claude-mpm 5.4.95__py3-none-any.whl → 5.4.97__py3-none-any.whl

claude_mpm/VERSION

@@ -1 +1 @@
-5.4.95
+5.4.97

claude_mpm/agents/{CLAUDE_MPM_FOUNDERS_OUTPUT_STYLE.md → CLAUDE_MPM_RESEARCH_OUTPUT_STYLE.md}

@@ -1,11 +1,11 @@
 ---
-name: Claude MPM Founders
-description: Non-technical explanations for startup founders inspecting codebases
+name: Claude MPM Research
+description: Codebase research tool for founders, PMs, and developers - deep analysis in accessible language
 ---
 
-# Claude MPM for Founders
+# Claude MPM Research Mode
 
-**Your code inspection companion** - Get clear, actionable insights about your codebase without needing to understand programming.
+**Your codebase research companion** - Get clear, actionable insights about any codebase, whether you're a founder, PM, or developer.
 
 ## Core Principle: Accurate but Accessible
 
@@ -18,14 +18,22 @@ Technical accuracy is never sacrificed for simplicity. You get the same accurate
 - Use analogies to explain, but note when the analogy has limits
 - When precision matters (security, compliance, data integrity), call it out explicitly
 
-## What This Mode Does
+## What Research Mode Does
 
-Translates technical details into business language so you can:
+Research Mode provides deep codebase analysis that's accessible to everyone:
+
+**For Founders & PMs:**
 - Understand what your developers are building
 - Assess code quality and team productivity
 - Make informed decisions about technical priorities
 - Spot potential risks before they become problems
 
+**For Developers:**
+- Quickly understand unfamiliar codebases
+- Get architectural overviews of complex systems
+- Identify technical debt and improvement opportunities
+- Research best practices and patterns in existing code
+
 ---
 
 ## Quick Assessment Framework

claude_mpm/agents/PM_INSTRUCTIONS.md

@@ -15,7 +15,7 @@ The Project Manager (PM) agent coordinates work across specialized agents in the
 2. Use Read tool more than ONCE per session - DELEGATE to Research
 3. Investigate, debug, or analyze code directly - DELEGATE to Research
 4. Use Edit/Write tools on any file - DELEGATE to Engineer
-5. Run verification commands (curl, lsof) - DELEGATE to local-ops
+5. Run verification commands (`curl`, `wget`, `lsof`, `netstat`, `ps`, `pm2`, `docker ps`) - DELEGATE to local-ops/QA
 
 **Violation of any prohibition = Circuit Breaker triggered**
 
@@ -267,9 +267,12 @@ See mpm-tool-usage-guide skill for complete tool usage patterns and examples.
 - Investigation keywords trigger delegation, not Read
 
 **Bash Tool** (Navigation and git tracking ONLY):
-- Allowed: `ls`, `pwd`, `cd`, `git status`, `git add`, `git commit`
-- FORBIDDEN: `curl`, `lsof`, `sed`, `awk`, `echo >`, `grep`, `find`, `cat`
-- Verification/implementation → Delegate to appropriate agent
+- **ALLOWED**: `ls`, `pwd`, `cd`, `git status`, `git add`, `git commit`, `git push`, `git log`
+- **FORBIDDEN** (must delegate):
+  - Verification: `curl`, `wget`, `lsof`, `netstat`, `ps`, `pm2 status`, `docker ps`
+  - Implementation: `sed`, `awk`, `echo >`, `npm`, `pip`, `make`
+  - Investigation: `grep`, `find`, `cat`, `head`, `tail`
+- **WHY**: Verification is technical work requiring domain expertise. Delegate to local-ops/QA.
 
 **Vector Search** (Quick semantic search):
 - MANDATORY: Use mcp-vector-search BEFORE Read/Research if available

claude_mpm/agents/templates/circuit-breakers.md

@@ -523,23 +523,25 @@ PM: Task(agent="qa", task="Verify bug fix with regression test")
 
 ### KEY PRINCIPLE
 
-PM delegates implementation work, then MAY verify results.
+PM delegates ALL work - implementation AND verification.
 
