agentmods.dev

rescue

rescue is a command for coding agents from contrapuntal/antigravity-cli-plugin-cc. It costs 17 tokens per session (833 once invoked), scanned A, original, Apache-2.0.

A command that delegates an investigation, analysis, or coding task to an Antigravity rescue subagent, which is a separate software agent.

In plain words
What is it for?
Use it to forward a task for foreground or background execution, optionally choosing a model and waiting for the delegated result.
Why use it?
It provides another agent to handle a task when additional investigation or implementation help is needed.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the ask-antigravity plugin — 4 commands, 1 agent shipped together

not rated 2 1mo ago A scan 17 tokens original Apache-2.0
View the source file contrapuntal/antigravity-cli-plugin-cc
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/contrapuntal/antigravity-cli-plugin-cc/rescue
Clone the repo
git clone --depth 1 https://github.com/contrapuntal/antigravity-cli-plugin-cc

Or install ask-antigravity, the plugin that ships this one along with the rest of its 4 commands, 1 agent.

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/contrapuntal/antigravity-cli-plugin-cc/rescue.svg)](https://agentmods.dev/commands/contrapuntal/antigravity-cli-plugin-cc/rescue)
Your own site
<a href="https://agentmods.dev/commands/contrapuntal/antigravity-cli-plugin-cc/rescue"><img src="https://agentmods.dev/badge/commands/contrapuntal/antigravity-cli-plugin-cc/rescue.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 833 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 $0.00017 $0.00833
Opus 5 $0.00009 $0.00417
Sonnet 5 $0.00003 $0.00167
Haiku 4.5 $0.00002 $0.00083

Measured 3d ago against content hash 5b9df310a34a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

plugins/ask-antigravity/commands/rescue.md · 34 lines

What it actually says

Invoke the ask-antigravity:antigravity-rescue subagent via the Agent tool (subagent_type: "ask-antigravity:antigravity-rescue"), forwarding the raw user request as the prompt. ask-antigravity:antigravity-rescue is a subagent, not a skill — do not call Skill(ask-antigravity:antigravity-rescue) (no such skill) or Skill(ask-antigravity:rescue) (that re-enters this command and hangs the session). The command runs inline so the Agent tool stays in scope. The final user-visible response must be Antigravity's output verbatim.

Raw user request: $ARGUMENTS

Execution mode:

  • If the request includes --background, run the ask-antigravity:antigravity-rescue subagent in the background.
  • If the request includes --wait, run the subagent 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 task, and do not treat them as part of the natural-language task text.
  • --model "<display name>" selects the model for this call (names come from agy models; quote them — they contain spaces). Preserve it for the forwarded task call. Without it, agy uses the model selected in its TUI (/model).
  • --write signals write intent (passes --dangerously-skip-permissions to agy). Preserve it for the forwarded task call. Without it, ask Antigravity to analyze and propose rather than apply changes — but note this is not a sandbox: on agy 1.1.1 no flag prevents agy from editing files, so a rescue run may modify the workspace either way. If the working tree is dirty and the user did not pass --write, warn them that any Antigravity edits will be mixed into their uncommitted changes.

Operating rules:

  • The subagent is a thin forwarder only. It writes the task text to a temp file and makes one Bash call — node "${CLAUDE_PLUGIN_ROOT}/scripts/antigravity-companion.mjs" task --prompt-file "<file>" ... — then returns that command's stdout as-is. Task text goes through the file, never interpolated into the shell command.
  • Return the Antigravity companion stdout verbatim to the user.
  • Do not paraphrase, summarize, rewrite, or add commentary before or after it.
  • Do not ask the subagent to inspect files, monitor progress, summarize output, or do follow-up work of its own.
  • Forward a user-supplied --model "<display name>" to the task call unchanged, including its quoting.
  • If the user did not supply a request, ask what Antigravity should investigate or solve.
  • If the helper reports that Antigravity is missing or unauthenticated, stop and tell the user to run /ask-antigravity:setup.
  • For background runs, completion arrives as an Agent-tool notification from the harness. Do not poll temp directories, do not search for sidecar files (this plugin does not create any), and do not invoke agy or the companion script directly to "check status" — that runs a separate agy session and does not surface the in-flight one. If the subagent returns the line [antigravity-rescue] dispatcher failed: <reason>, surface that to the user verbatim and stop.
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. 3d ago First seen · 34 lines · 17 tokens per session scan A 5b9df310a34a

Subscribe to this mod's changes

rescue is a command published in the GitHub repository contrapuntal/antigravity-cli-plugin-cc (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 17 tokens to every session and 833 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.

Building agentsanthropic-skillclaude-codecodex-clicopilot-cligemini
Related

Other commands, from other repositories

8eyes-copilot

Start a multi-agent review mission (Copilot CLI adapter notes).

AgentBuildersApp/eight-eyes · 19 tokens

8eyes

Start a failure-aware multi-agent code review mission.

AgentBuildersApp/eight-eyes · 12 tokens

update-ai-versions

Look up the latest published versions of the AI coding assistants pinned in the Dockerfile and update the ARG lines in place.

sugarfreebytes/aidevtools · 24 tokens

ceo.analyze

Use for ad campaign performance analysis, weekly trend reporting, data correlation, and actionable optimization insights.

ivfarias/ceo · 19 tokens

ceo.develop

Use for architecture design, software implementation, debugging, refactoring, and test automation.

ivfarias/ceo · 17 tokens

ceo.marketing

Use for go-to-market strategy, user acquisition, channel analysis, and performance marketing.

ivfarias/ceo · 17 tokens