Superpowers

Install

/plugin install superpowers@claude-plugins-official

This is third-party code. Review the repository files before installing.

What it does

Before writing code the agent clarifies what is needed and presents the design in chunks for approval. It then writes a plan of small tasks with file paths and verification steps and executes it through subagents with a two-stage review. Skills trigger automatically by context: test-driven-development, systematic-debugging, using-git-worktrees, requesting-code-review, finishing-a-development-branch and more. Each harness has its own install path, including the official Claude Code and Codex marketplaces.

Who it is for. Developers who want the agent to follow a disciplined process and execute a plan for long stretches without drifting.

Example request

I want to add CSV report export to the app, let's discuss the design first

Limitations

The process is mandatory: even simple tasks go through an intent approval. The TDD skill deletes code written before tests. It must be installed separately for each harness. The maintainers generally do not accept new community skills.

How to disable. Remove the plugin through your agent's plugin manager. The telemetry logo load is disabled with SUPERPOWERS_DISABLE_TELEMETRY; DISABLE_TELEMETRY and CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC are honored too.

Security check

• Registers a session-start hook
• Agents and subagents work autonomously for long periods and run commands in the project
• Loads a logo from the authors' site by default

README in short

Superpowers is described as a complete software development methodology for coding agents built on composable skills. The core workflow covers brainstorming, git worktrees, plan writing, subagent execution, TDD, code review and branch completion. Installation is documented for Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot CLI, OpenCode and several other harnesses. It is built by Jesse Vincent and the Prime Radiant team. MIT license.

SKILL.md

---
name: brainstorming
description: "You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation."
---

# Brainstorming Ideas Into Designs

Help turn ideas into fully formed designs and specs through natural collaborative dialogue.

Start by classifying how much process the request needs, then work
through your path: understand the context, refine the idea, present a
design, and get your human partner's approval.

<HARD-GATE>
Do NOT invoke any implementation skill, write any code, scaffold any
project, or take any implementation action until you have told your
human partner what you intend and they have approved it. This applies
to EVERY task on EVERY path below — the ceremony scales with the task;
the approval gate never does.
</HARD-GATE>

## Three Paths

Before your first question, classify the request and say the
classification out loud — "this looks bounded, so I'll present a short
design here rather than write a spec" — so your human partner can
override it:

- **Spike** — a feasibility question ("can we...", "is it possible...",
  "quick and dirty is fine") whose output is an answer, not code you
  keep. Present the question and what you'll try in 2-3 sentences, get
  a nod, then find out as cheaply as correctness allows. No design
  doc, no spec file. Report findings as a recommendation; anything you
  built stays labeled throwaway.
- **Bounded** — a well-scoped change to code that already exists in
  this repo: a new flag, a small endpoint, a one-file fix.
  Understanding the kind of app is not enough — bounded means the flow
  you are changing is already here to read. If there is no existing
  flow to change, the task is not bounded. Ask the clarifying
  questions that matter, present a short design IN CHAT (a few
  sentences to a few short paragraphs), and STOP. Implementation
  starts only after your human partner says yes to that design — a
  bounded task's approval is as hard a gate as an architectural
  one. No spec file, no implementation plan document.
- **Architectural** — new projects, new subsystems, changes that
  restructure how components fit together or alter interfaces others
  depend on. Follow the full process: questions, approaches, sectioned
  design, written spec, then the writing-plans skill.

When in doubt between two paths, take the heavier one. The ratchet is
one-way: hidden complexity discovered mid-task upgrades the path —
stop, say so, and step up. Nothing downgrades mid-task.

Related