### Qwen Code Integration Setup

Source: https://github.com/msitarzewski/agency-agents/blob/main/integrations/README.md

Qwen Code also requires generated SubAgent files on a fresh clone. Convert first, then install.

```bash
./scripts/convert.sh --tool qwen
```

```bash
./scripts/install.sh --tool qwen
```

--------------------------------

### Interactive Tool Installation

Source: https://github.com/msitarzewski/agency-agents/blob/main/README.md

Launches an interactive UI to select and install tools. Use arrow keys, 'a' for all, 'n' for none, 'd' for detected, and 'Enter' to install.

```bash
./scripts/install.sh --no-interactive --parallel
```

--------------------------------

### Install Specific Tool

Source: https://github.com/msitarzewski/agency-agents/blob/main/README.md

Installs a single, specified tool directly. Useful for quick setup or targeted installations.

```bash
./scripts/install.sh --tool cursor
```

```bash
./scripts/install.sh --tool opencode
```

```bash
./scripts/install.sh --tool openclaw
```

```bash
./scripts/install.sh --tool antigravity
```

--------------------------------

### Install OpenCode Agents

Source: https://github.com/msitarzewski/agency-agents/blob/main/integrations/README.md

Install OpenCode agents by running the installer script from your project root. Each agent becomes a project-scoped .md file.

```bash
cd /your/project && /path/to/agency-agents/scripts/install.sh --tool opencode
```

--------------------------------

### Install Windsurf Rules

Source: https://github.com/msitarzewski/agency-agents/blob/main/integrations/README.md

Install Windsurf by running the installer script from your project root. All agents are consolidated into a single .windsurfrules file for your project.

```bash
cd /your/project && /path/to/agency-agents/scripts/install.sh --tool windsurf
```

--------------------------------

### Install Aider Conventions

Source: https://github.com/msitarzewski/agency-agents/blob/main/integrations/README.md

Install Aider by running the installer script from your project root. All agents are consolidated into a single CONVENTIONS.md file.

```bash
cd /your/project && /path/to/agency-agents/scripts/install.sh --tool aider
```

--------------------------------

### Install Cursor Rules

Source: https://github.com/msitarzewski/agency-agents/blob/main/integrations/README.md

Install Cursor rules by running the installer script from your project root. Each agent becomes a project-scoped .mdc rule file.

```bash
cd /your/project && /path/to/agency-agents/scripts/install.sh --tool cursor
```

--------------------------------

### Install Qwen Agents

Source: https://github.com/msitarzewski/agency-agents/blob/main/integrations/README.md

Install Qwen agents from your project root after conversion. Ensure you are in the correct directory.

```bash
cd /your/project && /path/to/agency-agents/scripts/install.sh --tool qwen
```

--------------------------------

### Install Language Servers

Source: https://github.com/msitarzewski/agency-agents/blob/main/specialized/lsp-index-engineer.md

Commands to install various language servers for different programming languages using npm. Ensure Node.js and npm are installed.

```bash
# Install language servers
npm install -g typescript-language-server typescript
npm install -g intelephense  # or phpactor for PHP
npm install -g gopls          # for Go
npm install -g rust-analyzer  # for Rust
npm install -g pyright        # for Python

# Verify LSP servers work
echo '{"jsonrpc":"2.0","id":0,"method":"initialize","params":{"capabilities":{}}}' | typescript-language-server --stdio
```

--------------------------------

### Install Aider

Source: https://github.com/msitarzewski/agency-agents/blob/main/integrations/aider/README.md

Run this command from your project root to install Aider.

```bash
# Run from your project root
cd /your/project
/path/to/agency-agents/scripts/install.sh --tool aider
```

--------------------------------

### Generate and Install Integrations for Multiple Tools

Source: https://github.com/msitarzewski/agency-agents/blob/main/README.md

Generates integration files for supported tools and then installs them interactively. Specific tools can also be targeted for installation.

```bash
# Step 1 -- generate integration files for all supported tools
./scripts/convert.sh
```

```bash
# Step 2 -- install interactively (auto-detects what you have installed)
./scripts/install.sh
```

```bash
# Or target a specific tool directly
./scripts/install.sh --tool antigravity
```

```bash
./scripts/install.sh --tool gemini-cli
```

```bash
./scripts/install.sh --tool opencode
```

```bash
./scripts/install.sh --tool copilot
```

```bash
./scripts/install.sh --tool openclaw
```

```bash
./scripts/install.sh --tool cursor
```

```bash
./scripts/install.sh --tool aider
```

```bash
./scripts/install.sh --tool windsurf
```

```bash
./scripts/install.sh --tool kimi
```

