Claude Code Commands Manager (claude-cmd) is a lightweight CLI tool for managing Claude commands, configurations, and workflows. It helps operations teams automate and streamline interactions with Claude, improving efficiency in workflow automation and integration with other tools.
git clone https://github.com/kiliczsh/claude-cmd.gitclaude-cmd is a lightweight CLI tool that streamlines management of Claude commands, project configurations, and Model Context Protocol (MCP) servers. It provides an interactive command-line interface for discovering and installing from 184+ available commands, creating project-specific CLAUDE.md configuration files, and managing security profiles. The tool supports both local and remote command repositories, enabling teams to organize custom Claude workflows and automate interactions across projects. With hierarchical configuration management and built-in MCP integration, claude-cmd helps operations and development teams reduce manual setup time and maintain consistent Claude AI configurations.
[{"step":"Install and initialize claude-cmd in your environment. Run `npm install -g claude-cmd` (or use your preferred package manager) and then initialize with `claude-cmd init`. This sets up the CLI tool and creates a default configuration directory at `~/.claude-cmd/`.","tip":"Ensure you have Node.js installed if using npm. For alternative installation methods, check the [claude-cmd GitHub repository](https://github.com/claude-cmd/claude-cmd)."},{"step":"Save or import commands for reuse. Use `claude-cmd save [COMMAND_NAME] --script [SCRIPT_PATH] --tags [TAG1,TAG2]` to store a command in your local library. For example, save a log analysis script with `claude-cmd save analyze-logs --script ./scripts/log-analyzer.sh --tags devops,log-analysis`.","tip":"Tag commands with relevant keywords (e.g., 'devops', 'kubernetes') to make them easier to discover later. Use `claude-cmd list --tag [TAG]` to filter commands."},{"step":"Run saved commands directly from the CLI. Execute `claude-cmd run [COMMAND_NAME] --args [ARGUMENTS]` to trigger the command. For instance, run `claude-cmd run analyze-logs --path /var/log/app --threshold 50` to analyze logs with a 50-error threshold.","tip":"Use `--dry-run` to preview the command’s execution without running it. This is useful for testing complex workflows before deployment."},{"step":"Integrate claude-cmd with your CI/CD pipelines. For example, in GitHub Actions, add a step like `claude-cmd run deploy-service --image ${{ steps.build.outputs.image }} --namespace staging` to automate deployments after a successful build.","tip":"Store sensitive arguments (e.g., API keys) in environment variables and reference them in your claude-cmd configurations. Use `claude-cmd config set [KEY] [VALUE]` to manage settings."},{"step":"Monitor and audit command usage. Use `claude-cmd history` to view recent runs, or `claude-cmd logs --command [COMMAND_NAME]` to inspect the output of a specific command. This helps track performance and debug issues.","tip":"Set up alerts for failed command runs by configuring `claude-cmd` to send notifications to Slack or email. Use `claude-cmd config set notifications.enabled true` and specify your webhook URL."}]
Discovering and installing reusable Claude commands from online repositories
Creating and managing project-specific Claude instructions with CLAUDE.md files
Configuring security profiles and permissions for Claude operations
Managing multiple MCP servers across different projects
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/kiliczsh/claude-cmdCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Use claude-cmd to [TASK]. For example: 'List all saved Claude commands tagged with [TAG].' or 'Run the command named [COMMAND_NAME] with arguments [ARGUMENTS].' Ensure the output is formatted for easy integration into [TARGET_SYSTEM].
```json
{
"commands": [
{
"name": "analyze-logs",
"description": "Parses application logs for errors and generates a summary report.",
"tags": ["devops", "log-analysis"],
"last_run": "2024-05-15T14:30:00Z",
"usage": "claude-cmd run analyze-logs --path /var/log/app --threshold 50"
},
{
"name": "deploy-service",
"description": "Deploys a microservice to Kubernetes with rollback support.",
"tags": ["devops", "kubernetes"],
"last_run": "2024-05-14T09:15:00Z",
"usage": "claude-cmd run deploy-service --image myapp:v1.2.3 --namespace staging"
}
],
"total_commands": 2,
"recent_activity": {
"last_command": "deploy-service",
"status": "success",
"output_path": "/tmp/deploy-service-20240514.log"
}
}
```
**Key Insights:**
- The `analyze-logs` command was last run 2 days ago and is tagged for devops workflows. It’s ideal for proactive error detection in production environments.
- The `deploy-service` command supports Kubernetes deployments with built-in rollback, making it critical for CI/CD pipelines. Its recent successful run indicates stability.
- Both commands integrate seamlessly with GitHub Actions and Jenkins, as confirmed by their configuration files in `~/.claude-cmd/configs/`.
**Next Steps:**
1. Use `claude-cmd run analyze-logs --path /var/log/app --threshold 50` to generate a fresh error report for today’s logs.
2. Schedule the `deploy-service` command in your CI pipeline to trigger deployments automatically after code merges to the `main` branch.AI assistant built for thoughtful, nuanced conversation
Free Accounting Software
IronCalc is a spreadsheet engine and ecosystem
Customer feedback management made simple
Enterprise workflow automation and service management platform
Automate your spreadsheet tasks with AI power
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan