Get OpenAI Codex CLI's opinion on code, bugs, or implementation. Use when you want a second AI perspective during coding sessions.
Get a second AI opinion on your code from OpenAI's Codex CLI. Triggered when you ask for code review, bug analysis, or implementation feedback on specific files.
/plugin marketplace add theflysurfer/claude-skills-marketplace/plugin install theflysurfer-claude-skills-marketplace@theflysurfer/claude-skills-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Get feedback from OpenAI's Codex CLI on code, bugs, or implementation approaches.
npm install -g @openai/codexcodex login or sign in with ChatGPT accountcodex --versionThe user will ask something like:
codex exec "Review <file_path> and provide 3 specific improvements for production"
codex exec "Analyze <file_path> for potential bugs and edge cases"
codex review
Note: codex review opens an interactive review session - use codex exec for non-interactive feedback.
Present Codex's response clearly to the user. If Codex suggests improvements, summarize them as actionable items.
User: "demande à codex de reviewer le benchmark"
codex exec "Review scripts/benchmark-semantic-router.py for improvements and potential issues"
User: "ask codex to find bugs in this file"
codex exec "Analyze scripts/semantic-skill-router.py for potential bugs, edge cases, and error handling gaps"
| Error | Cause | Fix |
|---|---|---|
codex: command not found | CLI not installed | npm install -g @openai/codex |
Not authenticated | Not logged in | Run codex login |
Model not available | Account tier issue | Check ChatGPT subscription |
| Response timeout | Large codebase | Use specific file path, not whole repo |
codex exec for non-interactive (scripted) usecodex review for interactive review sessionjulien-workflow-advice-gemini for multiple AI opinionsBash (usage: run codex CLI command, timeout 60s)This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.