clrun - Interactive CLI for agent with a LLM readable YAML response surface

• Risk level: Low
• Analyzed: Feb 17, 2026, 1:09 AM
• Findings: 0
• Version: 1.0.0

Overview

The skill is an instruction-only guide for driving an interactive CLI tool (clrun); it is internally coherent for that purpose, with a minor metadata inconsistency and normal sensitivity around letting an agent run shell commands and handle session environment variables.

This skill is an instruction-only guide for using a separate CLI (clrun) to drive interactive terminals — it does not include code or request credentials itself. Before installing or using it: (1) note the SKILL.md requires Node.js >=18 and the clrun CLI (the registry metadata omitted that), so ensure those are installed from a trusted source and consider pinning an explicit clrun version if using npx. (2) Understand that the agent will be instructed to run arbitrary shell commands (including npx create-* scaffolding which downloads and executes code); run in an isolated/sandboxed environment if you don't fully trust the agent. (3) Avoid placing real secrets (API keys, private tokens) into sessions the agent will drive or read — examples in the docs show env vars surviving suspension and being echoed. (4) If you need stricter controls, require explicit approval before the agent executes any session-starting command or interacting with outputs that might contain secrets.