Skip to content
Sign in
  • Browse all toolsFilter by category and pricing
  • Browse categoriesWriting, code, image, audio and more
  • Compare toolsPut up to three side by side
  • Read the blogGuides and comparisons

Superpowers

Open-source skills framework for coding agents, with design planning, test-driven development, and code review.

Superpowers is an open-source skills framework and software development methodology that guides coding agents through design, planning, implementation, testing, and review. Superpowers serves developers and enterprise teams using AI coding agents and is available under the MIT license, with commercial enterprise services offered separately.

Updated 28 Oct 20266 sections

At a glance

Pricing
FreeOpen-source project under the MIT license. Commercial support, additional tooling, and managed spending are available for enterprise users by contacting the team.
Added
28 Oct 2026
Superpowers website screenshot

What is Superpowers?

Superpowers is an open-source skills framework and software development methodology for coding agents. Superpowers combines composable skills with initial instructions that direct agents to use those skills during development. Built by Jesse Vincent and the team at Prime Radiant, Superpowers serves developers who want their coding agents to clarify requirements, agree on designs, and follow implementation plans.

Superpowers begins with questions about what the user wants to build rather than immediate code generation. The agent presents its understanding for correction and seeks design approval before planning implementation. The documented methodology emphasizes test-driven development, avoiding unnecessary functionality, and avoiding duplication.

What Superpowers can do

Superpowers supplies skills covering planning, implementation, testing, debugging, and collaboration. The agent checks for relevant skills before tasks, and the repository describes these workflows as mandatory rather than suggestions. Execution can use task-specific subagents with individual reviews or remain within the current session with a final branch review.

  • Superpowers draws out requirements through brainstorming and design discussion.
  • Superpowers creates implementation tasks with file paths, code, and verification steps.
  • Superpowers sets up isolated Git worktrees and checks the test baseline.
  • Superpowers applies a failing-test, passing-test, and refactoring workflow.
  • Superpowers reviews work against the plan and blocks progress on critical issues.
  • Superpowers provides systematic debugging and verification-before-completion skills.
  • Superpowers diagnoses session problems using transcript evidence.

How Superpowers works

Superpowers installs through the mechanism supported by each coding-agent environment. Claude Code and Codex offer official plugin marketplace options, while Cursor supports marketplace installation from Agent chat. Gemini CLI uses an extension installation command, and other environments have their own documented instructions. Superpowers must be installed separately in each environment used.

Superpowers moves from brainstorming to design approval, an isolated workspace, and an implementation plan. After approval to proceed, the agent executes tasks with testing and review. At completion, the branch-finishing skill verifies tests and presents merge, pull request, keep, or discard options before worktree cleanup.

Who Superpowers is for

Superpowers is for developers using coding agents to build and maintain software, including enterprise users seeking commercial assistance. The documented use cases span requirements discovery, task execution, debugging, and branch completion. Superpowers also supports investigating agent behavior when a session ignores its plan, repeats work, or consumes more tokens than expected.

  • Superpowers helps developers turn conversations into agreed software designs.
  • Superpowers supports task-by-task implementation with testing and review.
  • Superpowers helps developers investigate bugs and verify fixes.
  • Superpowers helps users diagnose unexpected coding-agent session behavior.

Superpowers pricing and access

Superpowers is an open-source project available from a public GitHub repository under the MIT license. The repository documents installation through plugin marketplaces, repository-based commands, and local checkout options, depending on the environment. Superpowers also offers an enterprise contact route for commercial support, additional tooling, and managed spending; the page does not list prices for those services.

Superpowers strengths and limitations

Superpowers combines requirements clarification, implementation planning, testing, and review within a defined agent workflow. Multiple installation options and composable skills support different coding environments. However, the repository explicitly acknowledges sessions where skills trigger incorrectly, remain silent, or fail to keep the agent on plan, and provides a diagnostic skill for investigating those problems.

  • Superpowers requires a separate installation for each coding-agent environment.
  • Superpowers can experience missed skill triggers or deviations from the approved plan.
  • Superpowers loses its bootstrap if a Hermes Agent session compacts over its first turn; a fresh session may be needed.

Superpowers FAQ

What is Superpowers?

Superpowers is an open-source agentic skills framework and software development methodology for coding agents. Superpowers uses composable skills to guide requirements discovery, design approval, implementation planning, test-driven development, debugging, and code review.

Is Superpowers free?

Superpowers is available as an open-source project under the MIT license through its public GitHub repository. Superpowers also offers enterprise commercial support, additional tooling, and managed spending through direct contact, but the page does not publish service prices.

Which coding agents support Superpowers?

Superpowers documents installation for Claude Code, Antigravity, Codex App, Codex CLI, Cursor, Devin CLI, Factory Droid, Gemini CLI, GitHub Copilot CLI, Grok Build CLI, Kimi Code, OpenCode, Pi, Qwen Code, Hermes Agent, and Muse. Superpowers requires separate installation for each environment.

How does Superpowers handle testing and code review?

Superpowers includes a test-driven development skill that requires a failing test before minimal implementation and refactoring. Superpowers reviews work against the implementation plan, reports issues by severity, blocks progress on critical issues, and verifies tests before branch completion.

Can Superpowers diagnose problems with an agent session?

Superpowers includes a diagnosing-superpowers skill for investigating incorrect skill triggers, ignored plans, repeated work, or unexpected token consumption. Superpowers reads the session transcript, reports findings with line-level evidence, and can package a scrubbed bundle for a bug report.

From the community

No reviews yet

Be the first to review this tool. What you write helps the next person choose.

More tools like Superpowers

Emdash

www.emdash.ai

Open-source development environment for parallel coding agents, scheduled tasks, and code review.

Free

ECC

www.github.com

Open-source skills, agents, memory, and security tools for coordinated AI coding workflows.

Freemium

Agent of Empires

www.github.com

Manage parallel AI coding agents through persistent terminal sessions, a web dashboard, and mobile browser access.

Free

Claude Code Templates

www.github.com

Open-source CLI for configuring Claude Code with agents, commands, MCP integrations, hooks, and monitoring tools.

Free