# Superpowers

> Composable agent skills that force brainstorm → plan → TDD → subagent review

**Category:** AI Agents  
**Pricing:** open-source  
**URL:** https://github.com/obra/superpowers  
**GitHub:** https://github.com/obra/superpowers  
**Added:** 2026-09-17

---

## The Hook

Superpowers makes your coding agent stop vibing and follow a real engineering loop before it touches the repo.

## What's Good

MIT (obra/superpowers). A skills pack plus harness hooks so Claude Code, Cursor, Codex, OpenCode, Hermes, Gemini CLI, and peers brainstorm a design, write a bite-sized plan, then run subagent-driven development with red/green TDD and two-stage review. Install paths are first-class per harness (official Claude/Codex marketplaces, `/add-plugin`, `agy plugin install`, etc.). ★~288k with heavy forks — the viral agent-skills methodology, not a one-off prompt dump.

## The Catch

You still need a strong coding harness and model budget; Superpowers is process, not an agent runtime. Optional visual-companion telemetry (opt out via SUPERPOWERS_DISABLE_TELEMETRY / Claude DisableTelemetry). Vs agent-skills (Addy Osmani lifecycle pack) and ECC (multi-host skill ecosystem): Superpowers is the opinionated SDLC methodology that hijacks the session start, not a general skill library or host-agnostic plugin bag.

## Verdict

MIT agent methodology. Install when your agent skips specs and tests; not a replacement for the harness itself.