feat: include all plugin resources in package distribution

Copied all plugin resources to src/superclaude/ for package inclusion:
- agents/ (3 agent definitions)
- hooks/ (hooks.json configuration)
- scripts/ (2 utility scripts)

Updated packaging configuration:
- pyproject.toml: Added explicit includes for all resource types
  - skills/**/*.md, *.ts, *.json
  - commands/**/*.md
  - agents/**/*.md
  - hooks/**/*.json
  - scripts/**/*.py, *.sh

- MANIFEST.in: Added recursive-include for all directories
  - commands, agents, hooks, scripts, skills

Added README.md to each directory explaining sync requirements
until v5.0 plugin system is implemented.

Structure:
src/superclaude/
├── agents/          (3 .md files + README)
├── commands/        (5 .md files + README)
├── hooks/           (hooks.json + README)
├── scripts/         (2 files + README)
└── skills/          (confidence-check/)

Total: 16 non-Python resource files included

This ensures all SuperClaude resources are available when installed
via pipx/pip from PyPI.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

MANIFEST.in

@@ -7,9 +7,12 @@ include SECURITY.md
 include pyproject.toml
 recursive-include docs *.md
 recursive-include tests *.py
-recursive-include src/superclaude *.py *.md *.ts *.json
+recursive-include src/superclaude *.py *.md *.ts *.json *.sh
 recursive-include src/superclaude/commands *.md
-recursive-include src/superclaude/skills *.md *.json
+recursive-include src/superclaude/agents *.md
+recursive-include src/superclaude/hooks *.json
+recursive-include src/superclaude/scripts *.py *.sh
+recursive-include src/superclaude/skills *.md *.ts *.json
 global-exclude __pycache__
 global-exclude *.py[co]
 global-exclude .DS_Store

pyproject.toml

@@ -69,8 +69,14 @@ superclaude = "superclaude.pytest_plugin"
 [tool.hatch.build.targets.wheel]
 packages = ["src/superclaude"]
 include = [
-    "src/superclaude/skills/confidence-check/**",
+    "src/superclaude/skills/**/*.md",
+    "src/superclaude/skills/**/*.ts",
+    "src/superclaude/skills/**/*.json",
     "src/superclaude/commands/**/*.md",
+    "src/superclaude/agents/**/*.md",
+    "src/superclaude/hooks/**/*.json",
+    "src/superclaude/scripts/**/*.py",
+    "src/superclaude/scripts/**/*.sh",
 ]
 
 [tool.hatch.build.targets.sdist]

src/superclaude/agents/README.md

@@ -0,0 +1,20 @@
+# SuperClaude Agents
+
+This directory contains agent definition files for specialized AI agents.
+
+## Available Agents
+
+- **deep-research.md** - Autonomous web research agent
+- **repo-index.md** - Repository indexing agent
+- **self-review.md** - Code review and quality check agent
+
+## Important
+
+These agents are copies from `plugins/superclaude/agents/` for package distribution.
+
+When updating agents:
+1. Edit files in `plugins/superclaude/agents/`
+2. Copy changes to `src/superclaude/agents/`
+3. Both locations must stay in sync
+
+In v5.0, the plugin system will use `plugins/` directly.

src/superclaude/agents/deep-research.md

@@ -0,0 +1,31 @@
+---
+name: deep-research
+description: Adaptive research specialist for external knowledge gathering
+category: analysis
+---
+
+# Deep Research Agent
+
+Deploy this agent whenever the SuperClaude Agent needs authoritative information from outside the repository.
+
+## Responsibilities
+- Clarify the research question, depth (`quick`, `standard`, `deep`, `exhaustive`), and deadlines.
+- Draft a lightweight plan (goals, search pivots, likely sources).
+- Execute searches in parallel using approved tools (Tavily, WebFetch, Context7, Sequential).
+- Track sources with credibility notes and timestamps.
+- Deliver a concise synthesis plus a citation table.
+
+## Workflow
+1. **Understand** — restate the question, list unknowns, determine blocking assumptions.
+2. **Plan** — choose depth, divide work into hops, and mark tasks that can run concurrently.
+3. **Execute** — run searches, capture key facts, and highlight contradictions or gaps.
+4. **Validate** — cross-check claims, verify official documentation, and flag remaining uncertainty.
+5. **Report** — respond with:
+   ```
+   🧭 Goal:
+   📊 Findings summary (bullets)
+   🔗 Sources table (URL, title, credibility score, note)
+   🚧 Open questions / suggested follow-up
+   ```
+
+Escalate back to the SuperClaude Agent if authoritative sources are unavailable or if further clarification from the user is required.

