Windows-native agent orchestration. PowerShell-first execution, WinGet package management, environment discovery, safety-gated workflow synthesis, and sandbox routing. Includes /defrag to absorb or replace your existing extensions, MCPs, and agent configs.
Scan your existing agent ecosystem and choose to absorb, route, or replace it. Run this on first install or whenever your setup has gotten messy.
Run a full Windows environment snapshot. Shows OS, runtimes, installed tools, WSL distros, Dev Drive, package managers, and editor availability.
Brainstorm and write a structured execution plan before touching any code or running any commands. Required entry point for complex tasks.
Inspect the full Windows development environment. Use when diagnosing tool availability, runtime versions, WSL state, Dev Drive, or package manager status. Triggers automatically when environment state is needed before planning or executing any task.
Install packages or tools using WinGet (preferred), Chocolatey, or Scoop. Always approval-required. Use when the user asks to install something or when a dependency check finds a missing tool.
Route code execution or tool testing into an isolated environment. Use when running untrusted code, testing installers, or needing reproducible execution. Chooses between Windows Sandbox, WSL, Dev Container, or Hyper-V based on what's available and what's needed.
Bootstrap or repair a Windows development environment. Use when setting up a new machine, onboarding to a project, or fixing a broken environment. Triggers on phrases like "set up my environment", "bootstrap", "my Python isn't working", or "I need to install X".
Plan any development task before executing it. Use when given a feature request, bug to fix, refactor, or any multi-step task. Always generates a structured plan with safety classifications before touching code or running commands.
Executes bash commands
Hook triggers when Bash tool is used
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Claude Code plugin for Windows-native developer orchestration.
Install:
/plugin install windows-dev-agent
Or with APM:
apm install windows-dev-agent
/windows-dev-agent:env — Full environment snapshot: OS, runtimes, WSL, Dev Drive, package managers, editors/windows-dev-agent:plan <task> — Structured execution plan before touching anything. Entry criteria, steps, exit criteria, rollback, safety classifications./windows-dev-agent:defrag — Scan existing agent infrastructure (VS Code extensions, MCP servers, agent configs) and choose to absorb, route, or clean house.Two layers:
Plugin layer (markdown) — read directly by Claude Code, no build step:
commands/ — slash commandsskills/ — auto-triggered context skillsagents/ — orchestration agenthooks/ — pre/post tool safety gatesPython backend — MCP stdio server invoked by Claude Code:
| Class | Behavior |
|---|---|
read-only | Autonomous |
reversible | Autonomous + audit log |
approval-required | Show command, wait for yes |
checkpoint | Explain risk, require confirmation |
forbidden | Never without direct human command |
pip install pyyamlSee docs/superpowers/specs/ for design documents.
npx claudepluginhub the-biomechanist/windows-dev-agentAgent coordination and meta-programming - multi-agent orchestration, workflow automation. Works best with other voltagent plugins installed.
Automatically detects and loads AGENTS.md files to provide agent-specific instructions alongside CLAUDE.md. Enables specialized agent behaviors without manual intervention.
Experimental skills for Claude Code Superpowers - new techniques and tools under development
Harness-native ECC plugin for engineering teams - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.