Skip to main content
command CX Codex

help · superclaude-org — Claude Code command: reference for all /sc commands

help is a Claude Code command that lists SuperClaude Framework /sc commands with descriptions. It helps explore the framework’s capabilities.

MIT ★ 23,950 updated 2026-09-27

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/commands/superclaude-help.md
Open on GitHub

What help does

The /sc:help command outputs a reference table of all available /sc commands — ranging from code analysis and architecture design to testing and session management. Each entry includes a short description of what that command does. This is reference mode only: no execution happens, just documentation display.

The output also covers SuperClaude behavioral flags: parameters that control how commands behave. Mode flags like --brainstorm and --introspect shift interaction style. MCP server flags (--serena, --playwright, --magic) unlock specific tool integrations. Analysis depth flags (--think, --think-hard, --ultrathink) scale the reasoning effort. Execution control flags (--safe-mode, --validate, --delegate) manage risk and resource use.

Start here when you're new to the framework or need to recall a command name and what it does.

What it helps with

  • find the right /sc command for a task
  • learn which flags enable specific behavior
  • explore the full capability set of SuperClaude Framework
  • check the syntax and purpose of a command

Example prompts for the agent

  • /sc:help
  • what commands can analyze code?
  • help, I need to design architecture — what do I use?

How to install help

Manually: put the files in place

.claude/commands/superclaude-help.md

The built-in /help overrides a file with the same name, so the file is renamed. Call it with /superclaude-help. For all projects use ~/.claude/commands/

Questions about help

How do I install help in Claude Code?

The /sc:help command is built into SuperClaude Framework for Claude Code. Add the file .claude/commands/superclaude-help.md to your project root to enable the full SuperClaude command set.

What does the help command do?

It displays a reference table of all /sc commands, what each one does, and the behavioral flags you can use. It's informational only — no code runs.

How do I use the flags shown in help?

Pass flags to any /sc command. For example, /sc:analyze --think-hard enables deep analysis, or /sc:implement --all-mcp activates all MCP servers for maximum capability.

Source text

help.md · MIT
---
name: help
description: "List all available /sc commands and their functionality"
category: utility
complexity: low
mcp-servers: []
personas: []
---

# /sc:help - Command Reference Documentation

## Triggers
- Command discovery and reference lookup requests
- Framework exploration and capability understanding needs
- Documentation requests for available SuperClaude commands

## Behavioral Flow
1. **Display**: Present complete command list with descriptions
2. **Complete**: End interaction after displaying information

Key behaviors:
- Information display only - no execution or implementation
- Reference documentation mode without action triggers

Here is a complete list of all available SuperClaude (`/sc`) commands.

| Command | Description |
|---|---|
| `/sc:analyze` | Comprehensive code analysis across quality, security, performance, and architecture domains |
| `/sc:brainstorm` | Interactive requirements discovery through Socratic dialogue and systematic exploration |
| `/sc:build` | Build, compile, and package projects with intelligent error handling and optimization |
| `/sc:business-panel` | Multi-expert business analysis with adaptive interaction modes |
| `/sc:cleanup` | Systematically clean up code, remove dead code, and optimize project structure |
| `/sc:design` | Design system architecture, APIs, and component interfaces with comprehensive specifications |
| `/sc:document` | Generate focused documentation for components, functions, APIs, and features |
| `/sc:estimate` | Provide development estimates for tasks, features, or projects with intelligent analysis |
| `/sc:explain` | Provide clear explanations of code, concepts, and system behavior with educational clarity |
| `/sc:git` | Git operations with intelligent commit messages and workflow optimization |
| `/sc:help` | List all available /sc commands and their functionality |
| `/sc:implement` | Feature and code implementation with intelligent persona activation and MCP integration |
| `/sc:improve` | Apply systematic improvements to code quality, performance, and maintainability |
| `/sc:index` | Generate comprehensive project documentation and knowledge base with intelligent organization |
| `/sc:load` | Session lifecycle management with Serena MCP integration for project context loading |
| `/sc:reflect` | Task reflection and validation using Serena MCP analysis capabilities |
| `/sc:save` | Session lifecycle management with Serena MCP integration for session context persistence |
| `/sc:select-tool` | Intelligent MCP tool selection based on complexity scoring and operation analysis |
| `/sc:spawn` | Meta-system task orchestration with intelligent breakdown and delegation |
| `/sc:spec-panel` | Multi-expert specification review and improvement using renowned specification and software engineering experts |
| `/sc:task` | Execute complex tasks with intelligent workflow management and delegation |
| `/sc:test` | Execute tests with coverage analysis and automated quality reporting |
| `/sc:troubleshoot` | Diagnose and resolve issues in code, builds, deployments, and system behavior |
| `/sc:workflow` | Generate structured implementation workflows from PRDs and feature requirements |

