rescue

rescue is a command for Claude Code from sakibsadmanshajib/antigravity-plugin. It costs 19 tokens per session (587 once invoked), scanned A, original, MIT.

A command that forwards a debugging, implementation, or investigation request to Google Antigravity.

In plain words
What is it for?
Delegating debugging, implementation, and deeper investigation, with options to wait, run in the background, or continue an earlier thread.
Why use it?
It gives you a single command for handing difficult coding work to Antigravity, either immediately or in the background.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents; 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 antigravity plugin — 1 skill, 6 commands shipped together

Good fit Delegating debugging, implementation, and deeper investigation, with options to wait, run in the background, or continue an earlier thread.

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 sakibsadmanshajib/antigravity-plugin
Claude Code
/plugin install antigravity

Made for: Claude Code.

Or install antigravity, the plugin that ships this one along with the rest of its 1 skill, 6 commands.

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 rescue

README.md
[![agentmods](https://agentmods.dev/badge/commands/sakibsadmanshajib/antigravity-plugin/rescue/github.svg)](https://agentmods.dev/commands/sakibsadmanshajib/antigravity-plugin/rescue)
Your own site
<a href="https://agentmods.dev/commands/sakibsadmanshajib/antigravity-plugin/rescue"><img src="https://agentmods.dev/badge/commands/sakibsadmanshajib/antigravity-plugin/rescue/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for rescue

Your own site · 80×15
<a href="https://agentmods.dev/commands/sakibsadmanshajib/antigravity-plugin/rescue"><img src="https://agentmods.dev/badge/commands/sakibsadmanshajib/antigravity-plugin/rescue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 587 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 $0.00019 $0.00587
Opus 5 $0.00010 $0.00293
Sonnet 5 $0.00004 $0.00117
Haiku 4.5 $0.00002 $0.00059

Measured 9d ago against content hash 4ff221f26041, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

rescue 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 9d 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/rescue.md · 41 lines

What it actually says

You are a thin forwarding wrapper. Your only job is to invoke the Antigravity companion via Bash and return its output. Do not spawn subagents, do not invoke skills, do not do the work yourself.

Raw user request: $ARGUMENTS

Execution mode:

  • If the request includes --background, tell Claude Code to run this fork in the background.
  • If the request includes --wait, run in the foreground.
  • If neither flag is present, default to foreground.
  • --background and --wait are execution flags for Claude Code. Do not forward them to rescue, and do not treat them as part of the natural-language task text.
  • If the request includes --resume or --continue, do not ask whether to continue — the user already chose.
  • If the request includes --fresh, do not ask either — the user has chosen a new thread.
  • Otherwise, before starting Antigravity, you MAY check whether the user wants to resume the most recent rescue thread. If unsure, ask once via AskUserQuestion with these two choices:
    • Continue most recent Antigravity thread (Recommended) when the user is clearly giving a follow-up
    • Start a new Antigravity thread (Recommended) otherwise

Invocation:

  • Use exactly one Bash call to invoke node "${CLAUDE_PLUGIN_ROOT}/scripts/commands/rescue.mjs" ... and return that command's stdout as-is.
  • Strip --background and --wait from the task text — they are Claude Code execution flags.
  • Everything remaining after stripping flags is the task text — pass it through as the trailing positional.
  • --model <id> is accepted but currently logged-and-ignored: agy 1.0.1 does not expose a per-invocation model flag. Forward the flag anyway so the warning surfaces in stderr.

Auth note:

  • If the helper output says Antigravity is missing or not authenticated, stop and ask the user to run /antigravity:setup.

Output rules:

  • Return the rescue companion stdout verbatim to the user.
  • Do not paraphrase, summarize, rewrite, or add commentary before or after it.
  • If the Bash call fails, return nothing and surface the failure.
  • If the user did not supply a request, ask what Antigravity should investigate or fix.
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. 9d ago First seen · 41 lines · 19 tokens per session scan A 4ff221f26041

Subscribe to this mod's changes

rescue is a command published in the GitHub repository sakibsadmanshajib/antigravity-plugin (21 stars, last pushed 3mo ago), licensed MIT. It adds 19 tokens to every session and 587 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.