What problem does it solve?
This Skill provides a unified interface to run various AI coding agents (Codex, Claude Code, OpenCode, Pi) for programmatic code generation, review, and modification, ensuring safe execution through PTY and sandboxing.
Core Features & Use Cases
- Unified Agent Interface: Interact with multiple coding agents through a single bash-first interface.
- Safe Execution: Enforces PTY mode for interactive agents and offers sandboxing or
--yolo modes for different risk tolerances.
- Background Processing: Run long-running tasks like code generation or refactoring in the background with session monitoring.
- Use Case: Automatically generate boilerplate code for a new API endpoint, review a pull request, or refactor a module using your preferred AI coding assistant.
Quick Start
Use the coding-agent skill to run codex exec 'Add error handling to the API calls' in the ~/Projects/myproject directory with PTY enabled.