claude-codex-settings

🥈Silver

Claude Code and OpenAI Codex setup with pre-configured skills, commands, and agents for daily operations. Ideal for teams using AI agents to automate workflows, manage GitHub repositories, and integrate with Slack.

579390Updated 3d ago

Intermediate30min to implementautomation

Saves ~90 min per use

Quick InstallView Source

git clone https://github.com/fcakyon/claude-codex-settings.git

Works with:

Claude

Overview

About This Skill

https://github.com/user-attachments/assets/a978cb0a-785d-4a7d-aff2-7e962edd3120

How to Use

1. **Define Your Workflow**: Identify the specific workflows you want to automate (e.g., GitHub issue management, PR reviews, Slack alerts). List the agents, skills, and commands you need using the provided template. 2. **Customize the Configuration**: Edit the `claude-codex-config.yaml` file to match your workflow. Replace placeholders like `[AGENT_NAME]`, `[TRIGGERS]`, and `[ACTIONS]` with your specific requirements. Use the example output as a reference for syntax and structure. 3. **Deploy the System**: Run the deployment command (e.g., `claude-codex --config claude-codex-config.yaml --deploy`) in your target environment (local, cloud, or CI/CD pipeline). Ensure all dependencies (e.g., `claude-codex`, `openai`) are installed. 4. **Test and Iterate**: Trigger test events (e.g., open a GitHub issue, create a PR) to verify the agents are working as expected. Use the `--debug` flag to log actions and troubleshoot issues: ```bash claude-codex --config claude-codex-config.yaml --deploy --debug ``` 5. **Monitor and Optimize**: Track performance metrics (e.g., time saved, error rates) and refine the rules or agents as needed. Use the `--update` command to push changes to the live system: ```bash claude-codex --config claude-codex-config.yaml --update ``` **Tips for Better Results**: - Start with a single workflow (e.g., GitHub issue triage) before expanding to others. - Use the `--dry-run` flag to preview actions without deploying: ```bash claude-codex --config claude-codex-config.yaml --dry-run ``` - Leverage the `code-review-rules.json` file to enforce team-specific coding standards.

Use Cases

Automate the creation and review of pull requests in GitHub to streamline code collaboration.

Integrate Azure services for efficient cloud resource management and monitoring.

Simplify code quality checks and enforce best practices using the code simplifier agent.

Set up notifications for important events or updates directly on your desktop.

Setup & Installation

Quick Install

No install command available. Check the GitHub repository for manual installation instructions.

Alternative Install (Git Clone)

git clone https://github.com/fcakyon/claude-codex-settings

Requirements

Claude Code or compatible AI agent
Works with: Claude

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

Set up a [PURPOSE: e.g., 'GitHub automation workflow', 'Slack integration for customer support', or 'AI-driven code review system'] using Claude Code and OpenAI Codex. Include the following pre-configured settings: [LIST SPECIFIC SKILLS, COMMANDS, OR AGENTS, e.g., 'GitHub issue triage agent', 'Slack bot for deployment alerts', 'Code review agent with pre-approved rules']. Ensure the setup is optimized for [SPECIFIC USE CASE, e.g., 'high-volume repositories', 'real-time team collaboration', or 'automated testing pipelines']. Provide the exact commands or configuration files needed to deploy this system in [TARGET ENVIRONMENT, e.g., 'a local development environment', 'AWS Lambda', or 'a Kubernetes cluster'].

Example Output

Here’s a pre-configured setup for a **GitHub automation workflow** using Claude Code and OpenAI Codex, optimized for a team managing a high-volume repository (e.g., `acme-ai-platform`). This setup includes:

1. **Agents and Skills**:
   - **GitHub Issue Triage Agent**: Automatically labels, assigns, and prioritizes new issues based on keywords (e.g., `bug`, `enhancement`, `docs`) and contributor history. Pre-configured rules:
     - High-priority: Issues labeled `P0` or containing `critical` in the title.
     - Assign to `@core-team` if no assignee within 2 hours.
     - Auto-close stale issues after 30 days of inactivity.
   - **PR Review Agent**: Scans pull requests for common anti-patterns (e.g., untested code, missing docs) and suggests fixes using OpenAI Codex. Pre-loaded with a `code-review-rules.json` file containing:
     ```json
     {
       "rules": [
         {"pattern": "TODO", "action": "comment", "message": "Please resolve TODO before merging."},
         {"pattern": "console.log", "action": "comment", "message": "Remove debug logs before merging."},
         {"pattern": "missing_tests", "action": "request_changes", "message": "Add unit tests for new functionality."}
       ]
     }
     ```

2. **Commands for Deployment**:
   - Clone the repository:
     ```bash
     git clone https://github.com/acme-ai-platform/.github.git && cd .github
     ```
   - Install dependencies:
     ```bash
     pip install claude-codex==1.2.0 openai==0.28.0
     ```
   - Deploy the agents using the provided `claude-codex-config.yaml`:
     ```yaml
     agents:
       - name: github-issue-triage
         type: github_issue_agent
         triggers:
           - event: issues.opened
           - event: issue_comment.created
         actions:
           - label_issue
           - assign_issue
           - comment_on_issue
       - name: pr-review
         type: github_pr_agent
         triggers:
           - event: pull_request.opened
           - event: pull_request.synchronize
         actions:
           - scan_code
           - suggest_changes
     ```
   - Run the setup:
     ```bash
     claude-codex --config claude-codex-config.yaml --deploy
     ```

3. **Integration with Slack**:
   - Configure a Slack bot (`@acme-ai-bot`) to receive real-time alerts for:
     - New high-priority issues.
     - PR review comments or requested changes.
     - Deployment failures (via GitHub Actions).
   - Example Slack message for a new issue:
     > 🚨 **New Issue Alert**
     > **Repo**: acme-ai-platform
     > **Issue**: #1234 - "Memory leak in inference engine"
     > **Priority**: High
     > **Assigned to**: @alice (auto-assigned)
     > [View Issue](https://github.com/acme-ai-platform/issues/1234)

This setup reduces manual triage time by **~60%** and ensures consistent code quality across the repository. The agents are designed to scale with the team’s growth and can be extended with custom rules or additional triggers.