GemBoost Flags Guide 🏁

Most flags activate automatically - Gemini Cli reads behavioral instructions to engage appropriate contexts based on keywords and patterns in your requests.

Essential Auto-Activation Flags (90% of Use Cases)

Core Analysis Flags

Flag	When Activated	What It Does
--think	5+ files OR complex analysis	Standard structured analysis (~4K tokens)
--think-hard	Architectural analysis, system dependencies	Deep analysis (~10K tokens) with enhanced tools
--ultrathink	Critical system redesign, legacy modernization	Maximum depth analysis (~32K tokens) with all tools

MCP Server Flags

Flag	Server	Purpose	Auto-Triggers
--c7 / --context7	Context7	Official docs, framework patterns	Library imports, framework questions
--seq / --sequential	Sequential	Multi-step reasoning, debugging	Complex debugging, system design
--magic	Magic	UI component generation	/ui commands, frontend keywords
--play / --playwright	Playwright	Browser testing, E2E validation	Testing requests, visual validation
--morph / --morphllm	Morphllm	Bulk transformations, pattern edits	Bulk operations, style enforcement
--serena	Serena	Project memory, symbol operations	Symbol operations, large codebases

Behavioral Mode Flags

Flag	When Activated	What It Does
--brainstorm	Vague requests, exploration keywords	Collaborative discovery mindset
--introspect	Self-analysis, error recovery	Expose reasoning process with transparency
--task-manage	>3 steps, complex scope	Orchestrate through delegation
--orchestrate	Multi-tool operations, performance needs	Optimize tool selection and parallel execution
--token-efficient / --uc	Context >75%, efficiency needs	Symbol-enhanced communication, 30-50% reduction

Execution Control Flags

Flag	When Activated	What It Does
--loop	"improve", "polish", "refine" keywords	Iterative enhancement cycles
--safe-mode	Production, >85% resource usage	Maximum validation, conservative execution
--validate	Risk >0.7, production environment	Pre-execution risk assessment
--delegate	>7 directories OR >50 files	Sub-agent parallel processing

Command-Specific Flags

Analysis Command Flags (`/gb:analyze`)

--focusTarget specific domain

Values: security, performance, quality, architecture

--depthAnalysis thoroughness

Values: quick, deep

--formatOutput format

Values: text, json, report

Build Command Flags (`/gb:build`)

--typeBuild configuration

Values: dev, prod, test

--cleanClean before build

Boolean

--optimizeEnable optimizations

Boolean

--verboseDetailed output

Boolean

Design Command Flags (`/gb:design`)

--typeDesign target

Values: architecture, api, component, database

--formatOutput format

Values: diagram, spec, code

Explain Command Flags (`/gb:explain`)

--levelComplexity level

Values: basic, intermediate, advanced

--formatExplanation style

Values: text, examples, interactive

--contextDomain context

Any domain (e.g., react, security)

Improve Command Flags (`/gb:improve`)

--typeImprovement focus

Values: quality, performance, maintainability, style, security

--safeConservative approach

Boolean

--interactiveUser guidance

Boolean

--previewShow without executing

Boolean

Task Command Flags (`/gb:task`)

--strategyTask approach

Values: systematic, agile, enterprise

--parallelParallel execution

Boolean

--delegateSub-agent coordination

Boolean

Workflow Command Flags (`/gb:workflow`)

--strategyWorkflow approach

Values: systematic, agile, enterprise

--depthAnalysis depth

Values: shallow, normal, deep

--parallelParallel coordination

Boolean

Troubleshoot Command Flags (`/gb:troubleshoot`)

--typeIssue category

Values: bug, build, performance, deployment

--traceInclude trace analysis

Boolean

--fixApply fixes

Boolean

Cleanup Command Flags (`/gb:cleanup`)

--typeCleanup target

Values: code, imports, files, all

--safe / --aggressiveCleanup intensity

Boolean

--interactiveUser guidance

Boolean

--previewShow without executing

Boolean

Test Command Flags (`/gb:test`)

--coverageInclude coverage

Boolean

--typeTest type

Values: unit, integration, e2e

--watchWatch mode

Boolean

Advanced Control Flags

Scope and Focus

--scopeAnalysis boundary

Values: file, module, project, system

--focusDomain targeting

Values: performance, security, quality, architecture, accessibility, testing

Execution Control

--concurrency [n]Control parallel ops

Range: 1-15

--iterations [n]Improvement cycles

Range: 1-10

--all-mcpEnable all MCP servers

Boolean

--no-mcpNative tools only

Boolean

System Flags (GemBoost Installation)

