_delegate, call it directly. Tool names may have an MCP server prefix. - Otherwise use this harness's terminal to run
sub-antigravity direct. If not on PATH, useuvx --from git+https://github.com/ZorIgn/sub-antigravity sub-antigravity direct. - Do not launch Hermes, Codex, Claude Code, or another model-driven harness as a relay. MCP and the CLI use the same AGY runner.
Give AGY a complete task
Pass the user's goal, absolute cwd, relevant file paths, and intended output. Preserve their exclusions: a writing task does not imply running tests or auditing code. Refer to existing local files rather than copying them into the host's context.
For edits, use allow_edits=true (CLI --edit) and name the allowed files. Do not edit those files concurrently. Tool permissions are auto-approved by default within the authorized task; the user need not separately approve every AGY read. cwd and plan mode are not filesystem confinement. Use dangerously_skip_permissions=false (CLI --configured-permissions) if the user requests AGY's configured permissions; do not retry a denial with more privileges against that request.
Keep the automatic Gemini selection unless the user asks for a specific available Gemini. The runner discovers the latest Flash and uses high effort.
Receive the actual deliverable
- File edits: ask AGY to save the work in the named files and return a brief description. Wait with
antigravity_job(action="wait", detail="compact"); show the resulting files to the user. - Text output: ask for the actual text in the desired format. Use
detail="response"for the full response, or consumeresponse_pathdirectly from disk. A truncated preview is not the final article. - CLI:
--prompt-fileor--stdinaccepts long/multiline input.--outputsaves the complete answer and prints only its path and metadata, reducing host context usage.
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.
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.
- 4d ago Changed · +7 lines · -11 tokens per session a24c66ed1bfb
- 5d ago Changed · +3 lines a61332cf4a2a
- 9d ago First seen · 28 lines · 73 tokens per session scan A 0b50143c74ad
delegate-to-antigravity is a skill published in the GitHub repository ZorIgn/sub-antigravity (0 stars, last pushed 5d ago), licensed MIT. It adds 62 tokens to every session and 711 once invoked, about $0.0003 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
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…