What problem does it solve? Offloading coding work such as building features, refactoring modules, and reviewing pull requests to an autonomous agent is difficult to orchestrate from a terminal-driven assistant. This Skill provides the exact invocation patterns, flags, and process-management steps needed to run the OpenAI Codex CLI reliably inside a git repository. ## Core Features & Use Cases - One-Shot and Background Execution: Run codex exec for quick tasks or launch long-running jobs in the background and monitor them with process polling and logging. - PR Reviews and Batch Issue Fixing: Clone repos into temp directories for safe reviews, and use git worktrees to fix multiple issues in parallel with separate Codex sessions. - Sandbox and Gateway Handling: Apply the right flags (--full-auto, --yolo, --sandbox danger-full-access) depending on context, including workarounds for bubblewrap errors in Hermes gateway sessions. - Use Case: You need to fix issues #78 and #99 simultaneously. Create two git worktrees, launch a background Codex process in each with a targeted prompt, monitor progress, then push branches and open PRs with gh. ## Quick Start Ask the agent to run Codex in one-shot mode on your repository, for example: use Codex to add a dark mode toggle to the settings page of my project.
