Skip to content
Agentic Levels
Start hereLevelsTracksPromptsAbout
Get my levelGet my level

  • Start hereYour first useful task with AI.
  • Level quiz8 questions. No AI needed.
  • Fluency ScoreYour Level and a score, from your own AI.

  • LevelsThe 11 levels, in order.
  • LessonsShort lessons, filter by level.
  • TracksGuided paths by tool, role or goal.
  • Set up your AI tool
  • Starter packFree files that help AI remember.

  • PromptsReady prompts to copy and adapt.
  • ChatGPT vs Claude vs GeminiPick the right one for the job.
  • How-tos
  • ReferenceCommands for Claude Code, Codex, Antigravity.
  • ResourcesHand-picked reading and tools.

  • Your progress
  • Your next moveAn interview that picks your next skill.
  • Your next lessonsThe next lessons at your level.
  • Updates

  • Pricing
  • About
  • FAQ & Feedback
  • Work with us
  • How we handle your data
Sign inPreferences
AboutPricingHow-tosPromptsStarter packMy stackHow we handle your data

© 2026 Fuentes Studio

PrivacyTermsRefundsAccessibilityAI content policyCredits
yourCouncil
Ready to help
✦

What do you want to understand?

Ask anything about what you're learning.

←How-to guides
  1. Resources
  2. ›How-to guides

How to use SuperClaude Framework

Configuration framework adding 30 slash commands, 20 AI agents, and 7 behavioral modes to Claude Code, covering the full dev lifecycle from brainstorm to deploy.

Levels 3 to 5On GitHub

By default, Claude Code treats every task the same way. SuperClaude adds a structured layer: 30 /sc:* slash commands, 20 specialized AI agents, 7 behavioral modes, and 8 MCP server integrations that together cover the complete development lifecycle from brainstorming to deployment. Optional MCP servers deliver 2-3x speed improvements and 30-50% token reduction. Available via pipx, npm, and git clone.

Before you start

Claude Code installed and running. SuperClaude installs into your Claude Code config directory. Know where ~/.claude/ is before proceeding.

  1. 1Clone and install the framework
  2. 2Does this fit my harness?
  3. 3Invoke a persona and run a task in its domain
  4. 4Customize a persona for your stack
  5. 5Map a new slash command to a workflow you repeat

Steps

01

Clone and install the framework

SuperClaude installs by copying its config files into your Claude Code settings directory. The installer script handles the copy, it merges into your existing settings rather than overwriting them.

Run these commands
git clone https://github.com/SuperClaude-Org/SuperClaude_Framework cd SuperClaude_Framework python install.py
02

Does this fit my harness?

SuperClaude touches your CLAUDE.md and settings.json. Before installing, ask Claude to evaluate what it will change and whether that conflicts with anything you already have configured.

Ask Claude this
I'm building with [CURRENT_SETUP]. I'm looking at SuperClaude Framework and wondering if I should integrate it or build this capability myself. Here's what I already have: [WHAT_YOU_HAVE] Walk me through: 1. What does SuperClaude do that I would otherwise have to build? 2. What does it assume? Does it conflict with anything I have? 3. What is the integration cost? 4. What do I lose by integrating vs. building my own? End with: integrate, build, or skip.
[CURRENT_SETUP]Your current Claude Code configuration e.g. Claude Code with a custom CLAUDE.md and a few project-level rules
[WHAT_YOU_HAVE]Existing personas, commands, or routing rules e.g. a CLAUDE.md with role instructions and a handful of custom slash commands
03

Invoke a persona and run a task in its domain

SuperClaude ships with named personas: architect, frontend, backend, security, and others. Each has a focused system prompt and commands it handles well. Invoke with its slash command and give it a task in its domain.

Try this in a Claude Code session
/[PERSONA_NAME] [YOUR_TASK]
[PERSONA_NAME]SuperClaude persona name e.g. architect
[YOUR_TASK]A task that fits the persona's domain e.g. Review my current folder structure and suggest a cleaner layout for a Next.js app with a shared component library
04

Customize a persona for your stack

Persona files are plain markdown in `~/.claude/personas/`. Open any one and add stack-specific rules. If you work in Next.js + Supabase, add that context to the frontend persona so it stops suggesting raw SQL when you need Supabase client calls.

05

Map a new slash command to a workflow you repeat

Any task you run the same way more than twice is a candidate for a custom command. Add it to `~/.claude/commands/` as a markdown file. It shows up in the command list on the next Claude Code session.

How do you know it worked?

  • The installer completed without errors and new files appear in `~/.claude/`.
  • At least one persona command works: the model responds with a noticeably different focus than default.
  • You edited a persona file and the change reflected in the next session.
  • You created one custom slash command that encodes a workflow you repeat.

If something looks off

Installer overwrites a setting you care about
Run `git diff` on your Claude Code config dir after installing. If something changed unexpectedly, the git history in your config dir shows what.
Persona bloat adding cognitive overhead
More personas means more to remember. Start with two or three. Add more only when you feel a genuine gap in behavior.
Custom commands drifting from how you actually work
Revisit commands monthly. If you have not used one in two weeks, delete it or rewrite it around a task you actually run.

Skills & Commands Reference

Key SuperClaude slash commands and flags available after installation.

Command / SkillWhat it doesWhen to use it
/sc:analyzeDeep multi-file codebase analysis with pattern and dependency detectionUnderstanding an unfamiliar codebase or auditing before a major refactor
/sc:buildStructured build workflow: plan → implement → verify in sequenceImplementing a feature from spec to working code with a clear audit trail
/sc:reviewCode review covering quality, security, and performance in one passBefore merging or handing code to another developer
/sc:designArchitecture design with explicit trade-off analysis and documentationPlanning a new system or major refactor before writing any code
/sc:debugSystematic debug loop: reproduce → isolate → fix → verifyA bug that hasn't yielded to normal inspection
/[persona]Invoke a named persona (architect, frontend, backend, security, etc.) with domain-focused reasoningNarrowing Claude's focus to a specific discipline for a task in that domain
--ultrathinkadvancedExtended chain-of-thought reasoning before answeringHard algorithmic or architectural problems with many trade-offs
--magicUI/UX generation mode optimised for component and design workBuilding interfaces where design quality matters from the first pass
~/.claude/personas/Editable persona markdown files, add stack-specific conventions to any personaWhen the default persona keeps suggesting things that don't fit your stack
~/.claude/commands/Custom slash command directory, any markdown file here becomes a commandA workflow you run the same way more than twice

What you'll do, 5 steps

  1. 1Clone and install the framework
  2. 2Does this fit my harness?
  3. 3Invoke a persona and run a task in its domain
  4. 4Customize a persona for your stack
  5. 5Map a new slash command to a workflow you repeat

Was this helpful?