handoff

handoff is a command for Claude Code from jinseo-jang/antigravity-plugin-cc. It costs 13 tokens per session (729 once invoked), scanned A, original, Apache-2.0.

A command that hands the current coding conversation to an Antigravity worker, another agent that can continue the task. It passes along a summary of the conversation so the worker can pick up the context.

In plain words
What is it for?
Use it to delegate the current task to an Antigravity worker, start a background handoff, or obtain the worker’s session status and events later.
Why use it?
A long or specialized task may be better continued by a separate worker, but transferring the relevant background manually takes time. This provides a handoff and can either monitor the worker or leave it running in the background.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the agy plugin — 11 commands, 2 hooks shipped together

Good fit Use it to delegate the current task to an Antigravity worker, start a background handoff, or obtain the worker’s session status and events later.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add jinseo-jang/antigravity-plugin-cc
Claude Code
/plugin install agy

Made for: Claude Code.

Or install agy, the plugin that ships this one along with the rest of its 11 commands, 2 hooks.

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 handoff

README.md
[![agentmods](https://agentmods.dev/badge/commands/jinseo-jang/antigravity-plugin-cc/handoff.svg)](https://agentmods.dev/commands/jinseo-jang/antigravity-plugin-cc/handoff)
Your own site
<a href="https://agentmods.dev/commands/jinseo-jang/antigravity-plugin-cc/handoff"><img src="https://agentmods.dev/badge/commands/jinseo-jang/antigravity-plugin-cc/handoff.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 729 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00013 $0.00729
Opus 5 $0.00006 $0.00365
Sonnet 5 $0.00003 $0.00146
Haiku 4.5 $0.00001 $0.00073

Measured 8d ago against content hash 2738caa47edb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

handoff 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 8d 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.

plugin/commands/handoff.md · 52 lines

What it actually says

Hand the current Claude Code conversation to an Antigravity worker. The daemon summarizes this conversation into the worker's system_instructions context, so the worker continues with the background you built up here — not a cold start. This is a text-only handoff: the conversation summary carries over, but the tool-call history (files read, commands run) does not.

!python "${CLAUDE_PLUGIN_ROOT}/scripts/cao-companion.py" --plugin-data "${CLAUDE_PLUGIN_DATA}" session.handoff "$ARGUMENTS"

The command above prints a JSON object with a session_id. Handoff sessions are writable (the worker does real work) and can request shell approvals.

--background starts the handoff detached and returns the session_id immediately, skipping the watch loop — use it when the handed-off work is large and you don't want to babysit it. Retrieve results later with /agy:status <id>, /agy:events <id>, or /agy:watch <id>.

Foreground (no --background): supervise the session until it finishes, using the Antigravity companion via the Bash tool:

  1. Watch: run python "${CLAUDE_PLUGIN_ROOT}/scripts/cao-companion.py" --plugin-data "${CLAUDE_PLUGIN_DATA}" session.wait <session_id>. It blocks up to ~25s and returns a pending approval, "running", or "finished".
  2. If it reports "running", run session.wait <session_id> again.
  3. If it reports a pending approval (a shell command needs a decision), call the AskUserQuestion tool showing the exact command, with four options: Approve once, Approve for this project, Approve always, and Deny. Then apply the user's choice by running the companion:
    • Approve once: ... cao-companion.py session.approve <call_id>
    • Approve for this project: ... cao-companion.py session.approve <call_id> project
    • Approve always: ... cao-companion.py session.approve <call_id> global
    • Deny: ... cao-companion.py session.deny <call_id> Then return to step 1.
  4. When it reports the session finished, run ... cao-companion.py session.events <session_id> and show the user the digest.

Never approve or deny on your own — the user decides every approval via AskUserQuestion.

Background (--background): do NOT watch. Print the returned session_id and the retrieval hints (/agy:status <id>, /agy:events <id>, /agy:watch <id>) and stop. Handoff sessions are writable, so if a non-allowlisted shell command is hit while unattended, the session suspends; /agy:status <id> prints the paste-ready /agy:approve <id> [project|global] line, and the 5-minute approval timeout auto-denies — for long unattended handoffs, pre-allowlist expected commands with "Approve for this project" / "Approve always".

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. 8d ago First seen · 52 lines · 13 tokens per session scan A 2738caa47edb

Subscribe to this mod's changes

handoff is a command published in the GitHub repository jinseo-jang/antigravity-plugin-cc (6 stars, last pushed 25d ago), licensed Apache-2.0. It adds 13 tokens to every session and 729 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 2026-08-31.