src/superclaude/agents/repo-index.md

@@ -0,0 +1,30 @@
+---
+name: repo-index
+description: Repository indexing and codebase briefing assistant
+category: discovery
+---
+
+# Repository Index Agent
+
+Use this agent at the start of a session or when the codebase changes substantially. Its goal is to compress repository context so subsequent work stays token-efficient.
+
+## Core Duties
+- Inspect directory structure (`src/`, `tests/`, `docs/`, configuration, scripts).
+- Surface recently changed or high-risk files.
+- Generate/update `PROJECT_INDEX.md` and `PROJECT_INDEX.json` when stale (>7 days) or missing.
+- Highlight entry points, service boundaries, and relevant README/ADR docs.
+
+## Operating Procedure
+1. Detect freshness: if an index exists and is younger than 7 days, confirm and stop. Otherwise continue.
+2. Run parallel glob searches for the five focus areas (code, documentation, configuration, tests, scripts).
+3. Summarize results in a compact brief:
+   ```
+   📦 Summary:
+     - Code: src/superclaude (42 files), pm/ (TypeScript agents)
+     - Tests: tests/pm_agent, pytest plugin smoke tests
+     - Docs: docs/developer-guide, PROJECT_INDEX.md (to be regenerated)
+   🔄 Next: create PROJECT_INDEX.md (94% token savings vs raw scan)
+   ```
+4. If regeneration is needed, instruct the SuperClaude Agent to run the automated index task or execute it via available tools.
+
+Keep responses short and data-driven so the SuperClaude Agent can reference the brief without rereading the entire repository.

src/superclaude/agents/self-review.md

@@ -0,0 +1,33 @@
+---
+name: self-review
+description: Post-implementation validation and reflexion partner
+category: quality
+---
+
+# Self Review Agent
+
+Use this agent immediately after an implementation wave to confirm the result is production-ready and to capture lessons learned.
+
+## Primary Responsibilities
+- Verify tests and tooling reported by the SuperClaude Agent.
+- Run the four mandatory self-check questions:
+  1. Tests/validation executed? (include command + outcome)
+  2. Edge cases covered? (list anything intentionally left out)
+  3. Requirements matched? (tie back to acceptance criteria)
+  4. Follow-up or rollback steps needed?
+- Summarize residual risks and mitigation ideas.
+- Record reflexion patterns when defects appear so the SuperClaude Agent can avoid repeats.
+
+## How to Operate
+1. Review the task summary and implementation diff supplied by the SuperClaude Agent.
+2. Confirm test evidence; if missing, request a rerun before approval.
+3. Produce a short checklist-style report:
+   ```
+   ✅ Tests: uv run pytest -m unit (pass)
+   ⚠️ Edge cases: concurrency behaviour not exercised
+   ✅ Requirements: acceptance criteria met
+   📓 Follow-up: add load tests next sprint
+   ```
+4. When issues remain, recommend targeted actions rather than reopening the entire task.
+
+Keep answers brief—focus on evidence, not storytelling. Hand results back to the SuperClaude Agent for the final user response.

src/superclaude/hooks/README.md

@@ -0,0 +1,18 @@
+# SuperClaude Hooks
+
+This directory contains hook configuration files.
+
+## Files
+
+- **hooks.json** - Hook definitions for event-driven automation
+
+## Important
+
+These hooks are copies from `plugins/superclaude/hooks/` for package distribution.
+
+When updating hooks:
+1. Edit files in `plugins/superclaude/hooks/`
+2. Copy changes to `src/superclaude/hooks/`
+3. Both locations must stay in sync
+
+In v5.0, the plugin system will use `plugins/` directly.

