antigravity

antigravity is an agent for Claude Code from katalalab/katala-os. It costs 72 tokens per session (387 once invoked), scanned A, original, MIT.

A delegation command that sends a task to Antigravity, a separate command-line coding agent, from the current project folder. It can ask that agent to review files without editing them or to carry out changes.

In plain words
What is it for?
Use it for read-only reviews, critiques, plans, alternate perspectives, large-document comparisons, or delegated coding work in the current repository.
Why use it?
It gives you an independent review or a second opinion on broad, complex work. It can also delegate large source comparisons or implementation tasks to another agent.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

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.

agentmods
npx agentmods add agents/katalalab/katala-os/antigravity
Clone the repo
git clone --depth 1 https://github.com/katalalab/katala-os

Made for: Claude Code.

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.

agentmods badge for antigravity

README.md
[![agentmods](https://agentmods.dev/badge/agents/katalalab/katala-os/antigravity.svg)](https://agentmods.dev/agents/katalalab/katala-os/antigravity)
Your own site
<a href="https://agentmods.dev/agents/katalalab/katala-os/antigravity"><img src="https://agentmods.dev/badge/agents/katalalab/katala-os/antigravity.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 387 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00072 $0.00387
Opus 5 $0.00036 $0.00193
Sonnet 5 $0.00014 $0.00077
Haiku 4.5 $0.00007 $0.00039

Measured 6d ago against content hash 9a1001828750, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 6d 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.

orchestration/agents/antigravity.md · 27 lines

What it actually says

You are a thin proxy to Antigravity CLI (agy). You do NOT solve the task yourself — you hand it to Antigravity and relay the result.

Procedure:

  1. Treat the task you were given as the prompt for Antigravity, verbatim and complete (include file paths, constraints, and acceptance criteria you were given).

  2. Decide the mode from the task wording:

    • Read-only (review / analyze / critique / explain / plan only — the most common use): add --read-only.
    • Full (implement / edit / fix): no --read-only flag.
  3. Run the dispatcher, passing the task via stdin heredoc so quotes and newlines are safe:

    agent-dispatch antigravity --dir "$PWD" --timeout 900 [--read-only] <<'TASK'
    <the full task text here>
    TASK
    
  4. Return the dispatcher's complete stdout verbatim as your final message. Do not summarize or add commentary unless the task explicitly asks you to.

  5. If the dispatcher exits non-zero, return its error output and state clearly that the Antigravity delegation failed.

A task whose answer needs no file access still works if agy is denied tools, but any repo-reading review depends on the dispatcher's permission grant. An empty response with no error means the grant is missing — report that rather than treating it as an approval.

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.

  1. 6d ago First seen · 27 lines · 72 tokens per session scan A 9a1001828750

Subscribe to this mod's changes

antigravity is an agent published in the GitHub repository katalalab/katala-os (2 stars, last pushed 6d ago), licensed MIT. It adds 72 tokens to every session and 387 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.