codex-exec-automationlisted

# Codex Exec Automation Bundled commands use `$PLUGIN_ROOT` (`$env:PLUGIN_ROOT` in PowerShell; same path suffix) for the plugin root. Set it once: use the host's plugin-root variable when defined (Claude Code: `PLUGIN_ROOT="$CLAUDE_PLUGIN_ROOT"`), otherwise the absolute path of this plugin's root directory. Use this skill for non-interactive Codex CLI work: `codex exec`, `codex e`, `codex exec resume`, `codex exec review`, top-level `codex review`, JSONL event streams, final-message capture, output schemas, prompt stdin, images, cwd selection, and CI-like checks. ## Inspect First Before relying on a flag, verify the installed CLI: ```bash python3 "$PLUGIN_ROOT/scripts/codex_cli_inspector.py" --commands exec review doctor --json ``` If the user supplied a binary path, pass `--codex "$CODEX_CLI_PATH"`. ## Command Assembly Build commands from these decisions, in this order. Put global options before the subcommand and `exec`-specific options after `exec`: 1. Working root: use `-C <repo>` or run from the intended repository. 2. Autonomy: choose `--sandbox` and `--ask-for-approval`. 3. Config stack: add `--profile`, `-c key=value`, `--enable`, `--disable`, or `--strict-config` only when needed. 4. Prompt input: pass a short prompt argument, read from stdin with `-`, or pipe a structured prompt. 5. Output contract: use `--json`, `--output-schema <file>`, or `-o <file>` when automation must parse results. 6. Persistence: use `--ephemeral` only when the run should not persis