## SuperClaude Framework Flags

SuperClaude supports behavioral flags to enable specific execution modes and tool selection patterns. Use these flags with any `/sc` command to customize behavior.

### Mode Activation Flags

| Flag | Trigger | Behavior |
|------|---------|----------|
| `--brainstorm` | Vague project requests, exploration keywords | Activate collaborative discovery mindset, ask probing questions |
| `--introspect` | Self-analysis requests, error recovery | Expose thinking process with transparency markers |
| `--task-manage` | Multi-step operations (>3 steps) | Orchestrate through delegation, systematic organization |
| `--orchestrate` | Multi-tool operations, parallel execution | Optimize tool selection matrix, enable parallel thinking |
| `--token-efficient` | Context usage >75%, large-scale operations | Symbol-enhanced communication, 30-50% token reduction |

### MCP Server Flags

| Flag | Trigger | Behavior |
|------|---------|----------|
| `--c7` / `--context7` | Library imports, framework questions | Enable Context7 for curated documentation lookup |
| `--seq` / `--sequential` | Complex debugging, system design | Enable Sequential for structured multi-step reasoning |
| `--magic` | UI component requests (/ui, /21) | Enable Magic for modern UI generation from 21st.dev |
| `--morph` / `--morphllm` | Bulk code transformations | Enable Morphllm for efficient multi-file pattern application |
| `--serena` | Symbol operations, project memory | Enable Serena for semantic understanding and session persistence |
| `--play` / `--playwright` | Browser testing, E2E scenarios | Enable Playwright for real browser automation and testing |
| `--all-mcp` | Maximum complexity scenarios | Enable all MCP servers for comprehensive capability |
| `--no-mcp` | Native-only execution needs | Disable all MCP servers, use native tools |

### Analysis Depth Flags

| Flag | Trigger | Behavior |
|------|---------|----------|
| `--think` | Multi-component analysis needs | Standard structured analysis (~4K tokens), enables Sequential |
| `--think-hard` | Architectural analysis, system-wide dependencies | Deep analysis (~10K tokens), enables Sequential + Context7 |
| `--ultrathink` | Critical system redesign, legacy modernization | Maximum depth analysis (~32K tokens), enables all MCP servers |

### Execution Control Flags

| Flag | Trigger | Behavior |
|------|---------|----------|
| `--delegate [auto\|files\|folders]` | >7 directories OR >50 files | Enable sub-agent parallel processing with intelligent routing |
| `--concurrency [n]` | Resource optimization needs | Control max concurrent operations (range: 1-15) |
| `--loop` | Improvement keywords (polish, refine, enhance) | Enable iterative improvement cycles with validation gates |
| `--iterations [n]` | Specific improvement cycle requirements | Set improvement cycle count (range: 1-10) |
| `--validate` | Risk score >0.7, resource usage >75% | Pre-execution risk assessment and validation gates |
| `--safe-mode` | Resource usage >85%, production environment | Maximum validation, conservative execution |

### Output Optimization Flags

| Flag | Trigger | Behavior |
|------|---------|----------|
| `--uc` / `--ultracompressed` | Context pressure, efficiency requirements | Symbol communication system, 30-50% token reduction |
| `--scope [file\|module\|project\|system]` | Analysis boundary needs | Define operational scope and analysis depth |
| `--focus [performance\|security\|quality\|architecture\|accessibility\|testing]` | Domain-specific optimization | Target specific analysis domain and expertise application |

