ContextQMD
Back to Superclaude Framework

SuperClaude Flags Guide 🏁

docs/user-guide/flags.md

4.3.011.1 KB
Original Source

SuperClaude Flags Guide 🏁

Most flags activate automatically - Claude Code 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

FlagWhen ActivatedWhat It Does
--think5+ files OR complex analysisStandard structured analysis (~4K tokens)
--think-hardArchitectural analysis, system dependenciesDeep analysis (~10K tokens) with enhanced tools
--ultrathinkCritical system redesign, legacy modernizationMaximum depth analysis (~32K tokens) with all tools

MCP Server Flags

FlagServerPurposeAuto-Triggers
--c7 / --context7Context7Official docs, framework patternsLibrary imports, framework questions
--seq / --sequentialSequentialMulti-step reasoning, debuggingComplex debugging, system design
--magicMagicUI component generation/ui commands, frontend keywords
--play / --playwrightPlaywrightBrowser testing, E2E validationTesting requests, visual validation
--chrome / --devtoolsChrome DevToolsPerformance analysis, debuggingPerformance auditing, debugging, layout issues
--tavilyTavilyWeb search, real-time infoWeb search requests, research queries
--morph / --morphllmMorphllmBulk transformations, pattern editsBulk operations, style enforcement
--serenaSerenaProject memory, symbol operationsSymbol operations, large codebases

Behavioral Mode Flags

FlagWhen ActivatedWhat It Does
--brainstormVague requests, exploration keywordsCollaborative discovery mindset
--introspectSelf-analysis, error recoveryExpose reasoning process with transparency
--task-manage>3 steps, complex scopeOrchestrate through delegation
--orchestrateMulti-tool operations, performance needsOptimize tool selection and parallel execution
--token-efficient / --ucContext >75%, efficiency needsSymbol-enhanced communication, 30-50% reduction

Execution Control Flags

FlagWhen ActivatedWhat It Does
--loop"improve", "polish", "refine" keywordsIterative enhancement cycles
--safe-modeProduction, >85% resource usageMaximum validation, conservative execution
--validateRisk >0.7, production environmentPre-execution risk assessment
--delegate>7 directories OR >50 filesSub-agent parallel processing

Command-Specific Flags

Analysis Command Flags (/sc:analyze)

FlagPurposeValues
--focusTarget specific domainsecurity, performance, quality, architecture
--depthAnalysis thoroughnessquick, deep
--formatOutput formattext, json, report

Build Command Flags (/sc:build)

FlagPurposeValues
--typeBuild configurationdev, prod, test
--cleanClean before buildBoolean
--optimizeEnable optimizationsBoolean
--verboseDetailed outputBoolean

Design Command Flags (/sc:design)

FlagPurposeValues
--typeDesign targetarchitecture, api, component, database
--formatOutput formatdiagram, spec, code

Explain Command Flags (/sc:explain)

FlagPurposeValues
--levelComplexity levelbasic, intermediate, advanced
--formatExplanation styletext, examples, interactive
--contextDomain contextAny domain (e.g., react, security)

Improve Command Flags (/sc:improve)

FlagPurposeValues
--typeImprovement focusquality, performance, maintainability, style, security
--safeConservative approachBoolean
--interactiveUser guidanceBoolean
--previewShow without executingBoolean

Task Command Flags (/sc:task)

FlagPurposeValues
--strategyTask approachsystematic, agile, enterprise
--parallelParallel executionBoolean
--delegateSub-agent coordinationBoolean

Workflow Command Flags (/sc:workflow)

FlagPurposeValues
--strategyWorkflow approachsystematic, agile, enterprise
--depthAnalysis depthshallow, normal, deep
--parallelParallel coordinationBoolean

Troubleshoot Command Flags (/sc:troubleshoot)

FlagPurposeValues
--typeIssue categorybug, build, performance, deployment
--traceInclude trace analysisBoolean
--fixApply fixesBoolean

Cleanup Command Flags (/sc:cleanup)

FlagPurposeValues
--typeCleanup targetcode, imports, files, all
--safe / --aggressiveCleanup intensityBoolean
--interactiveUser guidanceBoolean
--previewShow without executingBoolean

Estimate Command Flags (/sc:estimate)

FlagPurposeValues
--typeEstimate focustime, effort, complexity
--unitTime unithours, days, weeks
--breakdownDetailed breakdownBoolean

Index Command Flags (/sc:index)

FlagPurposeValues
--typeIndex targetdocs, api, structure, readme
--formatOutput formatmd, json, yaml

Reflect Command Flags (/sc:reflect)

FlagPurposeValues
--typeReflection scopetask, session, completion
--analyzeInclude analysisBoolean
--validateValidate completenessBoolean

Spawn Command Flags (/sc:spawn)

FlagPurposeValues
--strategyCoordination approachsequential, parallel, adaptive
--depthAnalysis depthnormal, deep

Git Command Flags (/sc:git)

FlagPurposeValues
--smart-commitGenerate commit messageBoolean
--interactiveGuided operationsBoolean

Select-Tool Command Flags (/sc:select-tool)

FlagPurposeValues
--analyzeTool analysisBoolean
--explainExplain selectionBoolean

Test Command Flags (/sc:test)

FlagPurposeValues
--coverageInclude coverageBoolean
--typeTest typeunit, integration, e2e
--watchWatch modeBoolean

Advanced Control Flags

Scope and Focus

FlagPurposeValues
--scopeAnalysis boundaryfile, module, project, system
--focusDomain targetingperformance, security, quality, architecture, accessibility, testing

Execution Control

FlagPurposeValues
--concurrency [n]Control parallel ops1-15
--iterations [n]Improvement cycles1-10
--all-mcpEnable all MCP serversBoolean
--no-mcpNative tools onlyBoolean
--frontend-verifyUI testing, frontend debugging, layout validationEnable Playwright + Chrome DevTools + Serena

System Flags (SuperClaude Installation)

FlagPurposeValues
--verbose / -vVerbose loggingBoolean
--quiet / -qSuppress outputBoolean
--dry-runSimulate operationBoolean
--forceSkip checksBoolean
--yes / -yAuto-confirmBoolean
--install-dirTarget directoryPath
--legacyUse legacy scriptBoolean
--versionShow versionBoolean
--helpShow helpBoolean

Common Usage Patterns

Frontend Development

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

Backend Development

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

Large Projects

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

Quality & Maintenance

bash
/sc:improve src/ --type quality --safe --interactive
/sc:cleanup imports --type imports --preview
/sc:reflect --type completion --validate
/sc: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

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

Quick Fixes

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

Flag Priority Rules

  1. Safety First: --safe-mode > --validate > optimization flags
  2. Explicit Override: User flags > auto-detection
  3. Depth Hierarchy: --ultrathink > --think-hard > --think
  4. MCP Control: --no-mcp overrides all individual MCP flags
  5. Scope Precedence: system > project > module > file