A command that sends a prompt directly to Antigravity CLI, a Google terminal tool for coding agents. It supports choosing a model, setting a sandbox level, waiting or running in the background, and continuing a previous conversation.

Use it to delegate a prompt, select an Antigravity model, restrict file access, run asynchronously, or resume an earlier delegation.

It provides a controlled way to hand work from Claude to Antigravity while tracking the delegated job.

agy — Command by xiaolai

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 commands/xiaolai/cc-suite/agy

Clone the repo

git clone --depth 1 https://github.com/xiaolai/cc-suite

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 585 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.

Model	Per session	Once invoked
Fable 5	$0.00016	$0.00585
Opus 5	$0.00008	$0.00293
Sonnet 5	$0.00003	$0.00117
Haiku 4.5	$0.00002	$0.00059

Measured 2d ago against content hash 6331c3be3064, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agy 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 2d 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.

commands/agy.md · 73 lines

What it actually says

/cc-suite:agy

Send a prompt to Antigravity CLI (agy) through the cc-suite runner. This is the direct Claude → agy delegation surface; it is separate from Codex-backed audit and implementation commands.

User Input

$ARGUMENTS

Workflow

Step 1: Parse the request

Extract these optional flags from $ARGUMENTS and leave the remaining text as the prompt:

--model <name> — pass the complete model display name, including effort suffixes such as Gemini 3.1 Pro (High)
--sandbox <read-only|workspace-write|danger-full-access> — default read-only
--background or --wait — default --wait
--resume <conversation-id> — continue a prior agy conversation

If the prompt is empty, ask the user what they want agy to do and stop if they do not provide one.

Step 2: Choose a model when needed

If --model was omitted, run:

bash "${CLAUDE_PLUGIN_ROOT}/scripts/agy-preflight.sh"

If preflight returns an error, report its error and error_code and stop. Otherwise use default_model. Do not ask for a reasoning-effort setting: agy encodes effort in the model display name.

Step 3: Run the request

Follow commands/shared/agy-call.md and invoke:

node "${CLAUDE_PLUGIN_ROOT}/scripts/agy-runner.mjs" \
  --kind agy \
  --model "{chosen_model}" \
  --sandbox {chosen_sandbox} \
  --timeout-ms 900000 \
  {--background if selected} \
  {--resume "{conversation_id}" if selected} \
  --summary "agy: {short prompt summary}" \
  -- "{prompt}"

Parse the single JSON object from stdout. For a foreground call, display rawOutput, jobId, status, and threadId. For a background call, return the queued jobId and tell the user to use /cc-suite:status, /cc-suite:result, or /cc-suite:cancel.

On failed or stalled, report the error and job id. Do not retry the same request automatically; the runner has already recorded the diagnostic log.

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.

2d ago First seen · 73 lines · 16 tokens per session scan A 6331c3be3064

Subscribe to this mod's changes

agy is a command published in the GitHub repository xiaolai/cc-suite (44 stars, last pushed 24d ago), licensed ISC. It adds 16 tokens to every session and 585 once invoked, about $0.0001 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.

Building agents

agy

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

/cc-suite:agy

User Input

Workflow

Step 1: Parse the request

Step 2: Choose a model when needed

Step 3: Run the request

What this file has done since we first saw it

Other commands, from other repositories

claude-flow-swarm

bootstrap

ox-session-review

add-agent

handoff

xdo