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 PURPLE-ORCA/skills --skill antigravitygit clone --depth 1 https://github.com/PURPLE-ORCA/skillsWrote 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/purple-orca/skills/antigravity)<a href="https://agentmods.dev/skills/purple-orca/skills/antigravity"><img src="https://agentmods.dev/badge/skills/purple-orca/skills/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/purple-orca/skills/antigravity"><img src="https://agentmods.dev/badge/skills/purple-orca/skills/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 | $0.00052 | $0.03672 |
| Opus 5 | $0.00026 | $0.01836 |
| Sonnet 5 | $0.00010 | $0.00734 |
| Haiku 4.5 | $0.00005 | $0.00367 |
Grade A, and why
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.
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 — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Antigravity CLI
Delegate coding tasks to Antigravity CLI (agy) via the Hermes terminal. Antigravity is Google's terminal-based autonomous coding agent (rebranded from Gemini CLI, May 2026). Uses Gemini 3.5 Flash by default on Google AI Pro.
Workflow: Hermes Orchestrates, Antigravity Codes
Same pattern as Codex — Hermes handles orchestration, planning, and context. Antigravity does the actual coding.
Key rules:
- Delegate coding to Antigravity — when the user asks to build/code/debug/fix, route through
agyfirst. Do NOT code directly in the main session. - Prompt narrowly — scope each
agy -pto one focused slice so results are verifiable. - Inspect and report — after Antigravity finishes, verify the diff and report results.
- Don't stall — if Antigravity blocks, finish the slice with direct tools and note the limitation.
When to Use Antigravity Over Codex
- User explicitly asks for Antigravity/Google/Gemini
- You want Google's Gemini models instead
- You want built-in checkpointing (
/restore) before file changes - You want sandboxing via macOS Seatbelt (lightweight, no Docker needed)
- You want Plan Mode (read-only research before implementation)
- Parallel work — run Antigravity alongside Codex for batch tasks
Prerequisites
agyinstalled and authenticated (agyin terminal, Google OAuth)- Must run inside a project directory (agy auto-detects project root)
- Google AI Pro subscription (already configured)
One-Shot Tasks (Headless Mode)
The -p flag runs non-interactively and prints the response:
terminal(command="agy -p 'Add dark mode toggle to settings'", workdir="~/project", timeout=300)
For longer tasks, use a generous timeout:
terminal(command="agy -p 'Refactor the auth module to use JWT'", workdir="~/project", timeout=600)
Background Mode (Long Tasks)
# Start in background
terminal(command="agy -p 'Refactor the auth module'", workdir="~/project", background=true, timeout=600)
# Monitor progress
process(action="poll", session_id="<id>")
process(action="log", session_id="<id>")
# Kill if needed
process(action="kill", session_id="<id>")
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 · 325 lines · 52 tokens per session scan A 370bc288186f
antigravity is a skill published in the GitHub repository PURPLE-ORCA/skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 3,672 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…