codex-assistant
Run AI-powered tasks using OpenAI Codex CLI. Use when Claude needs to (1) delegate code analysis or generation tasks to Codex, (2) get a second opinion on code changes, (3) perform parallel AI review, or (4) leverage Codex for specific tasks. Triggers on requests like "use codex to...", "run codex", "ask codex", "codex review".
npx skills add majiayu000/claude-skill-registry --skill codex-assistant --agent codex
Same command for any agent — swap --agent for claude-code, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Codex Assistant Execute tasks using OpenAI Codex CLI and analyze results. ## Important Limitations **Codex runs in read-only sandbox mode.** It cannot: - Create or modify files - Execute scripts or commands that write to disk - Run generated code **Always ask Codex to output results directly to stdout.** Do not request file creation or modification - instead, ask Codex to print/output the code or results, which Claude can then save if needed. ## Command ```bash codex exec --model gpt-5.2-codex "PROMPT" ``` ## Prompt Format Structure prompts with three sections: ``` # Role [Describe the role/persona for the task] # Context [Include relevant information:] - File paths and links to documentation - Memory files or conversation context - Additional task-relevant details # Task [Clear task description] [Expected deliverables] ``` ## Workflow 1. **Construct prompt** - Build structured prompt with Role, Context, Task 2. **Execute codex** - Run command with the formatted prompt 3. **Analyze output** - Review results for: - Completeness of task execution - Quality and accuracy of output - Issues or recommendations identified - Actionable items to address ## Example ```bash codex exec --mod
- Important Limitations
- Command
- Prompt Format
- Workflow
- Example
- Output Analysis
codex exec --model gpt-5.2-codex "PROMPT" codex exec --model gpt-5.2-codex "# Role Senior code reviewer with expertise in security and best practices. Context Files changed: src/auth.py, src/api.py Task Review changes against develop branch. Search for security issues, bugs, and suggest improvements. Output your findings and recommendations to stdout."
What does the codex-assistant skill do?
Run AI-powered tasks using OpenAI Codex CLI. Use when Claude needs to (1) delegate code analysis or generation tasks to Codex, (2) get a second opinion on code changes, (3) perform parallel AI review, or (4) leverage Codex for specific tasks. Triggers on requests like "use codex to...", "run codex", "ask codex", "codex review".
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill codex-assistant --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.