codex-cli
Run OpenAI Codex CLI for coding tasks and second-opinion audits. Use when a user asks to run/ask/use Codex, says "codex prompt", or wants Claude to delegate a logic/code review to OpenAI models.
npx skills add majiayu000/claude-skill-registry --skill codex-cli-georgekhananaev-claude-skills-vault --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Codex CLI Run OpenAI Codex CLI locally for second-opinion audits, code review, and non-interactive task execution. ## Prerequisites Codex CLI must be installed and authenticated: 1. **Install:** `npm install -g @openai/codex` 2. **Auth:** `codex login` 3. **Verify:** `codex --version` ## Core Execution Pattern Use `codex exec` for delegated prompts (non-interactive): ```bash codex exec "Your prompt here" ``` When the user says "codex prompt", treat it as: ```bash codex exec "<user prompt>" ``` ## Model Guidance Use the default configured model unless the user asks otherwise. Latest tested working model in this environment: ```bash codex exec -m gpt-5.3-codex "Your prompt" ``` Compatibility note: - `gpt-5-codex` may fail if config uses `model_reasoning_effort = "xhigh"`. - If you must use `gpt-5-codex`, set reasoning effort explicitly: ```bash codex exec -m gpt-5-codex -c model_reasoning_effort="high" "Your prompt" ``` ## Commands ### Non-Interactive Execution ```bash # Basic task codex exec "Audit this logic for edge cases" # Explicit model codex exec -m gpt-5.3-codex "Review this implementation strategy" # Full-auto mode (sandboxed, lower friction) codex exec --full-auto "Implem
- Prerequisites
- Core Execution Pattern
- Model Guidance
- Commands
- Non-Interactive Execution
- Code Review
- Important Flag Placement
- Useful Flags
- Best Practices
codex exec "Your prompt here" codex exec "<user prompt>" codex exec -m gpt-5.3-codex "Your prompt" codex exec -m gpt-5-codex -c model_reasoning_effort="high" "Your prompt" Basic task codex exec "Audit this logic for edge cases" Explicit model codex exec -m gpt-5.3-codex "Review this implementation strategy" Full-auto mode (sandboxed, lower friction) codex exec --full-auto "Implement the requested refactor"
What does the codex-cli skill do?
Run OpenAI Codex CLI for coding tasks and second-opinion audits. Use when a user asks to run/ask/use Codex, says "codex prompt", or wants Claude to delegate a logic/code review to OpenAI models.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill codex-cli-georgekhananaev-claude-skills-vault --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.