From codex-collaborator
Collaborate with Codex CLI through iterative AI-to-AI discussion. Use whenever the user mentions "Codex" in any context—asking for Codex's opinion, consulting Codex, discussing with Codex, or any request involving Codex collaboration. Also triggers on phrases like "ask another AI", "get a second opinion from AI", or "AI-to-AI discussion".
How this skill is triggered — by the user, by Claude, or both
Slash command
/codex-collaborator:skills/codex-collaboratorThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Collaborate with Codex CLI for objective, multi-perspective analysis.
Collaborate with Codex CLI for objective, multi-perspective analysis.
Request Codex to provide unbiased, objective analysis:
Continue discussion until convergence—no fixed number of rounds.
Include:
codex exec "YOUR_PROMPT" --sandbox read-only
After each response:
Combine insights:
[TOPIC/QUESTION]
Context: [CONTEXT]
Important: Provide objective analysis. Be critical and point out flaws.
Don't defer to any assumed preference. If you disagree, say so clearly.
npx claudepluginhub ShintaroaSuzuki/claude-code-plugins --plugin codex-collaboratorConsults Codex CLI for second opinions on code reviews, designs, or implementations by crafting context-based prompts, executing via bash with configurable depth (light/normal/deep), and summarizing results.
Starts OpenAI Codex CLI sessions for deep code reasoning, review, and analysis. Handles new tasks or follow-ups via /codex; returns task ID for async /codex-result checks.
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing