Superpowers
An open-source workflow system that gives coding agents structured planning, review, QA, and delivery skills.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for Superpowers, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology. Are you the vendor? Factual corrections are free.
Overview
Superpowers is an open-source agentic skills framework and software development workflow designed for coding agents such as Claude Code and Codex. Its official GitHub repository describes it as a complete software development workflow built on composable skills and initial instructions that guide agents through design refinement, specification writing, implementation planning, subagent-driven execution, and review. Rather than being a standalone chatbot, Superpowers acts as an operational layer that helps coding agents follow disciplined engineering practices like Test-Driven Development, staged implementation, and structured quality checks. It is intended for developers and technical teams that want AI coding agents to behave more systematically and produce more reliable software outcomes.
Key features
- agentic skills
- software workflow
- Test-Driven Development
- design refinement
- code review
- QA
- subagents
- developer tools
- software delivery
- Claude Code
Use cases
- Adding structured planning and implementation workflows to AI coding agents.
- Guiding coding agents through design refinement before code generation begins.
- Improving code quality with staged review, QA, and disciplined software delivery routines.
- Standardizing how Claude Code, Codex, and similar agents are used across software projects.