 **Workflow:**
-1. **DELEGATE** to agent (using Task tool)
+1. **DELEGATE** implementation to appropriate agent (using Task tool)
 2. **WAIT** for agent to complete work
-3. **VERIFY** results (using Bash verification commands OR delegating verification)
-4. **REPORT** verified results with evidence
+3. **DELEGATE** verification to appropriate agent (local-ops, QA, web-qa)
+4. **REPORT** verified results with evidence from verification agent
 
-### Allowed Verification Commands (AFTER Delegation)
+### PM NEVER Uses Verification Commands
 
-These commands are ALLOWED for quality assurance AFTER delegating implementation:
+**FORBIDDEN for PM** (must delegate to local-ops or QA):
 
-- `curl`, `wget` - HTTP endpoint testing
-- `lsof`, `netstat`, `ss` - Port and network checks
-- `ps`, `pgrep` - Process status checks
-- `pm2 status`, `docker ps` - Service status
-- Health check endpoints
+- `curl`, `wget` - HTTP endpoint testing → Delegate to api-qa or local-ops
+- `lsof`, `netstat`, `ss` - Port and network checks → Delegate to local-ops
+- `ps`, `pgrep` - Process status checks → Delegate to local-ops
+- `pm2 status`, `docker ps` - Service status → Delegate to local-ops
+- Health check endpoints → Delegate to api-qa or web-qa
+
+**Why PM doesn't verify**: Verification is technical work requiring domain expertise. local-ops and QA agents have the tools, context, and expertise to verify correctly.
 
 ### Examples
 
@@ -550,23 +552,29 @@ These commands are ALLOWED for quality assurance AFTER delegating implementation
 PM: Bash("npm start")                       # VIOLATION - implementing
 PM: "App running on localhost:3000"         # VIOLATION - no delegation
 
+# Wrong: PM using verification commands
+PM: Bash("lsof -i :3000")                   # VIOLATION - should delegate to local-ops
+PM: Bash("curl http://localhost:3000")      # VIOLATION - should delegate to api-qa
+
 # Wrong: PM testing before delegating implementation
 PM: Bash("npm test")                        # VIOLATION - testing without implementation
 
 # Wrong: "Let me" thinking
 PM: "Let me check the code..."              # VIOLATION - should delegate
 PM: "Let me fix this bug..."                # VIOLATION - should delegate
+PM: "Let me verify the deployment..."       # VIOLATION - should delegate to local-ops
 ```
 
 #### ✅ CORRECT Examples
 
 ```
-# Correct: Delegate first, then verify
-PM: Task(agent="local-ops-agent", task="Start app on localhost:3000 using npm")
-    [Agent starts app]
-PM: Bash("lsof -i :3000 | grep LISTEN")     # ✅ ALLOWED - verifying after delegation
-PM: Bash("curl http://localhost:3000")      # ✅ ALLOWED - confirming deployment
-PM: "App verified: Port 3000 listening, HTTP 200 response"
+# Correct: Delegate implementation, then delegate verification
+PM: Task(agent="local-ops", task="Start app on localhost:3000 using npm")
+    [local-ops starts app]
+PM: Task(agent="local-ops", task="Verify app is running on port 3000")
+    [local-ops uses lsof and curl to verify]
+    [local-ops returns: "Port 3000 listening, HTTP 200 response"]
+PM: "App verified by local-ops: Port 3000 listening, HTTP 200 response"
 
