Use Superpowers to give coding agents a structured software-development method with discovery, spec review, planning, TDD, subagents, and review loops.
Scanned 6/8/2026
Install via CLI
openskills install agentskillexchange/skills---
name: "Install Superpowers methodology for coding agents"
slug: "install-superpowers-methodology-for-coding-agents"
description: "Use Superpowers to give coding agents a structured software-development method with discovery, spec review, planning, TDD, subagents, and review loops."
github_stars: 194639
verification: "security_reviewed"
source: "https://github.com/obra/superpowers"
author: "Jesse Vincent"
publisher_type: "individual"
category: "Templates & Workflows"
framework: "Multi-Framework"
tool_ecosystem:
github_repo: "obra/superpowers"
github_stars: 194639
---
# Install Superpowers methodology for coding agents
Use Superpowers to give coding agents a structured software-development method with discovery, spec review, planning, TDD, subagents, and review loops.
## Prerequisites
Supported coding-agent harness such as Claude Code, Codex, Cursor, Gemini CLI, OpenCode, or Factory Droid
## Installation
Basic usage or getting-started notes:
- Give your agent Superpowers: [Claude Code](#claude-code), [Codex CLI](#codex-cli), [Codex App](#codex-app), [Factory Droid](#factory-droid), [Gemini CLI](#gemini-cli), [OpenCode](#opencode), [Cursor](#cursor), [GitHub...
- ## How it works
- It starts from the moment you fire up your coding agent. As soon as it sees that you're building something, it *doesn't* just jump into trying to write code. Instead, it steps back and asks you what you're really tryi...
- Source: https://github.com/obra/superpowers
- Extracted from upstream docs: https://raw.githubusercontent.com/obra/superpowers/HEAD/README.md
## Documentation
- https://github.com/obra/superpowers
## Source
- [Agent Skill Exchange](https://agentskillexchange.com/skills/install-superpowers-methodology-for-coding-agents/)
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.