Local AI Additions

This fork of obra/superpowers adds support for offloading mechanical generation tasks to a local AI model running via Ollama, while keeping the primary AI agent as the reviewer and decision-maker.

---

What was added

skills/local-implementer/SKILL.md

A new skill that instructs the agent to use a local Ollama model for mechanical, token-heavy generation tasks instead of doing it itself.

When the skill is used:

• Test file first drafts for a handler or module
• Scaffolding new files from known patterns (handler skeletons, config files)
• Simple mechanical rewrites (rename, reformat, translate pattern)
• File summaries

What the skill does NOT do:

• Security or auth decisions
• Architecture or system design
• Debugging or root cause analysis
• Anything requiring judgment across multiple files

Core principle: Local model generates, primary agent reviews. Nothing is written to disk without user confirmation.

---

scripts/ask-local.ps1

Calls the Ollama /api/generate endpoint. Features:

• Lock file to prevent parallel calls (Ollama degrades badly under concurrent load)
• Stale lock detection (auto-clears locks older than 10 minutes)
• Two modes: fast (smaller/faster model) and quality (larger/slower model)
• Low temperature (0.1) for deterministic output
• Timeout handling with clear error messages

.\scripts\ask-local.ps1 -Mode fast -Prompt "Summarise what this file does"
.\scripts\ask-local.ps1 -Mode quality -Prompt "Write a vitest test file for handler.js"

Update these values at the top of the script for your setup:

$OLLAMA_URL    = 'http://localhost:11434/api/generate'   # or remote IP
$MODEL_FAST    = 'qwen2.5-coder:7b'
$MODEL_QUALITY = 'qwen2.5-coder:32b'

---

Setup

1. Install Ollama and pull your preferred models:

   ollama pull qwen2.5-coder:7b
   ollama pull qwen2.5-coder:32b

2. Make Ollama reachable from your dev machine (local network, Tailscale, etc.)

3. Copy scripts/ask-local.ps1 into your project and update the URL/model names

4. Copy .claude/commands/local.md and .claude/commands/local-test.md into your project

5. Add a Local AI section to your project's CLAUDE.md pointing to the script

6. The local-implementer skill is picked up automatically once this plugin is installed

---

Why

Large AI models are good at judgment, architecture, and debugging. They are expensive for high-volume mechanical output (test files, boilerplate). Local models on capable hardware (64GB+ RAM) handle the mechanical work well and are free after the hardware cost. This setup lets you use each where it makes sense.

---

---

Superpowers

Superpowers is a complete software development methodology for your coding agents, built on top of a set of composable skills and some initial instructions that make sure your agent uses them.

Quickstart

Give your agent Superpowers: Claude Code, Codex CLI, Codex App, Factory Droid, Gemini CLI, OpenCode, Cursor, GitHub Copilot CLI.

How it works

It starts from the moment you fire up your coding agent. As soon as it sees that you're building something, it doesn't just jump into trying to write code. Instead, it steps back and asks you what you're really trying to do.

Once it's teased a spec out of the conversation, it shows it to you in chunks short enough to actually read and digest.

After you've signed off on the design, your agent puts together an implementation plan that's clear enough for an enthusiastic junior engineer with poor taste, no judgement, no project context, and an aversion to testing to follow. It emphasizes true red/green TDD, YAGNI (You Aren't Gonna Need It), and DRY.

Next up, once you say "go", it launches a subagent-driven-development process, having agents work through each engineering task, inspecting and reviewing their work, and continuing forward. It's not uncommon for Claude to be able to work autonomously for a couple hours at a time without deviating from the plan you put together.

There's a bunch more to it, but that's the core of the system. And because the skills trigger automatically, you don't need to do anything special. Your coding agent just has Superpowers.

Sponsorship

If Superpowers has helped you do stuff that makes money and you are so inclined, I'd greatly appreciate it if you'd consider sponsoring my opensource work.

Thanks!

• Jesse

Installation

Installation differs by harness. If you use more than one, install Superpowers separately for each one.

Claude Code

Superpowers is available via the official Claude plugin marketplace

Official Marketplace

• Install the plugin from Anthropic's official marketplace:

  /plugin install superpowers@claude-plugins-official

Superpowers Marketplace

The Superpowers marketplace provides Superpowers and some other related plugins for Claude Code.

• Register the marketplace:

  /plugin marketplace add obra/superpowers-marketplace

• Install the plugin from this marketplace:

  /plugin install superpowers@superpowers-marketplace

Codex CLI

Superpowers is available via the official Codex plugin marketplace.

