Shell

Execute shell commands with timeout, output limits, and command allowlisting.

Shell

Execute shell commands from your agent. Supports timeouts, output truncation, and an optional command allowlist for safety.

---

Quick Start

import { Agent, openai, ShellToolkit } from "@radaros/core";

const shell = new ShellToolkit({
  timeout: 10_000,
  allowedCommands: ["ls", "cat", "grep", "find", "wc"],
});

const agent = new Agent({
  name: "devops-agent",
  model: openai("gpt-4o"),
  instructions: "Help users inspect their system and files.",
  tools: [...shell.getTools()],
});

const result = await agent.run("How many TypeScript files are in the src directory?");

---

Config

shell · string

Shell to use (default: platform default, e.g. /bin/sh).

timeout · number · default: "30000"

Command timeout in milliseconds.

maxOutput · number · default: "10000"

Max output characters to return. Long output is truncated from the start.

cwd · string

Working directory for commands.

allowedCommands · string[]

Allowlist of command prefixes. If set, only commands starting with one of these are permitted.

---

Tools

Tool	Description
shell_exec	Execute a shell command. Returns stdout, stderr, and exit code.

Use allowedCommands in production to restrict which commands agents can run.