--verbose / -v

Verbose logging (Boolean)

--quiet / -q

Suppress output (Boolean)

--dry-run

Simulate operation (Boolean)

--force

Skip checks (Boolean)

--yes / -y

Auto-confirm (Boolean)

--install-dir

Target directory (Path)

--legacy

Use legacy script (Boolean)

--version

Show version (Boolean)

--help

Show help (Boolean)

Common Usage Patterns

Frontend Development

/gb:implement "responsive dashboard" --magic --c7
/gb:design component-library --type component --format code
/gb:test ui-components/ --magic --play
/gb:improve legacy-ui/ --magic --morph --validate

Backend Development

/gb:analyze api/ --focus performance --seq --think
/gb:design payment-api --type api --format spec
/gb:troubleshoot "API timeout" --type performance --trace
/gb:improve auth-service --type security --validate

Large Projects

/gb:analyze . --ultrathink --all-mcp --safe-mode
/gb:workflow enterprise-system --strategy enterprise --depth deep
/gb:cleanup . --type all --safe --interactive
/gb:estimate "migrate to microservices" --type complexity --breakdown

Quality & Maintenance

/gb:improve src/ --type quality --safe --interactive
/gb:cleanup imports --type imports --preview
/gb:reflect --type completion --validate
/gb:git commit --smart-commit

Flag Interactions

Compatible Combinations

• --think + --c7: Analysis with documentation
• --magic + --play: UI generation with testing
• --serena + --morph: Project memory with transformations
• --safe-mode + --validate: Maximum safety
• --loop + --validate: Iterative improvement with validation

Conflicting Flags

• --all-mcp vs individual MCP flags (use one or the other)
• --no-mcp vs any MCP flags (--no-mcp wins)
• --safe vs --aggressive (cleanup intensity)
• --quiet vs --verbose (output level)

Auto-Enabling Relationships

• --safe-mode auto-enables --uc and --validate
• --ultrathink auto-enables all MCP servers
• --think-hard auto-enables --seq + --c7
• --magic triggers UI-focused agents

Troubleshooting Flags

Common Issues

• Too many tools: Use --no-mcp to test with native tools only
• Operation too slow: Add --uc to compress output
• Validation blocking: Use --validate instead of --safe-mode in development
• Context pressure: Auto-activates --token-efficient at >75% usage

Debug Flags

/gb:analyze . --verbose                      # Shows decision logic and flag activation
/gb:select-tool "operation" --explain        # Explains tool selection process
/gb:reflect --type session --analyze         # Reviews current session decisions

Quick Fixes

/gb:analyze . --help                         # Shows available flags for command
/gb:analyze . --no-mcp                       # Native execution only
/gb:cleanup . --preview                      # Shows what would be cleaned

Flag Priority Rules

Safety First:--safe-mode > --validate > optimization flags

Explicit Override:User flags > auto-detection

Depth Hierarchy:--ultrathink > --think-hard > --think

MCP Control:--no-mcp overrides all individual MCP flags

Scope Precedence:system > project > module > file

GemBoost Flags Guide 🏁

Essential Auto-Activation Flags (90% of Use Cases)

Core Analysis Flags

MCP Server Flags

Behavioral Mode Flags

Execution Control Flags

Command-Specific Flags

Analysis Command Flags (/gb:analyze)

Build Command Flags (/gb:build)

Design Command Flags (/gb:design)

Explain Command Flags (/gb:explain)

Improve Command Flags (/gb:improve)

Task Command Flags (/gb:task)

Workflow Command Flags (/gb:workflow)

Troubleshoot Command Flags (/gb:troubleshoot)

Cleanup Command Flags (/gb:cleanup)

Test Command Flags (/gb:test)

Advanced Control Flags

Scope and Focus

Execution Control

System Flags (GemBoost Installation)

Common Usage Patterns

Frontend Development

Backend Development

Large Projects

Quality & Maintenance

Flag Interactions

Compatible Combinations

Conflicting Flags

Auto-Enabling Relationships

Troubleshooting Flags

Common Issues

Debug Flags

Quick Fixes

Flag Priority Rules

Analysis Command Flags (`/gb:analyze`)

Build Command Flags (`/gb:build`)

Design Command Flags (`/gb:design`)

Explain Command Flags (`/gb:explain`)

Improve Command Flags (`/gb:improve`)

Task Command Flags (`/gb:task`)

Workflow Command Flags (`/gb:workflow`)

Troubleshoot Command Flags (`/gb:troubleshoot`)

Cleanup Command Flags (`/gb:cleanup`)

Test Command Flags (`/gb:test`)