• Open the plugin search interface:

  /plugins

• Search for Superpowers:

  superpowers

• Select Install Plugin.

Codex App

Superpowers is available via the official Codex plugin marketplace.

• In the Codex app, click on Plugins in the sidebar.
• You should see Superpowers in the Coding section.
• Click the + next to Superpowers and follow the prompts.

Factory Droid

• Register the marketplace:

  droid plugin marketplace add https://github.com/obra/superpowers

• Install the plugin:

  droid plugin install superpowers@superpowers

Gemini CLI

• Install the extension:

  gemini extensions install https://github.com/obra/superpowers

• Update later:

  gemini extensions update superpowers

OpenCode

OpenCode uses its own plugin install; install Superpowers separately even if you already use it in another harness.

• Tell OpenCode:

  Fetch and follow instructions from https://raw.githubusercontent.com/obra/superpowers/refs/heads/main/.opencode/INSTALL.md
  

• Detailed docs: docs/README.opencode.md

Cursor

• In Cursor Agent chat, install from marketplace:

  /add-plugin superpowers
  

• Or search for "superpowers" in the plugin marketplace.

GitHub Copilot CLI

• Register the marketplace:

  copilot plugin marketplace add obra/superpowers-marketplace

• Install the plugin:

  copilot plugin install superpowers@superpowers-marketplace

The Basic Workflow

1. brainstorming - Activates before writing code. Refines rough ideas through questions, explores alternatives, presents design in sections for validation. Saves design document.

2. using-git-worktrees - Activates after design approval. Creates isolated workspace on new branch, runs project setup, verifies clean test baseline.

3. writing-plans - Activates with approved design. Breaks work into bite-sized tasks (2-5 minutes each). Every task has exact file paths, complete code, verification steps.

4. subagent-driven-development or executing-plans - Activates with plan. Dispatches fresh subagent per task with two-stage review (spec compliance, then code quality), or executes in batches with human checkpoints.

5. test-driven-development - Activates during implementation. Enforces RED-GREEN-REFACTOR: write failing test, watch it fail, write minimal code, watch it pass, commit. Deletes code written before tests.

6. requesting-code-review - Activates between tasks. Reviews against plan, reports issues by severity. Critical issues block progress.

7. finishing-a-development-branch - Activates when tasks complete. Verifies tests, presents options (merge/PR/keep/discard), cleans up worktree.

The agent checks for relevant skills before any task. Mandatory workflows, not suggestions.

What's Inside

Skills Library

Testing

• test-driven-development - RED-GREEN-REFACTOR cycle (includes testing anti-patterns reference)

Debugging

• systematic-debugging - 4-phase root cause process (includes root-cause-tracing, defense-in-depth, condition-based-waiting techniques)
• verification-before-completion - Ensure it's actually fixed

Collaboration

• brainstorming - Socratic design refinement
• writing-plans - Detailed implementation plans
• executing-plans - Batch execution with checkpoints
• dispatching-parallel-agents - Concurrent subagent workflows
• requesting-code-review - Pre-review checklist
• receiving-code-review - Responding to feedback
• using-git-worktrees - Parallel development branches
• finishing-a-development-branch - Merge/PR decision workflow
• subagent-driven-development - Fast iteration with two-stage review (spec compliance, then code quality)

Meta

• writing-skills - Create new skills following best practices (includes testing methodology)
• using-superpowers - Introduction to the skills system

Philosophy

• Test-Driven Development - Write tests first, always
• Systematic over ad-hoc - Process over guessing
• Complexity reduction - Simplicity as primary goal
• Evidence over claims - Verify before declaring success

Read the original release announcement.

Contributing

The general contribution process for Superpowers is below. Keep in mind that we don't generally accept contributions of new skills and that any updates to skills must work across all of the coding agents we support.

1. Fork the repository
2. Switch to the 'dev' branch
3. Create a branch for your work
4. Follow the writing-skills skill for creating and testing new and modified skills
5. Submit a PR, being sure to fill in the pull request template.

See skills/writing-skills/SKILL.md for the complete guide.

Updating

Superpowers updates are somewhat coding-agent dependent, but are often automatic.

License

MIT License - see LICENSE file for details

Community

Superpowers is built by Jesse Vincent and the rest of the folks at Prime Radiant.

• Discord: Join us for community support, questions, and sharing what you're building with Superpowers
• Issues: https://github.com/obra/superpowers/issues
• Release announcements: Sign up to get notified about new versions