Reference for Codex CLI usage patterns. Consult before calling codex via Bash.
Executes Codex CLI commands for complex coding tasks when you need advanced reasoning or sandboxed execution. Triggers when you request code generation, analysis, or multi-file operations that benefit from Codex's specialized capabilities.
/plugin marketplace add GantisStorm/claude-code-repoprompt-codex-plugins/plugin install codex-swarm@claude-code-repoprompt-codex-pluginsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Quick reference for Codex CLI commands.
codex exec "[prompt]" -m gpt-5.2 --reasoning-effort high --sandbox read-only --ask-for-approval never 2>&1
| Flag | Purpose |
|---|---|
exec | Non-interactive execution mode |
-m gpt-5.2 | Model selection |
--reasoning-effort high | Reasoning effort (minimal, low, medium, high, xhigh) |
--sandbox read-only | Prevent file modifications |
--sandbox workspace-write | Allow writes within workspace |
--ask-for-approval never | Non-interactive mode |
--search | Enable web search |
-C DIR | Set working directory |
# Resume a previous session
codex resume [session-id] "[prompt]" --sandbox read-only --ask-for-approval never 2>&1
Note: Session IDs are returned in Codex output.
dangerouslyDisableSandbox: true for Bash calls2>&1 to capture all outputNEVER use these flags:
--dangerously-bypass-approvals-and-sandbox - FORBIDDEN--sandbox danger-full-access - FORBIDDENTimeout: Complex analysis may take 5-10 minutes. Use longer timeout values.
Authentication: Codex CLI must be authenticated via codex login.
Flag errors: Run codex --help to verify correct flag usage.
codex --help