mode
Purpose
Section titled “Purpose”Switch between behavioral modes to optimize responses for different task types. Modes adjust communication style, output format, and problem-solving approach.
Switch to the specified behavioral mode.
Available Modes
Section titled “Available Modes”| Mode | Description | Best For |
|---|---|---|
default | Balanced standard behavior | General tasks |
brainstorm | Creative exploration, more questions | Design, ideation |
token-efficient | Compressed, concise output | High-volume, cost savings |
deep-research | Thorough analysis, citations | Investigation, audits |
implementation | Code-focused, minimal prose | Executing plans |
review | Critical analysis, finding issues | Code review, QA |
orchestration | Multi-task coordination | Complex parallel work |
Mode Switching
Section titled “Mode Switching”Activate Mode
Section titled “Activate Mode”/mode [mode-name]Check Current Mode
Section titled “Check Current Mode”/mode(Shows current active mode)
Reset to Default
Section titled “Reset to Default”/mode defaultMode Details
Section titled “Mode Details”Default Mode
Section titled “Default Mode”- Standard balanced responses
- Mix of explanation and code
- Normal verification steps
Brainstorm Mode
Section titled “Brainstorm Mode”- Ask more clarifying questions
- Present multiple alternatives
- Explore trade-offs explicitly
- Delay convergence on solutions
Token-Efficient Mode
Section titled “Token-Efficient Mode”- Minimal explanations
- Code-only responses where possible
- Skip obvious context
- 30-70% token savings
Deep-Research Mode
Section titled “Deep-Research Mode”- Thorough investigation
- Evidence and citations
- Confidence levels stated
- Comprehensive analysis
Implementation Mode
Section titled “Implementation Mode”- Jump straight to code
- Progress indicators
- Minimal discussion
- Execute don’t deliberate
Review Mode
Section titled “Review Mode”- Look for issues first
- Categorized findings
- Severity levels
- Actionable feedback
Orchestration Mode
Section titled “Orchestration Mode”- Task breakdown
- Parallel execution planning
- Result aggregation
- Coordination focus
| Flag | Description |
|---|---|
--info | Show detailed mode description |
--list | List all available modes |
Usage Examples
Section titled “Usage Examples”/mode brainstorm # Switch to brainstorm mode/mode token-efficient # Switch to efficient mode/mode # Show current mode/mode --list # List all modes/mode default # Reset to defaultArguments
Section titled “Arguments”$ARGUMENTS
If mode name provided: switch to that mode
If no arguments: show current mode
If --list: show all modes
Mode Persistence
Section titled “Mode Persistence”- Modes persist for the session
- Explicitly switch when task type changes
- Mode affects all subsequent responses
- Can be overridden per-command with flags
Command Flag Override
Section titled “Command Flag Override”Override mode for single command:
/feature --mode=implementation [desc]/review --mode=deep-research [file]/plan --mode=brainstorm [task]Recommended Workflows
Section titled “Recommended Workflows”Feature Development
Section titled “Feature Development”/mode brainstorm # Explore approaches[discuss design]/mode implementation # Execute plan[write code]/mode review # Check quality[review code]Bug Investigation
Section titled “Bug Investigation”/mode deep-research # Investigate thoroughly[analyze bug]/mode implementation # Apply fix[fix bug]/mode default # Return to normalCost-Conscious Session
Section titled “Cost-Conscious Session”/mode token-efficient # Set for session[work on multiple tasks]/mode default # Reset when doneMode Files
Section titled “Mode Files”Mode definitions are in .claude/modes/:
default.mdbrainstorm.mdtoken-efficient.mddeep-research.mdimplementation.mdreview.mdorchestration.md
Customize modes by editing these files.
Gap Analysis Rule
Section titled “Gap Analysis Rule”Always identify gaps and suggest next steps to users. In case there is no gaps anymore, then AI should clearly state that there is no gap left.