agentuity-cli-cloud-sandbox-run
Run a one-shot command in a sandbox (creates, executes, destroys). Requires authentication. Use for Agentuity cloud platform operations
When & Why to Use This Skill
This Claude skill enables the execution of one-shot commands within a secure, isolated cloud sandbox on the Agentuity platform. It automates the entire lifecycle—creation, execution, and destruction—allowing developers and AI agents to run untrusted code, test scripts with specific resource constraints, or perform cloud-native operations without manual infrastructure overhead. By providing fine-grained control over CPU, memory, and network access, it ensures a safe and reproducible environment for ephemeral tasks.
Use Cases
- Secure Code Execution: Running untrusted or experimental scripts in an isolated environment to prevent local system compromise or data leaks.
- Resource-Constrained Testing: Validating application performance and stability by specifying exact CPU, memory, and disk limits for a specific command.
- Automated Dependency Management: Testing scripts that require specific system packages (apt) or environment variables without polluting the host environment.
- Cloud-Native Task Automation: Executing ephemeral tasks on the Agentuity platform with integrated authentication, snapshot restoration, and network control.
- CI/CD Pipeline Integration: Using the sandbox as a clean room for building or testing code snippets as part of a larger automation workflow.
| 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 | "0.0.110" |
| license | Apache-2.0 |
| allowed-tools | "Bash(agentuity:*)" |
| argument-hint | "<command...>" |
| 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-idor default org)
Usage
agentuity cloud sandbox run <command...> [options]
Arguments
| Argument | Type | Required | Description |
|---|---|---|---|
<command...> |
array | Yes | - |
Options
| Option | Type | Required | Default | Description |
|---|---|---|---|---|
--memory |
string | Yes | - | Memory limit (e.g., "500Mi", "1Gi") |
--cpu |
string | Yes | - | CPU limit in millicores (e.g., "500m", "1000m") |
--disk |
string | Yes | - | Disk limit (e.g., "500Mi", "1Gi") |
--network |
boolean | No | false |
Enable outbound network access |
--timeout |
string | Yes | - | Execution timeout (e.g., "5m", "1h") |
--env |
array | Yes | - | Environment variables (KEY=VALUE) |
--file |
array | Yes | - | Files to create in sandbox (sandbox-path:local-path) |
--timestamps |
boolean | No | false |
Include timestamps in output (default: true) |
--snapshot |
string | Yes | - | Snapshot ID or tag to restore from |
--dependency |
array | Yes | - | Apt packages to install (can be specified multiple times) |
Examples
Run a simple command:
bunx @agentuity/cli cloud sandbox run -- echo "hello world"
Run with resource limits:
bunx @agentuity/cli cloud sandbox run --memory 1Gi --cpu 1000m -- bun run index.ts
Run with network access enabled:
bunx @agentuity/cli cloud sandbox run --network -- curl https://api.example.com
Output
Returns JSON object:
{
"sandboxId": "string",
"exitCode": "number",
"durationMs": "number",
"output": "string"
}
| Field | Type | Description |
|---|---|---|
sandboxId |
string | Sandbox ID |
exitCode |
number | Exit code from the process |
durationMs |
number | Duration in milliseconds |
output |
string | Combined stdout/stderr output |