AgentSkillsCN

agentuity-cli-cloud-sandbox-run

在沙盒中运行一次性命令(创建、执行、销毁)。需要身份验证。适用于 Agentuity 云平台运维。

SKILL.md
--- frontmatter
name: agentuity-cli-cloud-sandbox-run
description: "Run a one-shot command in a sandbox (creates, executes, destroys). Requires authentication. Use for Agentuity cloud platform operations"
version: "0.1.24"
license: Apache-2.0
allowed-tools: "Bash(agentuity:*)"
argument-hint: "<command...>"
metadata:
  command: "agentuity cloud sandbox run"
  tags: "slow requires-auth"

Cloud Sandbox Run

Run a one-shot command in a sandbox (creates, executes, destroys)

Prerequisites

  • Authenticated with agentuity auth login
  • Organization context required (--org-id or default org)

Usage

bash
agentuity cloud sandbox run <command...> [options]

Arguments

ArgumentTypeRequiredDescription
<command...>arrayYes-

Options

OptionTypeRequiredDefaultDescription
--runtimestringYes-Runtime name (e.g., "bun:1", "python:3.14")
--runtimeIdstringYes-Runtime ID (e.g., "srt_xxx")
--namestringYes-Sandbox name
--descriptionstringYes-Sandbox description
--memorystringYes-Memory limit (e.g., "500Mi", "1Gi")
--cpustringYes-CPU limit in millicores (e.g., "500m", "1000m")
--diskstringYes-Disk limit (e.g., "500Mi", "1Gi")
--networkbooleanNofalseEnable outbound network access
--timeoutstringYes-Execution timeout (e.g., "5m", "1h")
--envarrayYes-Environment variables (KEY=VALUE)
--filearrayYes-Files to create in sandbox (sandbox-path:local-path)
--timestampsbooleanNofalseInclude timestamps in output (default: true)
--snapshotstringYes-Snapshot ID or tag to restore from
--dependencyarrayYes-Apt packages to install (can be specified multiple times)
--projectIdstringYes-Project ID to associate this sandbox with

Examples

Run a simple command:

bash
bunx @agentuity/cli cloud sandbox run -- echo "hello world"

Run with resource limits:

bash
bunx @agentuity/cli cloud sandbox run --memory 1Gi --cpu 1000m -- bun run index.ts

Run with network access enabled:

bash
bunx @agentuity/cli cloud sandbox run --network -- curl https://api.example.com

Output

Returns JSON object:

json
{
  "sandboxId": "string",
  "exitCode": "number",
  "durationMs": "number",
  "output": "string"
}
FieldTypeDescription
sandboxIdstringSandbox ID
exitCodenumberExit code from the process
durationMsnumberDuration in milliseconds
outputstringCombined stdout/stderr output