core

Manage Codegg agent sessions and transport protocols between TUI and daemon.

Updated May 6, 2026
One-click install
npx skills add https://github.com/dbowm91/codegg --skill core-dbowm91
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: core
Source: https://github.com/dbowm91/codegg/tree/main/.opencode/skills/core
Command: npx skills add https://github.com/dbowm91/codegg --skill core-dbowm91

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides the essential interface for managing the Codegg agent's lifecycle, session state, and communication transport, ensuring seamless interaction between the TUI and the backend daemon.

Core Features & Use Cases

  • Session Lifecycle Management: Create, load, fork, archive, and restore agent sessions with full workspace awareness.
  • Transport Flexibility: Switch between local daemon socket, in-process standalone mode, or stdio-based communication.
  • Use Case: When working on multiple projects, use this skill to switch between different workspace contexts and ensure the agent daemon is correctly attached to your current terminal session.

Quick Start

Use the core skill to list all active sessions and attach to the workspace associated with the current directory.

Frequently Asked Questions about core

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

FAQPage Schema
How do I manage agent session lifecycle and workspace contexts for terminal operations?

You can manage agent session lifecycle by creating, loading, forking, archiving, and restoring sessions with full workspace awareness to switch between different project contexts.

What transport protocols are available for daemon communication in a terminal UI?

Daemon transport supports multi-mode communication protocols including local Unix sockets, in-process standalone mode, and stdio-based communication for flexible agent operations.

How does the request-response boundary work between a TUI and backend agent sessions?

The request-response boundary works by implementing a core protocol envelope and execution context binding that facilitates seamless interaction between the TUI and underlying agent session logic.

Can I run an agent daemon in standalone mode without external socket dependencies?

Yes, you can run the agent daemon in standalone mode using in-process communication, which bypasses the need for external Unix socket dependencies while maintaining full session state.

What is the best way to attach a backend daemon to a current terminal workspace?

The best way to attach a daemon is by using the core skill to list all active sessions and register the current directory as the active workspace context.

Why do I need persistent execution context binding for agent operations?

Persistent execution context binding is required to maintain daemon lifecycle integrity and ensure the protocol envelope correctly routes request-response cycles across workspace switches.