Build automated AI agents with Claude Code

Research Agent Builder Prompt

How to Install and Set Up Claude Code

1. Open the terminal on your computer.
2. Run the command 'npm i -g @anthropic-ai/claude-code' for a global installation.
3. Navigate to your project directory using the 'cd' command.
4. Launch Claude by typing 'claude' in the terminal.
5. Follow the on-screen instructions to log into your Anthropic account.
6. Grant Permission for Claude to access your project folder when prompted.

How to Build and Use AI Agents in the Terminal

1. Start a Claude session in your terminal.
2. Type the '/agents' command to open the terminal menu for agent management.
3. Select 'Create a new agent' and give it a name (e.g., 'Research Guru').
4. Define the agent scope as either 'Project-specific' or 'Global'.
5. Write a persona or specific task for the agent (System Prompt).
6. Press 'Enter' to save and 'Esc' to return to the main terminal.
7. Use the '@' symbol followed by a document or agent name to mention them in the conversation.
8. Press 'Ctrl+O' to monitor agent activity running in the background.

Running Claude Without Restrictions (Danger Mode)

1. Stop the current Claude session by pressing 'Ctrl+C' twice.
2. Relaunch Claude using the additional argument: 'claude --dangerously-skip-permissions'.
3. Use the 'claude -r' command if you want to resume a previous conversation.
4. The agent will now perform web searches and file edits automatically without asking for manual confirmation every time.

Switching Working Modes (Thinking & Planning)

1. Press 'Tab' while in the Claude terminal to activate 'Thinking Mode' for complex problem-solving.
2. Press 'Shift + Tab' to switch to 'Planning Mode'.
3. In 'Planning Mode', Claude will first outline an action plan.
4. Review the plan and type 'Yes' or 'Approve' to let the AI execute the tasks automatically.