Megapowers banner
lawzava lawzava

Megapowers

Development community

Description

Skills, plugins, and hooks that change how coding agents work — Claude Code, Codex, OpenCode, Antigravity. Measured, not vibed.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

megapowers

[![CI](https://github.com/lawzava/megapowers/actions/workflows/ci.yml/badge.svg)](https://github.com/lawzava/megapowers/actions/workflows/ci.yml) [![Latest tag](https://img.shields.io/github/v/tag/lawzava/megapowers?label=release)](https://github.com/lawzava/megapowers/tags) [![License](https://img.shields.io/github/license/lawzava/megapowers)](./LICENSE)

megapowers is exactly one plugin for current Claude Code and Codex. It adds fifteen task-level skills, one shared default communication style, and a small destructive-command tripwire. It does not replace native agents, plans, goals, permissions, worktrees, memory, or browser tools.

The plugin is deliberately small. There is no model router, session catalog, formatter, status line, custom scheduler, hosted service, or compatibility layer for other harnesses.

Install

Claude Code:

claude plugin marketplace add lawzava/megapowers
claude plugin install megapowers@megapowers

Codex:

codex plugin marketplace add lawzava/megapowers
codex plugin add megapowers@megapowers

Start a fresh session after installation. Full update, verification, pinning, and uninstall instructions are in [docs/install.md](./docs/install.md).

The workflow

Use the smallest skill that matches the task. Skill descriptions stay visible; the full body loads only when selected.

Need Skill
Choose between inline work, native agents, a durable run, or review orchestrating
Specify behavior, resolve requirements, and write an executable plan design-and-plan
Stress-test a plan, decision, or idea through a round-based interview grill-me
Change behavior with a verified red, green, refactor loop test-first-implementation
Find a root cause before fixing a bug or flaky test systematic-debugging
Prove completion, handoff, commit, merge, or release claims verify-and-finish
Preview and authorize a real-world side effect safe-effects
Preserve