### 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

### Usage Examples

```bash
# Deep analysis with Context7 enabled
/sc:analyze --think-hard --context7 src/

# UI development with Magic and validation
/sc:implement --magic --validate "Add user dashboard"

# Token-efficient task management
/sc:task --token-efficient --delegate auto "Refactor authentication system"

# Safe production deployment
/sc:build --safe-mode --validate --focus security
```

## Boundaries

**Will:**
- Display comprehensive list of available SuperClaude commands
- Provide clear descriptions of each command's functionality
- Present information in readable tabular format
- Show all available SuperClaude framework flags and their usage
- Provide flag usage examples and priority rules

**Will Not:**
- Execute any commands or create any files
- Activate implementation modes or start projects
- Engage TodoWrite or any execution tools

---

**Note:** This list is manually generated and may become outdated. If you suspect it is inaccurate, please consider regenerating it or contacting a maintainer.

© SuperClaude-Org · MIT · SuperClaude-Org/SuperClaude_Framework

Similar slash commands

All slash commands for Agent setup: memory, context, orchestration →

help by other authors comes first.

help official Anthropic help explains the Ralph Loop technique, its iterative cycle, and the commands for starting or cancelling it. Useful when a task needs repeated passes toward a clear result. CX Codex +1 ★ 47,914repo stars help official Anthropic help prints the hookify plugin reference: which events it hooks, how rule files are shaped, and what else the plugin can do. CX Codex +1 ★ 47,914repo stars help composio-community help prints skill-bus status plus its slash-command list. Add advanced to get the longer reference on settings and conditions. CX Codex +1 ★ 2,003repo stars ponytail-help DietrichGebert ponytail-help is a Claude Code skill that displays a quick guide to Ponytail levels, skills, and commands. Call /ponytail-help to show it in one response. CX Codex +1 59,200installs unslop-help MohamedAbdallah-14 unslop-help prints one card listing every unslop mode, sub-skill and exit phrase. Handy when you forget the syntax but do not want to switch anything on. CX Codex +1 ★ 195repo stars reference-docs existential-birds reference-docs is a Claude Code skill for writing API and symbol reference pages, with parameter tables, return values, errors, and runnable examples. CX Codex +1 121installs fa-help FortAwesome fa-help — a skill for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode that answers Font Awesome questions by fetching the official documentation. Answers come from the live docs, not from the model's training data. CX Codex +1 710installs absolute-docs dhruvjainin absolute-docs is a Claude Code skill that structures technical documentation with Diátaxis. It creates and reviews tutorials, how-to guides, reference pages, and architectural explanations from code. CX Codex +1 171installs railway-docs Railway Feeds the agent fresh Railway docs instead of letting it answer from memory. Comes in handy when you ask about deployments, variables or pricing and need accurate details. CX Codex +1 74installs

From the same set56

The whole set →
implement The /sc:implement command coordinates feature development in Claude Code using specialist personas and MCP tools. It handles planning, code generation, and test prep. CX Codex +1 ★ 23,950repo stars task task — a slash command for multi-stage project execution with seven expert personas, intelligent MCP server routing, and cross-session context preservation. User-invoked, runs to completion, then stops. CX Codex +1 ★ 23,950repo stars workflow workflow parses PRDs and feature requirements to generate structured implementation plans with dependency mapping. It plans the execution without touching your code. CX Codex +1 ★ 23,950repo stars brainstorm brainstorm is a command for Claude Code, Codex, GitHub Copilot, and Gemini CLI that clarifies vague project ideas and turns them into requirements before planning. CX Codex +1 ★ 23,950repo stars business-panel-experts business-panel-experts simulates an advisory panel combining Christensen, Porter, Drucker, Taleb, and Collins. Useful for evaluating business models, competitive forces, and structural risks. CX Codex ★ 23,950repo stars socratic-mentor The socratic-mentor subagent teaches programming concepts through guided questions. Use it to examine code, work through Clean Code principles, or identify GoF patterns. CX Codex ★ 23,950repo stars spec-panel spec-panel assembles a virtual panel of recognized software engineers to review and improve technical specifications inside Claude Code. CX Codex +1 ★ 23,950repo stars pm The pm command launches automatically at session start and coordinates all sub-agents while preserving project context via Serena MCP memory. No manual invocation needed—it runs in the background. CX Codex +1 ★ 23,950repo stars

Project sponsors

Companies that keep this analytics open