 # Correct: Delegate implementation, then delegate testing
 PM: Task(agent="engineer", task="Fix authentication bug")
@@ -578,6 +586,7 @@ PM: "Bug fix verified by QA: All tests passed"
 # Correct: Thinking in delegation terms
 PM: "I'll have Research check the code..."
 PM: "I'll delegate this fix to Engineer..."
+PM: "I'll have local-ops verify the deployment..."
 ```
 
 ---

claude_mpm/cli/commands/autotodos.py

@@ -0,0 +1,526 @@
+"""CLI commands for auto-generating todos from hook errors.
+
+WHY this is needed:
+- Convert hook errors into actionable todos for the PM
+- Enable PM to delegate error resolution to appropriate agents
+- Reduce manual todo creation overhead
+- Maintain error visibility in the PM's workflow
+
+DESIGN DECISION: Event-driven architecture
+- Read from event log instead of hook_errors.json
+- Event log provides clean separation between detection and consumption
+- Supports multiple consumers (CLI, dashboard, notifications)
+- Persistent storage with pending/resolved status tracking
+"""
+
+import json
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Any, Dict, List
+
+import click
+
+from claude_mpm.services.delegation_detector import get_delegation_detector
+from claude_mpm.services.event_log import get_event_log
+
+
+def format_error_event_as_todo(event: Dict[str, Any]) -> Dict[str, str]:
+    """Convert event log error event to todo format compatible with PM TodoWrite.
+
+    Args:
+        event: Event from event log with payload containing error details
+
+    Returns:
+        Dictionary with todo fields (content, activeForm, status)
+    """
+    payload = event.get("payload", {})
+    error_type = payload.get("error_type", "unknown")
+    hook_type = payload.get("hook_type", "unknown")
+    details = payload.get("details", "")
+    full_message = payload.get("full_message", "")
+
+    # Create concise todo content
+    content = f"Fix {hook_type} hook error: {error_type}"
+    if details:
+        content += f" ({details[:50]}{'...' if len(details) > 50 else ''})"
+
+    # Active form for in-progress display
+    active_form = f"Fixing {hook_type} hook error"
+
+    return {
+        "content": content,
+        "activeForm": active_form,
+        "status": "pending",
+        "metadata": {
+            "event_id": event.get("id", ""),
+            "event_type": event.get("event_type", ""),
+            "error_type": error_type,
+            "hook_type": hook_type,
+            "details": details,
+            "full_message": full_message,
+            "suggested_fix": payload.get("suggested_fix", ""),
+            "timestamp": event.get("timestamp", ""),
+        },
+    }
+
+
+def format_delegation_event_as_todo(event: Dict[str, Any]) -> Dict[str, str]:
+    """Convert event log delegation event to todo format compatible with PM TodoWrite.
+
+    Args:
+        event: Event from event log with payload containing delegation details
+
+    Returns:
+        Dictionary with todo fields (content, activeForm, status)
+    """
+    payload = event.get("payload", {})
+    pattern_type = payload.get("pattern_type", "Task")
+    suggested_todo = payload.get("suggested_todo", "")
+    action = payload.get("action", "")
+    original_text = payload.get("original_text", "")
+
+    # Create concise todo content
+    content = f"[Delegation] {suggested_todo}"
+
+    # Active form for in-progress display
+    active_form = f"Delegating: {action[:30]}..."
+
+    return {
+        "content": content,
+        "activeForm": active_form,
+        "status": "pending",
+        "metadata": {
+            "event_id": event.get("id", ""),
+            "event_type": event.get("event_type", ""),
+            "pattern_type": pattern_type,
+            "suggested_todo": suggested_todo,
+            "action": action,
+            "original_text": original_text,
+            "timestamp": event.get("timestamp", ""),
+        },
+    }
+
+
+def get_autotodos() -> List[Dict[str, Any]]:
+    """Get all pending hook error events formatted as todos.
+
+    DESIGN DECISION: Only autotodo.error events are returned
+    - autotodo.error = Script/coding failures → PM should delegate fix
+    - pm.violation = Delegation anti-patterns → PM behavior error (not todo)
+
+    Returns:
+        List of todo dictionaries ready for PM injection
+    """
+    event_log = get_event_log()
+    todos = []
+
+    # Get all pending autotodo.error events (script failures)
+    pending_error_events = event_log.list_events(
+        event_type="autotodo.error", status="pending"
+    )
+
+    for event in pending_error_events:
+        todo = format_error_event_as_todo(event)
+        todos.append(todo)
+
+    return todos
+
+
+@click.group(name="autotodos")
+def autotodos_group():
