Codex CLI Skill

codex exec "PROMPT"

When to Use

• Code generation tasks needing OpenAI/GPT model perspective
• Cross-validation of code solutions with a non-Claude model
• Tasks benefiting from Codex's code optimization focus
• Multi-LLM consultation workflows

Usage

Ask a question

node .claude/skills/omega-codex-cli/scripts/ask-codex.mjs "Implement a Redis caching layer for Express"

With timeout

node .claude/skills/omega-codex-cli/scripts/ask-codex.mjs "Refactor this module" --timeout-ms 120000

JSONL streaming output

node .claude/skills/omega-codex-cli/scripts/ask-codex.mjs "Generate unit tests" --json

Sandbox mode

node .claude/skills/omega-codex-cli/scripts/ask-codex.mjs "Write and test a sort algorithm" --sandbox

Availability Check

node .claude/skills/omega-codex-cli/scripts/verify-setup.mjs
# Exit 0 = available (CLI found + OPENAI_API_KEY set)
# Exit 1 = not available

Scripts

ask-codex.mjs

parse-args.mjs

verify-setup.mjs

format-output.mjs

Flags

--model MODEL

--json

--sandbox

--timeout-ms N

Exit Codes

Anti-Patterns & Iron Laws

1. ALWAYS verify OPENAI_API_KEY is set before invocation
2. NEVER use stdin for prompt delivery — Codex uses positional arg
3. ALWAYS include --skip-git-repo-check (built into wrapper)
4. ALWAYS set --timeout-ms for production usage
5. NEVER assume --json output is standard JSON — it produces JSONL event stream

Integration Notes

• API key:

  OPENAI_API_KEY

  env var required
• Rate limits: OpenAI API rate limits apply
• Platform: Full cross-platform (Windows uses cmd.exe /d /s /c wrapper)

Memory Protocol (MANDATORY)

.claude/context/memory/learnings.md

• New pattern ->

  .claude/context/memory/learnings.md

• Issue found ->

  .claude/context/memory/issues.md

• Decision made ->

  .claude/context/memory/decisions.md

ASSUME INTERRUPTION: If it's not in memory, it didn't happen.

pnpm search:code