Superpowers
An agentic skills framework & software development methodology that works. observed · 2026-08-28
Health v2 · maintenance only
83/100
- Activity 98
- Release rhythm 97
- Longevity 23
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.
- gap_med: 7
- age_days: 328
- days_rel: 21
- days_push: 14
- n_releases_24m: 12
Adoption not part of the score
278117 stars · 24888 forks observed · 2026-08-28
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded
Superpowers is an agentic skills framework that installs a complete software development methodology into coding agents like Claude Code, Codex, Cursor, and Gemini CLI. It composes skills for spec elicitation, planning, and subagent-driven development with TDD so agents can work autonomously on engineering tasks.
Use cases
- make my coding agent follow a structured SDLC instead of jumping straight to code
- run subagent-driven development with automatic code review
- enforce red/green TDD and YAGNI in AI-assisted coding
- have an agent autonomously implement a plan for hours without drifting
- turn brainstorming conversations into a signed-off spec and implementation plan
- install reusable skills across multiple coding agent harnesses
When to choose
- you use Claude Code, Codex, Cursor, or similar agents and want disciplined, spec-first development workflows
- you want long autonomous coding sessions with built-in review and testing rigor
- you want a composable, MIT-licensed skills system you can extend
When to avoid
- you want a one-shot code generator without process overhead
- your project is too small to benefit from specs, plans, and subagent orchestration
- you need a GUI application or non-agent development tool
Facets
framework · maturity active
agent-framework developer-tools workflow-automation testing developer-tools large-language-models cli cross-platform coding-agents skills sdlc subagent-driven-development tdd claude-code prompting methodology ai-agents automation
1 source
- readme: https://github.com/obra/superpowers · fetched 2026-08-28 · ed06493d0a41
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| obra/superpowers | main | 83 |
| obra/superpowers-marketplace | plugin | 60 |
For agents
markdown · JSON · MCP: product_card(name="obra/superpowers")
Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem