### Install and Reload Extension

Source: https://quintinshaw.github.io/pi-dynamic-workflows

Install the package via npm and reload the Pi environment to initialize the extension.

```bash
pi install npm:@quintinshaw/pi-dynamic-workflows
# then in Pi:
/reload
```

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

### Installation Command

Source: https://quintinshaw.github.io/pi-dynamic-workflows

Install the dynamic workflows package into the Pi environment.

```bash
pi install npm:@quintinshaw/pi-dynamic-workflows
```

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

### Configuration and Progress Commands

Source: https://quintinshaw.github.io/pi-dynamic-workflows

Commands for configuring triggers, progress reporting, and model mapping.

```APIDOC
## /workflows-trigger off|on|status|set <word>|reset

### Description
Configures keyword-triggered workflow behavior, including enabling/disabling, checking status, or setting a custom trigger word.

## /workflows-progress compact|detailed|status

### Description
Switches the live progress panel view between compact and detailed modes.

## /workflows-progress-max <N>

### Description
Sets the maximum number of agents shown per phase in detailed mode (1-1000).

## /workflows-models

### Description
Displays the mapping of small, medium, and big tiers to specific models.
```

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

### Configure Ultracode Settings

Source: https://quintinshaw.github.io/pi-dynamic-workflows

Toggle exhaustive multi-agent workflows or adjust effort levels for incoming messages.

```bash
/ultracode          # on — auto-arm an exhaustive workflow for every substantive message
/ultracode off      # back to normal
/effort high|ultra  # finer control (high = thorough, ultra = ultracode)
```

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

### Run Workflow via Prompt

Source: https://quintinshaw.github.io/pi-dynamic-workflows

Execute a workflow by providing a natural language task description to Pi.

```text
Run a workflow to audit every route under src/routes/ for missing auth checks.
```

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

### Workflow Management Commands

Source: https://quintinshaw.github.io/pi-dynamic-workflows

Commands for managing, running, and monitoring dynamic workflows.

```APIDOC
## /workflows

### Description
Opens the interactive navigator to view workflow status.

## /workflows run <prompt>

### Description
Forces a dynamic workflow for the provided prompt, bypassing keyword triggering settings.

## /workflows status <id>

### Description
Watches a specific workflow run live and prints the result upon completion.

## /workflows save <name>

### Description
Saves the latest workflow run's script as a reusable command named /<name>.

## /workflows pause|resume|stop|rm <id>

### Description
Manages the lifecycle of a specific workflow run.
```

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

### Define Custom Workflow

Source: https://quintinshaw.github.io/pi-dynamic-workflows

Create a custom JavaScript workflow using phase, agent, and parallel orchestration primitives.

```javascript
export const meta = {
  name: 'auth_audit',
  description: 'Find routes missing auth checks and verify the findings',
  phases: [{ title: 'Scan' }, { title: 'Review' }, { title: 'Verify' }],
}

phase('Scan')
const files = await agent('List every route file under src/routes/.', { tier: 'small' })

phase('Review')
const findings = await parallel(
  files.split('\n').filter(Boolean).map((file) =>
    () => agent(`Audit ${file} for missing auth checks.`, { tier: 'medium', isolation: 'worktree' }),
  ),
)

phase('Verify')
return await agent('Synthesize and double-check:\n' + findings.join('\n\n'), { tier: 'big' })
```

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

### Automation and Research Commands

Source: https://quintinshaw.github.io/pi-dynamic-workflows

Commands for automated code workflows and specialized research tasks.

```APIDOC
## /ultracode [off]

### Description
Auto-arms an exhaustive workflow for every substantive message.

## /effort off|high|ultra

### Description
Sets the standing opt-in level for workflow effort.

## /deep-research <question>

### Description
Performs a web-researched, source-cross-checked report.

## /adversarial-review <task>

### Description
Executes a task with findings vetted by skeptical reviewers.

## /multi-perspective "<topic>" [angle …]

### Description
Analyzes a topic from multiple independent angles and synthesizes the results.

## /codebase-audit <scope> "<check>" …

### Description
Runs parallel checks over a specified scope, then cross-validates and reports findings.
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.