+    """Auto-generate todos from hook errors.
+
+    This command converts hook errors into actionable todos that can be
+    injected into the PM's todo list for delegation and resolution.
+
+    Uses event-driven architecture - reads from event log instead of
+    directly from hook error memory.
+    """
+
+
+@autotodos_group.command(name="status")
+def show_autotodos_status():
+    """Show autotodos status and statistics.
+
+    Quick overview of pending hook errors, PM violations, and autotodos.
+
+    Example:
+        claude-mpm autotodos status
+    """
+    event_log = get_event_log()
+    stats = event_log.get_stats()
+    todos = get_autotodos()
+    violations = event_log.list_events(event_type="pm.violation", status="pending")
+
+    click.echo("\n📊 AutoTodos Status")
+    click.echo("=" * 80)
+
+    click.echo(f"Total Events: {stats['total_events']}")
+    click.echo(f"Pending Todos (script errors): {len(todos)}")
+    click.echo(f"Pending Violations (PM errors): {len(violations)}")
+    click.echo(f"Total Pending Events: {stats['by_status']['pending']}")
+    click.echo(f"Resolved Events: {stats['by_status']['resolved']}")
+
+    if stats.get("by_type"):
+        click.echo("\n📋 Events by Type:")
+        for event_type, count in stats["by_type"].items():
+            click.echo(f"   {event_type}: {count}")
+
+    click.echo(f"\n📁 Event Log: {stats['log_file']}")
+
+    if todos or violations:
+        click.echo("\n⚠️  Action Required:")
+        if todos:
+            click.echo(f"   {len(todos)} script error(s) need delegation")
+        if violations:
+            click.echo(f"   {len(violations)} PM violation(s) need correction")
+        click.echo("\nCommands:")
+        click.echo(
+            "  claude-mpm autotodos list         # View pending todos (script errors)"
+        )
+        click.echo("  claude-mpm autotodos violations   # View PM violations")
+        click.echo("  claude-mpm autotodos inject       # Inject todos into PM session")
+        click.echo("  claude-mpm autotodos clear        # Clear after resolution")
+    else:
+        click.echo("\n✅ No pending todos or violations. All clear!")
+
+
+@autotodos_group.command(name="list")
+@click.option(
+    "--format",
+    type=click.Choice(["table", "json"], case_sensitive=False),
+    default="table",
+    help="Output format (table or json)",
+)
+def list_autotodos(format):
+    """List all auto-generated todos from hook errors.
+
+    Shows pending hook errors formatted as todos that can be acted upon
+    by the PM.
+
+    Examples:
+        claude-mpm autotodos list
+        claude-mpm autotodos list --format json
+    """
+    todos = get_autotodos()
+
+    if not todos:
+        click.echo("✅ No pending hook errors. All clear!")
+        return
+
+    if format == "json":
+        # JSON output for programmatic use
+        click.echo(json.dumps(todos, indent=2))
+    else:
+        # Table output for human readability
+        click.echo("\n" + "=" * 80)
+        click.echo("Auto-Generated Todos from Hook Errors")
+        click.echo("=" * 80)
+
+        for i, todo in enumerate(todos, 1):
+            metadata = todo.get("metadata", {})
+            click.echo(f"\n{i}. {todo['content']}")
+            click.echo(f"   Status: {todo['status']}")
+            click.echo(f"   Hook: {metadata.get('hook_type', 'Unknown')}")
+            click.echo(f"   Error Type: {metadata.get('error_type', 'Unknown')}")
+            click.echo(f"   Timestamp: {metadata.get('timestamp', 'Unknown')}")
+
+            # Show suggested fix if available
+            suggested_fix = metadata.get("suggested_fix", "")
+            if suggested_fix:
+                # Show first line of suggestion
+                first_line = suggested_fix.split("\n")[0]
+                click.echo(f"   Suggestion: {first_line}")
+
+        click.echo("\n" + "=" * 80)
+        click.echo(f"Total: {len(todos)} pending todo(s)")
+        click.echo("\nTo inject into PM session: claude-mpm autotodos inject")
+
+
+@autotodos_group.command(name="inject")
+@click.option(
+    "--output",
+    type=click.Path(),
+    help="Output file path (default: stdout)",
+)
+def inject_autotodos(output):
+    """Inject auto-generated todos in PM-compatible format.
+
+    Outputs todos in a format that can be injected into the PM's
+    session as system reminders.
+
+    Examples:
+        claude-mpm autotodos inject
+        claude-mpm autotodos inject --output todos.json
+    """
+    todos = get_autotodos()
+
+    if not todos:
+        click.echo("✅ No pending hook errors to inject.", err=True)
+        return
+
+    # Format as system reminder for PM
+    pm_message = {
+        "type": "autotodos",
+        "timestamp": datetime.now(timezone.utc).isoformat(),
+        "todos": todos,
+        "message": f"Found {len(todos)} hook error(s) requiring attention. "
+        "Consider delegating to appropriate agents for resolution.",
+    }
+
+    output_json = json.dumps(pm_message, indent=2)
+
+    if output:
+        # Write to file
+        output_path = Path(output)
+        output_path.write_text(output_json)
+        click.echo(f"✅ Injected {len(todos)} todo(s) to {output_path}", err=True)
+    else:
+        # Write to stdout for piping
+        click.echo(output_json)
+
+
+@autotodos_group.command(name="clear")
+@click.option(
+    "--event-id",
+    help="Clear specific event by ID",
+)
+@click.option(
+    "--event-type",
+    type=click.Choice(["error", "violation", "all"], case_sensitive=False),
+    default="all",
+    help="Type of events to clear (default: all)",
+)
+@click.option(
+    "--yes",
+    "-y",
+    is_flag=True,
+    help="Skip confirmation prompt",
+)
+def clear_autotodos(event_id, event_type, yes):
+    """Clear hook errors and PM violations after resolution.
+
+    This marks resolved events in the event log, removing them from
+    the autotodos and violations lists.
+
+    Examples:
+        claude-mpm autotodos clear                        # Clear all pending
+        claude-mpm autotodos clear --event-type error     # Clear only errors
+        claude-mpm autotodos clear --event-type violation # Clear only violations
+        claude-mpm autotodos clear --event-id ID          # Clear specific event
+        claude-mpm autotodos clear -y                     # Skip confirmation
+    """
+    event_log = get_event_log()
+
+    if event_id:
+        # Clear specific event
+        if not yes:
+            message = f"Clear event: {event_id}?"
+            if not click.confirm(message):
+                click.echo("Cancelled.")
+                return
+
+        # Mark as resolved
+        if event_log.mark_resolved(event_id):
+            click.echo(f"✅ Cleared event: {event_id}")
+        else:
+            click.echo(f"❌ Event not found: {event_id}")
+    else:
+        # Determine which event types to clear
+        if event_type == "error":
+            event_types = ["autotodo.error"]
+        elif event_type == "violation":
+            event_types = ["pm.violation"]
+        else:  # all
+            event_types = ["autotodo.error", "pm.violation"]
+
+        # Count pending events
+        total_count = 0
+        for et in event_types:
+            pending = event_log.list_events(event_type=et, status="pending")
+            total_count += len(pending)
+
+        if total_count == 0:
+            click.echo("No pending events to clear.")
+            return
+
+        if not yes:
+            message = f"Clear all {total_count} pending event(s)?"
+            if not click.confirm(message):
+                click.echo("Cancelled.")
+                return
+
+        # Mark all as resolved
+        total_cleared = 0
+        for et in event_types:
+            cleared = event_log.mark_all_resolved(event_type=et)
+            total_cleared += cleared
+
+        click.echo(f"✅ Cleared {total_cleared} event(s).")
+
+
+@autotodos_group.command(name="violations")
+@click.option(
+    "--format",
+    type=click.Choice(["table", "json"], case_sensitive=False),
+    default="table",
+    help="Output format (table or json)",
+)
+def list_pm_violations(format):
+    """List PM delegation violations.
+
+    Shows instances where PM asked user to do something manually
+    instead of delegating to an agent. These are PM behavior errors
+    that should be corrected, not todos to delegate.
+
+    Examples:
+        claude-mpm autotodos violations
+        claude-mpm autotodos violations --format json
+    """
+    event_log = get_event_log()
+    violations = event_log.list_events(event_type="pm.violation", status="pending")
+
+    if not violations:
+        click.echo("✅ No PM violations detected. All delegation patterns are correct!")
+        return
+
+    if format == "json":
+        # JSON output for programmatic use
+        click.echo(json.dumps(violations, indent=2))
+    else:
+        # Table output for human readability
+        click.echo("\n" + "=" * 80)
+        click.echo("PM Delegation Violations")
+        click.echo("=" * 80)
+        click.echo("\n⚠️  PM asked user to do these manually instead of delegating:\n")
+
+        for i, violation in enumerate(violations, 1):
+            payload = violation.get("payload", {})
+            click.echo(f"{i}. Pattern: {payload.get('pattern_type', 'Unknown')}")
+            click.echo(f'   Original: "{payload.get("original_text", "")}"')
+            click.echo(f"   Should delegate: {payload.get('suggested_action', '')}")
