* refactor(gemini-cli): change agent storage from multiple files to single concatenated file - Update configuration to use .gemini/bmad-method/ directory instead of .gemini/agents/ - Implement new logic to concatenate all agent files into single GEMINI.md - Add backward compatibility for existing settings.json - Remove old agents directory and update related documentation - Ensure all agent settings are properly loaded * fix(ide-setup): change agent trigger symbol from @ to * The change was made to standardize the agent trigger symbol across the system and avoid confusion with other special characters. * docs: update gemini cli syntax and file structure - Change agent mention syntax from @ to * in docs and config - Update file structure documentation from .gemini/agents/ to .gemini/bmad-method/ - Add gemini cli syntax to workflow guide * fix(ide-setup): remove redundant contextFileNames handling
1.0 KiB
1.0 KiB
BMad Method Guide for Gemini CLI
For the complete workflow, see the BMad Workflow Guide.
Installation
When running npx bmad-method install, select Gemini CLI as your IDE. This creates:
.gemini/bmad-method/directory with all agent context in GEMINI.md file
Using BMad Agents with Gemini CLI
Simply mention the agent in your prompt:
- "As *dev, implement the login feature"
- "Acting as *architect, review this system design"
- "*sm, create the next story for our project"
The Gemini CLI automatically loads the appropriate agent context.
Gemini CLI-Specific Features
- Context files: All agents loaded as context in
.gemini/bmad-method/GEMINI.md - Automatic loading: GEMINI.md ensures agents are always available
- Natural language: No special syntax needed, just mention the agent
Tips for Gemini CLI Users
- Be explicit about which agent you're addressing
- You can switch agents mid-conversation by mentioning a different one
- The CLI maintains context across your session