agent-modes
Agent Modes Skill
Guidance on choosing and using the right agent mode for your task.
When to Use
Use this skill when:
- Selecting the right mode for a task
- Explaining mode capabilities
- Switching between modes
- Understanding mode-specific workflows
Mode Selection
Agent Mode (Default)
Best for: Complex features, refactoring, autonomous exploration
Use when:
- Implementing features requiring multiple file changes
- Refactoring across codebase
- Clear, well-defined tasks
- Need autonomous exploration and fixes
Example:
- "Add a new API endpoint for goals"
- "Refactor authentication system"
- "Update components to new design system"
Ask Mode
Best for: Learning, planning, read-only exploration
Use when:
- Learning about unfamiliar code
- Understanding system architecture
- Planning before implementation
- Exploring codebase structure
Example:
- "How does authentication work?"
- "Explain memory extraction flow"
- "What happens when user submits form?"
Plan Mode
Best for: Complex features requiring planning
Use when:
- Complex features with multiple approaches
- Tasks touching many files/systems
- Unclear requirements
- Architectural decisions need review
Example:
- "Add user preferences system"
- "Implement real-time notifications"
- "Refactor data layer"
Workflow:
- Agent asks clarifying questions
- Researches codebase
- Creates implementation plan
- You review and edit plan
- Click to build when ready
Debug Mode
Best for: Tricky bugs, regressions
Use when:
- Bugs you can reproduce but can't figure out
- Race conditions and timing issues
- Performance problems
- Regressions
Example:
- "Audio streaming stops after 30 seconds"
- "Memory extraction fails for some conversations"
- "BLE connection drops intermittently"
Workflow:
- Explore and hypothesize
- Add instrumentation
- Reproduce bug
- Analyze logs
- Make targeted fix
- Verify and clean up
Mode Switching
- Use mode picker dropdown
- Press
Cmd+.(Mac) orCtrl+.(Windows/Linux) - Set keyboard shortcuts in settings
Related Resources
- Rule:
.cursor/rules/agent-modes.mdc - Commands:
/plan,/ask,/debug
More from basedhardware/omi
local-dev
Start local development environment — backend, macOS app, or Flutter mobile in iOS simulator. Use when: 'run the app', 'start backend', 'run simulator', 'flutter run', 'local dev', 'start dev environment', 'run mobile app'.
45rotate-key
Rotate an API key or secret across all locations — local .env files, macOS Keychain, GCP Secret Manager, Kubernetes deployments, and Codemagic CI. Use when: 'rotate key', 'update key', 'key leaked', 'replace secret', 'new API key', 'update GEMINI key', 'rotate secret'.
26self-improvement
Meta-skill for analyzing PRs, issues, and user interactions to improve Cursor rules and skills automatically
14debug-mode
Debug mode workflows and best practices for troubleshooting bugs, regressions, and performance issues. Use when debugging tricky issues that standard agent interactions struggle with.
13docs-automation
Automate documentation updates when API endpoints, functions, or architecture change. Detects code changes that require doc updates, generates API reference from FastAPI routers, updates architecture diagrams, and syncs between internal and external docs.
13omi-flutter-patterns
Flutter Dart BLE device communication state management Provider backend integration localization cross-platform iOS Android
13