CodeAgent Wrapper

What it does

CodeAgent provides a CLI wrapper for executing code-focused tasks across multiple AI backends (Codex, Claude, Gemini, OpenCode). It standardises invocation patterns, supports @file references, parallel execution with per-task backend selection, and produces structured summaries or full outputs for debugging. The skill documents invocation syntaxes, backend recommendations, concurrency controls, and security flags.

When to use it

Use CodeAgent when automating complex code analysis, large-scale refactors, multi-file changes, or orchestration that benefits from backend specialization (e.g., Codex for implementation & review, Gemini for UI components). It's useful in CI automation, developer tooling, and scripted agent-driven workflows where per-task backend tuning improves results.

What's included

• Scripts: CLI invocation patterns for single tasks, parallel batches, and resume flows; examples of HEREDOC usage and tmux integration.
• References: Backend capability matrix and environment variables for timeouts, concurrency, and permission controls.
• Instructions: Clear parameter list, example task metadata schema for parallel execution, and best-practice security notes about permission skips and sandbox bypass.

Compatible agents

Agents and automation runners that can execute shell CLIs and manage tmux sessions, plus LLM backends (Codex, Claude, Gemini) when integrated. Ideal for developer-oriented agents and orchestration pipelines.