--------------------------------

### Convert and Install Qwen Code Agent

Source: https://github.com/msitarzewski/agency-agents/blob/main/README.md

Installs the Qwen Code agent. SubAgents are installed to .qwen/agents/ in your project root (project-scoped). Run from your project root.

```bash
# Convert and install (run from your project root)
cd /your/project
./scripts/convert.sh --tool qwen
./scripts/install.sh --tool qwen
```

--------------------------------

### Convert and Install Kimi Agents

Source: https://github.com/msitarzewski/agency-agents/blob/main/integrations/README.md

Run these commands to convert and install agents for Kimi. Ensure you execute this from a fresh clone.

```bash
./scripts/convert.sh --tool kimi
./scripts/install.sh --tool kimi
```

--------------------------------

### Install OpenCode Agent (Global)

Source: https://github.com/msitarzewski/agency-agents/blob/main/README.md

Installs the OpenCode agent globally. Agents are copied to ~/.config/opencode/agents/.

```bash
mkdir -p ~/.config/opencode/agents
cp integrations/opencode/agents/*.md ~/.config/opencode/agents/
```

--------------------------------

### Install Specific Home-Scoped Tool

Source: https://github.com/msitarzewski/agency-agents/blob/main/integrations/README.md

Use this command to install a specific home-scoped tool integration.

```bash
./scripts/install.sh --tool antigravity
```

```bash
./scripts/install.sh --tool copilot
```

```bash
./scripts/install.sh --tool openclaw
```

```bash
./scripts/install.sh --tool claude-code
```

--------------------------------

### Install Qwen Agent Files

Source: https://github.com/msitarzewski/agency-agents/blob/main/integrations/qwen/README.md

Execute the installer script from your target project root to copy generated Qwen agent files. Ensure you replace `/path/to/agency-agents/` with the actual path to the agency-agents repository.

```bash
cd /your/project && /path/to/agency-agents/scripts/install.sh --tool qwen

```

--------------------------------

### Configure NetworkManager via Code

Source: https://github.com/msitarzewski/agency-agents/blob/main/game-development/unity/unity-multiplayer-engineer.md

Configure Unity Transport and start a host or client with relay services programmatically. Useful for dynamic network setup.

```csharp
// NetworkManager configuration via code (supplement to Inspector setup)
public class NetworkSetup : MonoBehaviour
{
    [SerializeField] private NetworkManager _networkManager;

    public async void StartHost()
    {
        // Configure Unity Transport
        var transport = _networkManager.GetComponent<UnityTransport>();
        transport.SetConnectionData("0.0.0.0", 7777);

        _networkManager.StartHost();
    }

    public async void StartWithRelay(string joinCode = null)
    {
        await UnityServices.InitializeAsync();
        await AuthenticationService.Instance.SignInAnonymouslyAsync();

        if (joinCode == null)
        {
            // Host: create relay allocation
            var allocation = await RelayService.Instance.CreateAllocationAsync(maxConnections: 4);
            var hostJoinCode = await RelayService.Instance.GetJoinCodeAsync(allocation.AllocationId);

            var transport = _networkManager.GetComponent<UnityTransport>();
            transport.SetRelayServerData(AllocationUtils.ToRelayServerData(allocation, "dtls"));
            _networkManager.StartHost();

            Debug.Log($
```

```csharp
Join Code: {hostJoinCode}");
        }
        else
        {
            // Client: join via relay join code
            var joinAllocation = await RelayService.Instance.JoinAllocationAsync(joinCode);
            var transport = _networkManager.GetComponent<UnityTransport>();
            transport.SetRelayServerData(AllocationUtils.ToRelayServerData(joinAllocation, "dtls"));
            _networkManager.StartClient();
        }
    }
}

```

--------------------------------

### Dockerfile Example

Source: https://github.com/msitarzewski/agency-agents/blob/main/strategy/playbooks/phase-2-foundation.md

Defines how to build a Docker image for an application. Specifies the base image, dependencies, and commands to run.

```dockerfile
FROM python:3.9-slim
WORKDIR /app
COPY requirements.txt requirements.txt
RUN pip install --no-cache-dir -r requirements.txt
COPY . .
CMD ["python", "app.py"]
```

--------------------------------

### Usability Testing Protocol Structure

Source: https://github.com/msitarzewski/agency-agents/blob/main/design/design-ux-researcher.md

