Talk through the design with your coding agent, agree on it, then let the agent build it.

Superbrainstorming is a plugin for Claude Code. When you ask your agent to build something, it asks you a few questions first, shows you a design, and waits for your OK. As soon as you approve, it starts building in the same session.

flowchart LR
    ask["You ask for something"] --> design["Agent asks questions<br/>and proposes a design"]
    design --> approve{"You approve?"}
    approve -->|Not yet| design
    approve -->|Yes| build["Agent builds it"]

Coding agents are good at building things. They can't know what you meant, who it's for, or which trade-offs you care about until someone asks, so a capable agent can still build the wrong thing, and build it well. Superbrainstorming has the agent check with you before it writes any code.

It's a fork of Superpowers by Jesse Vincent and Prime Radiant. Superpowers is a full workflow: brainstorm a design, write a detailed plan, then hand each task to a fresh subagent with test-driven development and code review at every step. That structure helped earlier models stay on track. Current models like Claude Opus 5.5, Sonnet 5.5 and Fable 5.1 can keep an agreed design in context and work through it on their own, so this fork keeps the brainstorming and drops the rest.

First, the agent makes sure it understands what you're after: what you want to achieve, who it's for, and what "done" looks like. It writes that back to you so you can correct it.

Then it picks one of three paths based on the size of the job, and tells you which one so you can overrule it:

Whichever path it takes, nothing gets built until you approve. Once you do, the agent gets started right away. It tracks its own steps, follows your project's conventions for tests and commits, and checks its work before calling it done. If it finds a problem with the design partway through, it stops and asks you instead of quietly changing course. When it's finished, you get a summary of what it built and how it checked it.

If you'd rather skip the design and just build, say so and the agent will.

In Claude Code, run:

/plugin marketplace add harrymunro/superbrainstorming
/plugin install superbrainstorming@superbrainstorming

Then start a new session.

Already using Superpowers? Disable or uninstall it through /plugin first. Both plugins have a brainstorming skill and a session-start hook, and Superpowers' version moves on to writing a plan instead of building.

Try it out: in a fresh session, send Let's make a react todo list. The agent should load the superbrainstorming:brainstorming skill, say it's treating this as architectural work, and ask what the app is for before writing any code.

The skill is a standard SKILL.md in skills/brainstorming/, so any agent that supports Agent Skills can load it. Without the session-start hook it may not kick in on its own, so ask for it by name. Superpowers has integrations for many other tools if you want to port one.

Some questions are easier to answer by looking, like layouts, mockups or diagrams. For those, the agent can offer to open a tab in your browser and show you options there. It's opt-in, needs Node.js, and runs entirely on your machine without loading anything from the internet. Mockups are saved in .superbrainstorming/ in your project, so add that to your .gitignore.

Pick Superbrainstorming if you're using a current frontier model and want a quick design check before the agent gets to work.

Pick Superpowers if you're using smaller or older models, or you want enforced TDD, per-task code review and git worktree management. Its extra structure is there for good reasons, and they still hold for models that need it.

• skills/brainstorming/: the skill and the optional visual companion.
• hooks/: a session-start hook that reminds the agent to brainstorm before building, and to build once you've approved the design.

Run the tests with:

# Visual companion server
cd tests/brainstorm-server && npm ci && npm test

# Session-start hook
bash tests/hooks/test-session-start.sh

Changes to skills/brainstorming/SKILL.md or hooks/bootstrap.md change how the agent behaves, so try them in real sessions before merging. AGENTS.md lists the checks to run.

Superbrainstorming is built on Superpowers, created by Jesse Vincent and the team at Prime Radiant. The brainstorming skill and visual companion are their work, and the full upstream git history is kept in this repo. Please report problems with this fork here, not upstream.

MIT. See LICENSE.