waybarrios/opencode-power-pack

55 rigorous skills for Claude Code, Codex, OpenCode 1 and 2, and Pi: code review, security audit, feature development, frontend design, MCP tools, Hugging Face ML/training, and more.

What it solves

This project provides a unified library of 55 portable workflows (skills) for AI coding agents like Claude Code, Codex, OpenCode, and Pi. It addresses the fragmentation in AI agent capabilities, ensuring that specialized tasks—such as security auditing, code reviews, and feature development—can be executed consistently across different agent platforms.

How it works

The project acts as a cross-platform plugin and package manager. It allows users to install specific skill sets or profiles (e.g., "security," "frontend," or "authoring") into their local environment. It includes a "sandbox capability contract" that uses native OS security features (like macOS Seatbelt or Linux Bubblewrap) to enforce least-privilege execution, ensuring that AI-driven commands operate within defined safety boundaries.

Who it’s for

It is designed for developers and power users who utilize AI coding agents for complex tasks and want to standardize their agent's behavior, improve security during automated code execution, and access a broader catalog of specialized, pre-defined workflows.

Highlights

  • 55 pre-built workflows covering code review, security auditing, feature development, and design.
  • Native sandbox runner that provides fail-closed security for command execution.
  • Cross-platform support for Claude Code, Codex, OpenCode, and Pi.
  • Flexible installation options via npm, npx, or native agent plugins.
  • Role-based profiles to tailor agent behavior to specific project needs (e.g., security-focused or feature-development-focused).

Related

  • Project
    yunshu0909/yunshu_skillshub

    A collection of structured, battle-tested workflows and prompts designed to be installed into AI agents like Claude Code or Codex to standardize and improve performance across development, writing, and design tasks.

  • Project
    nikvdp/cco

    cco is a sandboxing wrapper for AI coding agents (Claude Code, Codex, etc.) that runs them in an isolated environment to protect your system from prompt injections and accidental damage, while preserving a seamless terminal experience.

  • Project
    akitaonrails/ai-jail

    A CLI that runs AI coding agents in an OS sandbox (bubblewrap/Landlock/seccomp on Linux, sandbox-exec on macOS), scoped to prevent accidents — not to stop attackers. The project directory is read-write; the host is hidden by default, with opt-in flags for credentials, network, GPU, display, etc. Includes a strict `--lockdown` mode and a "phantom credential" proxy that keeps real API keys out of the sandbox. A mature, well-documented Rust project — not a list, tutorial, or demo.

  • Project
    Yuan1z0825/nature-skills

    A library of 22 packaged AI-agent workflows ("skills") for academic research — paper reading, Nature-style writing, figure generation, reviewer responses, literature search, and patent drafting — installable into Claude Code, Codex, Chatbox, and other agents.

  • Project
    trailofbits/claude-code-config

    A collection of opinionated configurations, sandboxing rules, and hooks for Claude Code to enable secure, high-throughput autonomous AI coding.