A markdown template for structuring a usability testing session guide. It covers pre-test setup, session flow, and data collection methods.

```markdown
# Usability Testing Session Guide

## Pre-Test Setup
**Environment**: [Testing location and setup requirements]
**Technology**: [Recording tools, devices, software needed]
**Materials**: [Consent forms, task cards, questionnaires]
**Team Roles**: [Moderator, observer, note-taker responsibilities]

## Session Structure (60 minutes)
### Introduction (5 minutes)
- Welcome and comfort building
- Consent and recording permission
- Overview of think-aloud protocol
- Questions about background

### Baseline Questions (10 minutes)
- Current tool usage and experience
- Expectations and mental models
- Relevant demographic information

### Task Scenarios (35 minutes)
**Task 1**: [Realistic scenario description]
- Success criteria: [What completion looks like]
- Metrics: [Time, errors, completion rate]
- Observation focus: [Key behaviors to watch]

**Task 2**: [Second scenario]
**Task 3**: [Third scenario]

### Post-Test Interview (10 minutes)
- Overall impressions and satisfaction
- Specific feedback on pain points
- Suggestions for improvement
- Comparative questions

## Data Collection
**Quantitative**: [Task completion rates, time on task, error counts]
**Qualitative**: [Quotes, behavioral observations, emotional responses]
**System Metrics**: [Analytics data, performance measures]
```

--------------------------------

### High-Quality README Template

Source: https://github.com/msitarzewski/agency-agents/blob/main/engineering/engineering-technical-writer.md

A template for creating comprehensive README files that include project description, badges, quick start, installation, usage, API reference, contributing, and license information.

```markdown
# Project Name

> One-sentence description of what this does and why it matters.

[![npm version](https://badge.fury.io/js/your-package.svg)](https://badge.fury.io/js/your-package)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)

## Why This Exists

<!-- 2-3 sentences: the problem this solves. Not features — the pain. -->

## Quick Start

<!-- Shortest possible path to working. No theory. -->

```bash
npm install your-package
```

```javascript
import { doTheThing } from 'your-package';

const result = await doTheThing({ input: 'hello' });
console.log(result); // "hello world"
```

## Installation

<!-- Full install instructions including prerequisites -->

**Prerequisites**: Node.js 18+, npm 9+

```bash
npm install your-package
# or
yarn add your-package
```

## Usage

### Basic Example

<!-- Most common use case, fully working -->

### Configuration

| Option | Type | Default | Description |
|--------|------|---------|-------------|
| `timeout` | `number` | `5000` | Request timeout in milliseconds |
| `retries` | `number` | `3` | Number of retry attempts on failure |

### Advanced Usage

<!-- Second most common use case -->

## API Reference

See [full API reference →](https://docs.yourproject.com/api)

## Contributing

See [CONTRIBUTING.md](CONTRIBUTING.md)

## License

MIT © [Your Name](https://github.com/yourname)

```

--------------------------------

### Metal Rendering Pipeline Setup

Source: https://github.com/msitarzewski/agency-agents/blob/main/spatial-computing/macos-spatial-metal-engineer.md

Initializes Metal device, command queue, pipeline state, and depth state for rendering. Requires a Metal-compatible device.

```swift
// Core Metal rendering architecture
class MetalGraphRenderer {
    private let device: MTLDevice
    private let commandQueue: MTLCommandQueue
    private var pipelineState: MTLRenderPipelineState
    private var depthState: MTLDepthStencilState
    
    // Instanced node rendering
    struct NodeInstance {
        var position: SIMD3<Float>
        var color: SIMD4<Float>
        var scale: Float
        var symbolId: UInt32
    }
    
    // GPU buffers
    private var nodeBuffer: MTLBuffer        // Per-instance data
    private var edgeBuffer: MTLBuffer        // Edge connections
    private var uniformBuffer: MTLBuffer     // View/projection matrices
    
    func render(nodes: [GraphNode], edges: [GraphEdge], camera: Camera) {
        guard let commandBuffer = commandQueue.makeCommandBuffer(),
              let descriptor = view.currentRenderPassDescriptor,
              let encoder = commandBuffer.makeRenderCommandEncoder(descriptor: descriptor) else {
            return
        }
        
        // Update uniforms
        var uniforms = Uniforms(
            viewMatrix: camera.viewMatrix,
            projectionMatrix: camera.projectionMatrix,
            time: CACurrentMediaTime()
        )
        uniformBuffer.contents().copyMemory(from: &uniforms, byteCount: MemoryLayout<Uniforms>.stride)
        
        // Draw instanced nodes
        encoder.setRenderPipelineState(nodePipelineState)
        encoder.setVertexBuffer(nodeBuffer, offset: 0, index: 0)
        encoder.setVertexBuffer(uniformBuffer, offset: 0, index: 1)
        encoder.drawPrimitives(type: .triangleStrip, vertexStart: 0, 
                              vertexCount: 4, instanceCount: nodes.count)
        
        // Draw edges with geometry shader
        encoder.setRenderPipelineState(edgePipelineState)
        encoder.setVertexBuffer(edgeBuffer, offset: 0, index: 0)
        encoder.drawPrimitives(type: .line, vertexStart: 0, vertexCount: edges.count * 2)
        
        encoder.endEncoding()
        commandBuffer.present(drawable)
        commandBuffer.commit()
    }
}

