codex_execute
Execute OpenAI Codex tasks synchronously with full control over subcommand, arguments, model selection, and reasoning effort, returning only core results to save context.
Instructions
Execute OpenAI Codex (GPT-5) synchronously with full control over subcommand and arguments. Returns only the core result, filtering out thinking process to save context. Common usage: subcommand="exec", prompt="your task", args=["--full-auto"]
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| args | No | Additional command-line arguments. Model selection: ["-m", "gpt-5-codex"] for coding (default) or ["-m", "gpt-5"] for analysis. Reasoning effort: ["--config", "model_reasoning_effort=low|medium|high"] (gpt-5-codex supports low/medium/high; gpt-5 supports minimal/low/medium/high). Example: ["--full-auto", "-m", "gpt-5", "--config", "model_reasoning_effort=high"]. Always include "--full-auto" for non-interactive execution. | |
| prompt | No | Main prompt/argument for the command (required for exec, optional for others) | |
| timeout | No | Timeout in seconds (default: no limit) | |
| subcommand | No | Codex subcommand to execute | exec |