Codex

Codex Skill Guide

Running a Task

1. Default to gpt-5.5 model. Ask the user in the normal conversation which reasoning effort to use (xhigh, high, medium, or low). User can override model if needed (see Model Options below). If gpt-5.5 is unavailable in your environment, fall back to gpt-5.4.
2. Select the sandbox mode required for the task; default to --sandbox read-only unless edits or network access are necessary.
3. Assemble the command with the appropriate options:
   • -m, --model <MODEL>
   • --config model_reasoning_effort="<high|medium|low>"
   • --sandbox <read-only|workspace-write|danger-full-access>
   • -a never before exec for non-interactive runs
   • --output-last-message <FILE> when a clean final response file is needed
   • -C, --cd <DIR>
   • --skip-git-repo-check
4. Always use --skip-git-repo-check.
5. When continuing a previous session, use codex exec --skip-git-repo-check resume --last via stdin. When resuming don't use any configuration flags unless explicitly requested by the user e.g. if he species the model or the reasoning effort when requesting to resume a session. Resume syntax: echo "your prompt here" | codex exec --skip-git-repo-check resume --last 2>/dev/null. All flags have to be inserted between exec and resume.
6. IMPORTANT: By default, append 2>/dev/null to all codex exec commands to suppress thinking tokens (stderr). Only show stderr if the user explicitly requests to see thinking tokens or if debugging is needed.
7. Run the command, capture stdout/stderr (filtered as appropriate), and summarize the outcome for the user.
8. After Codex completes, inform the user: "You can resume this Codex session at any time by saying 'codex resume' or asking me to continue with additional analysis or changes."

Quick Reference

Model Options

Selection guide: Start with gpt-5.5 for most tasks. Drop to gpt-5.4 when 5.5 isn't available. Use gpt-5.3-codex when you need maximum coding quality without 5.5 reasoning overhead. Use gpt-5.4-mini for sub-agents and cleanup workloads.

Verify exact context window / pricing on the official model card — values may shift as preview/stable status changes.

Reasoning Effort Levels:

• xhigh - Ultra-complex tasks (deep problem analysis, complex reasoning, deep understanding of the problem)
• high - Complex tasks (refactoring, architecture, security analysis, performance optimization)
• medium - Standard tasks (refactoring, code organization, feature additions, bug fixes)
• low - Simple tasks (quick fixes, simple changes, code formatting, documentation)

Cached Input Discount: Repeated context is heavily discounted with cache lasting up to 24 hours. Verify current rates on the official OpenAI pricing page.

Following Up

• After every codex command, ask in the normal conversation when confirmation, clarification, or a resume decision is actually needed.
• When resuming, pipe the new prompt via stdin: echo "new prompt" | codex exec resume --last 2>/dev/null. The resumed session automatically uses the same model, reasoning effort, and sandbox mode from the original session.
• Restate the chosen model, reasoning effort, and sandbox mode when proposing follow-up actions.

Error Handling

• Stop and report failures whenever codex --version or a codex exec command exits non-zero; request direction before retrying.
• Before you use high-impact flags (--sandbox danger-full-access, --skip-git-repo-check), ask the user in the normal conversation unless permission was already given.
• When output includes warnings or partial results, summarize them and ask in the normal conversation how to adjust.

CLI Version

Requires a recent Codex CLI version for GPT-5.5 model support. Check version: codex --version and update with npm install -g @openai/codex@latest if needed. Use /model slash command within a session to switch, or set default in ~/.codex/config.toml.