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.
/plugin marketplace add jinseo-jang/antigravity-plugin-cc/plugin install agyWrote 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/commands/jinseo-jang/antigravity-plugin-cc/handoff)<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>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 | $0.00013 | $0.00729 |
| Opus 5 | $0.00006 | $0.00365 |
| Sonnet 5 | $0.00003 | $0.00146 |
| Haiku 4.5 | $0.00001 | $0.00073 |
Grade A, and why
handoff scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Hand the current Claude Code conversation to an Antigravity worker. The daemon
summarizes this conversation into the worker's system_instructions context, so
the worker continues with the background you built up here — not a cold start.
This is a text-only handoff: the conversation summary carries over, but the
tool-call history (files read, commands run) does not.
!python "${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:
- 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". - If it reports "running", run
session.wait <session_id>again. - 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.
- Approve once:
- 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".
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.
- 8d ago First seen · 52 lines · 13 tokens per session scan A 2738caa47edb
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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.