collaborating-with-antigravity

collaborating-with-antigravity is a skill for Claude Code, Codex from Boulea7/agy-mcp. It costs 71 tokens per session (869 once invoked), scanned A, original, MIT.

A bridge for delegating development questions and tasks to Google Antigravity or Gemini through a JSON-based wrapper. It can run reviews, isolated prototypes, or long-running agent sessions and return structured results.

In plain words
What is it for?
Use it to ask about code, review changes, prototype in a separate worktree, run sandboxed commands, or start and monitor a detached agent loop.
Why use it?
A separate agent can provide a second opinion, handle a lengthy investigation, or work in an isolated copy of the project. This keeps the main session from being blocked or exposed to unnecessary changes.

Skill for Claude CodeCodex

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 skills/boulea7/agy-mcp/codex
Any agent
npx skills add Boulea7/agy-mcp --skill codex
Clone the repo
git clone --depth 1 https://github.com/Boulea7/agy-mcp

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.

agentmods badge for collaborating-with-antigravity

README.md
[![agentmods](https://agentmods.dev/badge/skills/boulea7/agy-mcp/codex.svg)](https://agentmods.dev/skills/boulea7/agy-mcp/codex)
Your own site
<a href="https://agentmods.dev/skills/boulea7/agy-mcp/codex"><img src="https://agentmods.dev/badge/skills/boulea7/agy-mcp/codex.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 869 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 $0.00071 $0.00869
Opus 5 $0.00036 $0.00434
Sonnet 5 $0.00014 $0.00174
Haiku 4.5 $0.00007 $0.00087

Measured 4d ago against content hash e79b2a5b9990, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

collaborating-with-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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/agy_bridge.py), 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.

src/agy_mcp/_skill_bodies/codex/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Collaborating with Antigravity (Codex edition)

agy-bridge is a thin JSON wrapper around the Google Antigravity (agy) CLI plus a gemini CLI fallback. The bridge returns stable BridgeResponse envelopes designed to drop cleanly into Codex's exec-json protocol via --output-protocol codex.

When to use

  • You want a second opinion from Antigravity / Gemini on a tricky bug, design call, or code review.
  • You want to prototype a change in an isolated worktree before touching the main checkout.
  • You want a long-running agent loop to run in the background while Codex continues other work.

Avoid for trivial single-step questions — the round-trip is overkill.

Quick start

python scripts/agy_bridge.py \
  --cd "/path/to/project" \
  --PROMPT "Find every place that calls db.commit() without a try/except." \
  --mode review \
  --output-protocol codex

The bridge prints one JSON line on stdout: {"success": true, "SESSION_ID": "…", "agent_messages": "…", "adapter": {…}}. With --output-protocol codex the event log conforms to Codex exec-json (thread.started, item.completed, turn.completed).

Modes

Mode Use it for Worktree Writes
ask (default) Q&A, code reading no no
plan Multi-step planning no no
prototype Diff-only suggestions optional no
review Critique a staged change no no
execute Apply edits in a worktree yes requires --allow-write
browser Research with browsing no no
long Detached agent loop no varies

Multi-turn

Capture and reuse SESSION_ID:

# Turn 1
python scripts/agy_bridge.py --cd /proj --PROMPT "Find race conditions in src/queue/"
# → {"SESSION_ID": "abc-123", ...}

# Turn 2
python scripts/agy_bridge.py --cd /proj --SESSION_ID abc-123 \
  --PROMPT "Propose a minimal fix for the worst one."

Detached long jobs

Codex projects that run long agent loops should prefer the MCP tool surface (agy_start / agy_status / agy_result / agy_read / agy_cancel / agy_sessions) over polling the CLI in a shell loop. The supervisor handles worker thread lifecycle, log spooling, and cross-platform process-group cleanup.

Read the full file on GitHub · 95 lines

Files

What ships with it

4 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.

  1. 4d ago First seen · 95 lines · 71 tokens per session scan A e79b2a5b9990

Subscribe to this mod's changes

collaborating-with-antigravity is a skill published in the GitHub repository Boulea7/agy-mcp (22 stars, last pushed 22d ago), licensed MIT. It adds 71 tokens to every session and 869 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 2026-08-30.