Codeagent

A thoughtful wrapper around multiple AI code backends (Codex, Claude, Gemini, OpenCode) that actually handles the orchestration layer most of us end up building anyway. The parallel execution model is the real story here: you can queue up a code explorer task, an architect task, and an implementation task with dependency chains, all in one config block. Agent presets let you bundle backend, model, and prompts into reusable personas like code-explorer or develop. Auto-detects your stack from go.mod or package.json and injects relevant skill files. The worktree isolation flag is a nice touch for keeping experimental changes off your main branch. If you're already scripting multi-step AI workflows or switching between models based on task type, this consolidates that into one tool.

skills.sh installs: 185
GitHub stars: 2.7K
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add cexll/myclaude --skill codeagent --agent claude-code

Installs into .claude/skills of the current project.

Files

Codeagent Wrapper Integration

Overview

Execute codeagent-wrapper commands with pluggable AI backends (Codex, Claude, Gemini, OpenCode), agent presets, auto-detected skill injection, and parallel task orchestration. Default to background execution, and prefer --parallel whenever work can be split into independent tasks.

When to Use

Complex code analysis requiring deep understanding
Large-scale refactoring across multiple files
Multi-agent orchestration (explore → design → implement → review)
Automated code generation with backend/agent selection
Parallel task execution with dependency management

Quick Reference

codeagent-wrapper [flags] <task|-> [workdir]
codeagent-wrapper [flags] resume <session_id> <task|-> [workdir]
codeagent-wrapper --parallel [flags] < tasks_config