# clrun — The Interactive CLI for AI Agents

> Persistent. Deterministic. Project-Scoped Execution.
> No more --yes flags or command retries.

clrun gives AI agents full control over interactive terminal sessions — TUI prompts, select lists, checkboxes, confirms, long-running processes — with structured YAML responses, contextual hints, and auto-suspend/restore.

- GitHub: https://github.com/cybertheory/clrun
- npm: https://www.npmjs.com/package/clrun

## Documentation

- [Core Skill Reference](/skills/clrun-skill.md): Complete CLI reference for AI agents. All commands, queue behavior, session lifecycle, state layout.
- [Claude Code Integration](/skills/claude-code-skill.md): Optimized instructions for Claude Code. Workflow, prompt detection, override strategies.
- [OpenClaw Integration](/skills/openclaw-skill.md): Structured skill reference for OpenClaw agents. Command reference, workflow pattern, session states.

## Agent Skills Format (agentskills.io)

- [SKILL.md](/skills/clrun/SKILL.md): Agent Skills spec format. Frontmatter + concise instructions for any compatible agent runtime.
- [TUI Patterns Reference](/skills/clrun/references/tui-patterns.md): Real-world walkthroughs — create-vue, create-vite, npm init, dev servers, env persistence.

## Quick Start

Install:
```
npm install -g clrun
```

Run a command:
```
clrun echo "hello world"
```

Drive an interactive scaffolder:
```
clrun "npx create-vue@latest"
clrun <id> "my-app"
clrun key <id> down down enter
```

## Full Documentation

For the complete unabridged documentation, see [/llms-full.txt](/llms-full.txt).