---
title: "dotpowers"
description: "The superpowers dev methodology as a DOT pipeline — brainstorms your idea, plans with TDD, builds it with multi-model review, and ships."
canonical_url: "https://2389.ai/products/dotpowers/"
last_updated: "2026-03-17T11:10:28-05:00"
doc_version: "1.0"
date: 2026-03-11
product_type: "Tool"
status: "Alpha"
tags: ["pipeline", "dot", "graphviz", "superpowers", "tdd", "multi-model", "code-review", "agents", "orchestration", "claude-code"]
---

# dotpowers

> The superpowers dev methodology as a DOT pipeline — brainstorms your idea, plans with TDD, builds it with multi-model review, and ships.


You write `echo "a dvd bouncing tui" > idea.md`, point a runner at `dotpowers.dot`, and come back to a tested, reviewed project in a git branch. One DOT file, ~1300 lines. It encodes the [superpowers](https://github.com/obra/superpowers) dev methodology as a pipeline graph — brainstorming, planning, TDD implementation, multi-model review, and shipping decisions, all wired together with failure handling and human gates.

## Install

```bash
git clone https://github.com/2389-research/dotpowers.git
```

Run it with any [attractor](https://github.com/strongdm/attractor)-compliant DOT runner:

```bash
mkdir my-project && cd my-project
echo "a terminal dashboard that shows system metrics" > idea.md
git init

# tracker, mammoth, smasher — whatever you have
tracker /path/to/dotpowers.dot --tui
```

## What it does

**Six phases from idea to shipping decision.** Brainstorm reads your idea and asks questions one at a time (YAGNI enforced), then writes a design brief with 2-3 architectural approaches. Plan has GPT-5.2 draft a TDD plan, a shell script reject vague steps, and Opus audit every requirement against the brief — up to 5 iterations. Setup creates a feature branch and installs deps. Implement runs a TDD loop per task: failing test, minimal code, spec review (Opus), quality review (GPT-5.4), commit. Review has three models independently review the finished project, then each critiques the other two (6 cross-critiques), and Opus makes the call. Ship lets you merge locally, push a PR, keep the branch, or discard it.

**Four models, each doing what it's best at.** Opus 4.6 handles spec audits, consensus decisions, and debugging. GPT-5.4 writes the code. GPT-5.2 drafts and patches plans. Gemini 3.5 Flash provides the third opinion in reviews.

**Graduated failure handling.** When something breaks, the pipeline tries four things before asking you: retry the node (up to 2 times), run a debug investigation with root cause analysis, replan the task with a revised approach, then escalate to a human gate. Loop caps prevent runaway token burn — plan validation gets 5 iterations, implementation review gets 5 per task, final rework gets 2 full cycles.

**Human-in-the-loop, not human-on-the-hook.** You approve the design brief. You review batch checkpoints every 3 completed tasks. You choose how to ship. If the implementer has questions, it pauses and asks. The pipeline runs headless between those gates.

## How it works

The pipeline is a single Graphviz DOT file. Each node is either an LLM prompt (with model assignment via CSS-like stylesheets), a shell script (format validation, counter management, build verification), or a human gate (design approval, batch review, shipping decision). Edges encode success/failure routing, loop-backs, and escalation paths.

State lives in two places: `docs/plans/` for artifacts the LLMs read and write (brainstorm notes, design brief, TDD plan, audit results), and `.tracker/` for pipeline mechanics (loop counters, batch counts, checkpoint data). The plans directory is committed; the tracker directory is gitignored.

Fan-out nodes run the three final reviews in parallel. Fan-in nodes collect the results before cross-critiques begin. The consensus node reads all reviews and critiques, then routes to ship, rework, or fail.

## Requirements

- An [attractor](https://github.com/strongdm/attractor)-compliant DOT runner ([tracker](https://github.com/2389-research/tracker), [mammoth](https://github.com/2389-research/mammoth), [smasher](https://github.com/2389-research/smasher))
- API keys for OpenAI, Anthropic, and Google (in `.env` or environment variables)
- git
- The language toolchain for whatever you're building (Rust, Python/uv, Node, Go — the plan specifies the stack)


## Sitemap

Parent: [Products](https://2389.ai/products/index.md)

Related pages in this section:

- [Skills Marketplace](https://2389.ai/products/skills-marketplace/index.md)
- [Mammoth](https://2389.ai/products/mammoth/index.md)
- [BotBoard](https://2389.ai/products/botboard/index.md)
- [Smasher](https://2389.ai/products/smasher/index.md)
- [Jeff](https://2389.ai/products/jeff/index.md)
- [Mux](https://2389.ai/products/mux/index.md)
- [ISH](https://2389.ai/products/ish/index.md)
- [Coven](https://2389.ai/products/coven/index.md)
- [Soloclaw](https://2389.ai/products/soloclaw/index.md)
- [ccvault](https://2389.ai/products/ccvault/index.md)


Site index: [llms.txt](https://2389.ai/llms.txt) · [sitemap.md](https://2389.ai/sitemap.md) · [HTML](https://2389.ai/products/dotpowers/)