```

--------------------------------

### Dialogue Node Format Example (Ink/Yarn/Generic)

Source: https://github.com/msitarzewski/agency-agents/blob/main/game-development/narrative-designer.md

Illustrates a branching dialogue structure using a format compatible with Ink or Yarn. Includes scene setup, character lines, player choices, and conditional node transitions.

```Ink
// Scene: First meeting with Commander Reyes
// Tone: Tense, power imbalance, protagonist is being evaluated

REYES: "You're late."
-> [Choice: How does the player respond?]
    + "I had complications." [Pragmatic]
        REYES: "Everyone does. The ones who survive learn to plan for them."
        -> reyes_neutral
    + "Your intel was wrong." [Challenging]
        REYES: "Then you improvised. Good. We need people who can."
        -> reyes_impressed
    + [Stay silent.] [Observing]
        REYES: "(Studies you.) Interesting. Follow me."
        -> reyes_intrigued

= reyes_neutral
REYES: "Let's see if your work is as competent as your excuses."
-> scene_continue

= reyes_impressed
REYES: "Don't make a habit of blaming the mission. But today — acceptable."
-> scene_continue

= reyes_intrigued
REYES: "Most people fill silences. Remember that."
-> scene_continue
```

--------------------------------

### Livewire Component Example

Source: https://github.com/msitarzewski/agency-agents/blob/main/engineering/engineering-senior-developer.md

Demonstrates a basic Livewire component structure for building dynamic interfaces within Laravel.

```php
class PremiumNavigation extends Component
{
    public $mobileMenuOpen = false;
    
    public function render()
    {
        return view('livewire.premium-navigation');
    }
}
```

--------------------------------

### Use Kimi Agent

Source: https://github.com/msitarzewski/agency-agents/blob/main/integrations/README.md

After installation, use the `--agent-file` flag to invoke a Kimi agent. You can specify a working directory if needed.

```bash
kimi --agent-file ~/.config/kimi/agents/frontend-developer/agent.yaml
```

```bash
cd /your/project
kimi --agent-file ~/.config/kimi/agents/frontend-developer/agent.yaml \
     --work-dir /your/project
```

--------------------------------

### Convert and Install Gemini CLI Agent

Source: https://github.com/msitarzewski/agency-agents/blob/main/README.md

Installs the Gemini CLI agent. On a fresh clone, generate the Gemini extension files before running the installer. Agents are installed as a Gemini CLI extension with one skill per agent plus a manifest.

```bash
./scripts/convert.sh --tool gemini-cli
./scripts/install.sh --tool gemini-cli
```

--------------------------------

### Install OpenCode Agent

Source: https://github.com/msitarzewski/agency-agents/blob/main/integrations/opencode/README.md

Run this script from your project root to create project-scoped OpenCode agent files.

```bash
# Run from your project root
cd /your/project
/path/to/agency-agents/scripts/install.sh --tool opencode
```

--------------------------------

### Convert and Install Kimi Code Agent

Source: https://github.com/msitarzewski/agency-agents/blob/main/README.md

Installs the Kimi Code agent. Agents are converted to Kimi Code CLI format (YAML + system prompt) and installed to ~/.config/kimi/agents/.

```bash
# Convert and install
./scripts/convert.sh --tool kimi
./scripts/install.sh --tool kimi
```

--------------------------------

### Frontend Project Scaffolding - Vite Example

Source: https://github.com/msitarzewski/agency-agents/blob/main/strategy/playbooks/phase-2-foundation.md

Configuration for Vite build tooling in a frontend project. Sets up the development server and build process.

```javascript
import { defineConfig } from 'vite'
import react from '@vitejs/plugin-react'

// https://vitejs.dev/config/
export default defineConfig({
  plugins: [react()],
})
```

--------------------------------

### Convert and Install OpenClaw Agent

Source: https://github.com/msitarzewski/agency-agents/blob/main/README.md

Installs the OpenClaw agent. Each agent becomes a workspace with SOUL.md, AGENTS.md, and IDENTITY.md in ~/.openclaw/agency-agents/. The installer registers each workspace automatically if the openclaw CLI is available.

```bash
./scripts/convert.sh --tool openclaw
./scripts/install.sh --tool openclaw
```