agentrun-cli

Execute shell commands with enforced timeouts and bounded output.

Updated Mar 12, 2026
One-click install
npx skills add https://github.com/SebastianBoehler/agent-cli-utils --skill agentrun-cli
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agentrun-cli
Source: https://github.com/SebastianBoehler/agent-cli-utils/tree/main/skills/agentrun-cli
Command: npx skills add https://github.com/SebastianBoehler/agent-cli-utils --skill agentrun-cli

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Execute shell commands safely by enforcing timeouts and bounded output while returning structured results.

Core Features & Use Cases

  • Enforces per-command timeouts to prevent hangs.
  • Captures stdout and stderr with size limits and returns structured results.
  • Supports optional working directories and controlled input when needed.
  • Use Case: Validate long-running health checks on remote agents and gather parseable metrics.

Quick Start

Run a quick health check with a 5s timeout and collect structured JSON output.

Frequently Asked Questions about agentrun-cli

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I execute shell commands with a timeout and prevent them from hanging?

You can execute shell commands with a timeout by using a runtime that enforces deterministic execution and per-command timeouts. This safely captures stdout and stderr while returning structured, bounded output to prevent processes from hanging.

How do I capture command line output safely without flooding agent logs?

To capture command line output safely without flooding logs, use bounded output limits that restrict stdout and stderr size. This returns structured results and ensures unbounded processes cannot overwhelm your automated task logs.

What is the best way to run automated health checks and get parseable metrics?

The best way to run automated health checks and get parseable metrics is to execute shell commands with enforced timeouts and structured output. This validates long-running checks on remote agents and returns consistent, parseable results.

Can I set a working directory and controlled input when running shell commands in an agent runtime?

Yes, you can set a working directory and provide controlled input when running shell commands in an agent runtime. This feature supports deterministic execution and safe containment of command runs within specified boundaries.

Why do my automated shell commands hang and how do I enforce deterministic execution?

Automated shell commands hang when unbounded processes lack execution limits. You can enforce deterministic execution by applying per-command timeouts and consistent output formatting, which safely contains command runs and prevents indefinite hangs.