codex-qa
π―Skillfrom funnelenvy/agents_webinar_demos
Queries and analyzes code using OpenAI Codex CLI, providing read-only codebase exploration and technical insights.
Installation
npx skills add https://github.com/funnelenvy/agents_webinar_demos --skill codex-qaSkill Details
Use OpenAI Codex CLI to answer questions about code, analyze files, or perform read-only codebase exploration. Invoke this skill when the user asks to use Codex, wants a second opinion from another AI agent, or wants to compare Claude's answer with Codex's response.
Overview
# Codex Q&A
Use OpenAI's Codex CLI to answer questions about the codebase.
Prerequisites
Codex CLI must be installed and configured:
```bash
npm install -g @openai/codex
# or
brew install --cask codex
```
An OpenAI API key must be configured (OPENAI_API_KEY environment variable or via codex initial setup).
Usage
Spawn the codex-qa subagent to handle the question:
```
Use the Task tool to spawn the codex-qa agent with the user's question.
```
The subagent will:
- Formulate a clear prompt for Codex
- Run
codex exec "question"in read-only mode - Return Codex's response
Direct Usage (without subagent)
If you prefer to run Codex directly:
```bash
codex exec "your question here"
```
Command Options
- Basic query:
codex exec "question" - With image:
codex -i image.png exec "question about image" - JSON output:
codex exec --json "question" - Longer timeout:
codex exec --timeout 300000 "complex question"
Common Use Cases
- Code explanation: "What does this function do?"
- Architecture questions: "How is the database layer structured?"
- Finding patterns: "Where is error handling implemented?"
- Code review: "Review this file for potential issues"
- Comparison: Get a second opinion on a code question
Notes
- Codex exec runs in read-only mode by default - it cannot modify files
- Activity streams to stderr, final answer goes to stdout
- For complex questions, use the subagent for better context isolation
More from this repository9
Generates precise CSV export formats for Google Ads Enhanced Conversions, Customer Match, and Meta Custom Audiences with specific data schema requirements.
Queries code and files using Google Gemini CLI, providing AI-powered insights, explanations, and analysis for codebases.
gcp-cli-gotchas skill from funnelenvy/agents_webinar_demos
gcp-bq-data-loading skill from funnelenvy/agents_webinar_demos
Automates browser interactions using Playwright Python, enabling web scraping, screenshot capture, and dynamic page testing with precise element selection.
Automates BigQuery table operations like creation, schema updates, data loading, and management across Google Cloud Platform projects
Automates anomaly detection workflows by connecting data sources, triggering alerts in Slack, and orchestrating multi-step notification processes using N8N workflow automation.
Exports BigQuery data to Cloud Storage in various formats like CSV, JSON, Avro, and Parquet with flexible compression and export options.
Syncs contacts and lists to HubSpot CRM using a private API token, enabling seamless data integration and management.