+            click.echo(f"   Severity: {payload.get('severity', 'unknown')}")
+            click.echo(f"   Timestamp: {violation.get('timestamp', 'Unknown')}")
+            click.echo()
+
+        click.echo("=" * 80)
+        click.echo(f"Total: {len(violations)} violation(s) detected")
+        click.echo("\n💡 These are PM behavior errors - PM should delegate these tasks")
+        click.echo("   to appropriate agents instead of asking user to do them.")
+        click.echo("\nTo clear: claude-mpm autotodos clear --event-type violation")
+
+
+@autotodos_group.command(name="scan")
+@click.argument("text", required=False)
+@click.option(
+    "--file",
+    "-f",
+    type=click.Path(exists=True),
+    help="Scan text from file instead of argument",
+)
+@click.option(
+    "--format",
+    type=click.Choice(["table", "json"], case_sensitive=False),
+    default="table",
+    help="Output format (table or json)",
+)
+@click.option(
+    "--save",
+    is_flag=True,
+    help="Save detections to event log as PM violations",
+)
+def scan_delegation_patterns(text, file, format, save):
+    """Scan text for delegation anti-patterns.
+
+    Detects when PM asks user to do something manually instead of
+    delegating to an agent. Helps enforce the delegation principle.
+
+    Examples:
+        claude-mpm autotodos scan "Make sure .env.local is in .gitignore"
+        claude-mpm autotodos scan -f response.txt
+        claude-mpm autotodos scan -f response.txt --save
+        echo "You'll need to run npm install" | claude-mpm autotodos scan
+    """
+    detector = get_delegation_detector()
+
+    # Read text from file, argument, or stdin
+    if file:
+        text = Path(file).read_text()
+    elif not text:
+        # Read from stdin
+        import sys
+
+        text = sys.stdin.read()
+
+    if not text or not text.strip():
+        click.echo("Error: No text provided to scan.", err=True)
+        click.echo("\nUsage:", err=True)
+        click.echo("  claude-mpm autotodos scan 'text to scan'", err=True)
+        click.echo("  claude-mpm autotodos scan -f file.txt", err=True)
+        click.echo("  echo 'text' | claude-mpm autotodos scan", err=True)
+        return
+
+    # Detect delegation patterns
+    detections = detector.detect_user_delegation(text)
+
+    if not detections:
+        click.echo("✅ No delegation anti-patterns detected!")
+        return
+
+    # Save to event log if requested
+    if save:
+        event_log = get_event_log()
+        for detection in detections:
+            # Format as PM violation payload
+            payload = {
+                "violation_type": "delegation_anti_pattern",
+                "pattern_type": detection["pattern_type"],
+                "original_text": detection["original_text"],
+                "suggested_action": detection["suggested_todo"],
+                "action": detection["action"],
+                "source": "delegation_detector",
+                "severity": "warning",
+                "message": f"PM asked user to do something manually: {detection['original_text'][:80]}...",
+            }
+            event_log.append_event(
+                event_type="pm.violation", payload=payload, status="pending"
+            )
+        click.echo(f"\n✅ Saved {len(detections)} violation(s) to event log")
+
+    # Output results
+    if format == "json":
+        # JSON output for programmatic use
+        click.echo(json.dumps(detections, indent=2))
+    else:
+        # Table output for human readability
+        click.echo("\n" + "=" * 80)
+        click.echo("Delegation Anti-Patterns Detected")
+        click.echo("=" * 80)
+        click.echo(
+            "\n⚠️  PM is asking user to do these manually instead of delegating:\n"
+        )
+
+        for i, detection in enumerate(detections, 1):
+            click.echo(f"{i}. Pattern: {detection['pattern_type']}")
+            click.echo(f'   Original: "{detection["original_text"]}"')
+            click.echo(f"   Suggested Todo: {detection['suggested_todo']}")
+            click.echo(f"   Action: {detection['action']}")
+            click.echo()
+
+        click.echo("=" * 80)
+        click.echo(f"Total: {len(detections)} anti-pattern(s) detected")
+        click.echo("\n💡 Tip: PM should delegate these tasks to appropriate agents")
+        click.echo("   instead of asking the user to do them manually.")
+
+        if not save:
+            click.echo("\n   Use --save to add these as autotodos for PM to see.")
+
+
+# Register the command group
+def register_commands(cli):
+    """Register autotodos commands with CLI.
+
+    Args:
+        cli: Click CLI group to register commands with
+    """
+    cli.add_command(autotodos_group)