src/superclaude/hooks/hooks.json

@@ -0,0 +1,15 @@
+{
+  "hooks": {
+    "SessionStart": [
+      {
+        "hooks": [
+          {
+            "type": "command",
+            "command": "./scripts/session-init.sh",
+            "timeout": 10
+          }
+        ]
+      }
+    ]
+  }
+}

src/superclaude/scripts/README.md

@@ -0,0 +1,19 @@
+# SuperClaude Scripts
+
+This directory contains utility scripts.
+
+## Files
+
+- **clean_command_names.py** - Command name cleaning utility
+- **session-init.sh** - Session initialization script
+
+## Important
+
+These scripts are copies from `plugins/superclaude/scripts/` for package distribution.
+
+When updating scripts:
+1. Edit files in `plugins/superclaude/scripts/`
+2. Copy changes to `src/superclaude/scripts/`
+3. Both locations must stay in sync
+
+In v5.0, the plugin system will use `plugins/` directly.

src/superclaude/scripts/clean_command_names.py

@@ -0,0 +1,168 @@
+#!/usr/bin/env python3
+"""
+SuperClaude Plugin - Command Name Attribute Cleanup Script
+
+This script automatically removes redundant 'name:' attributes from command
+frontmatter in markdown files. The plugin naming system derives command names
+from the plugin name + filename, making explicit name attributes unnecessary.
+
+Usage:
+    python scripts/clean_command_names.py
+
+Exit Codes:
+    0 - Success (files modified or no changes needed)
+    1 - Error (directory not found or processing failed)
+"""
+
+import os
+import re
+import sys
+from pathlib import Path
+from typing import Tuple
+
+
+def find_project_root() -> Path:
+    """
+    Find the project root directory by locating plugin.json.
+
+    Returns:
+        Path: Project root directory
+
+    Raises:
+        FileNotFoundError: If project root cannot be determined
+    """
+    script_dir = Path(__file__).parent.absolute()
+    current_dir = script_dir.parent
+
+    # Look for plugin.json up to 3 levels up
+    for _ in range(3):
+        if (current_dir / "plugin.json").exists():
+            return current_dir
+        current_dir = current_dir.parent
+
+    raise FileNotFoundError("Could not find project root (plugin.json not found)")
+
+
+def clean_name_attributes(content: str) -> Tuple[str, bool]:
+    """
+    Remove 'name:' attributes from YAML frontmatter.
+
+    Args:
+        content: File content as string
+
+    Returns:
+        Tuple of (cleaned content, was_modified)
+    """
+    # Pattern to match 'name: value' in frontmatter
+    # Matches: name: value, name : value, NAME: value (case-insensitive)
+    name_pattern = re.compile(r'^\s*name\s*:\s*.*$', re.MULTILINE | re.IGNORECASE)
+
+    # Check if modification is needed
+    if not name_pattern.search(content):
+        return content, False
+
+    # Remove name attributes
+    cleaned = name_pattern.sub('', content)
+
+    # Clean up multiple consecutive newlines (max 2)
+    cleaned = re.sub(r'\n{3,}', '\n\n', cleaned)
+
+    # Remove trailing whitespace while preserving final newline
+    cleaned = cleaned.rstrip() + '\n' if cleaned.strip() else ''
+
+    return cleaned, True
+
+
+def process_commands_directory(commands_dir: Path) -> int:
+    """
+    Process all command markdown files in directory.
+
+    Args:
+        commands_dir: Path to commands directory
+
+    Returns:
+        Number of files modified
+    """
+    if not commands_dir.is_dir():
+        print(f"Error: Directory not found: {commands_dir}", file=sys.stderr)
+        return -1
+
+    modified_count = 0
+    processed_count = 0
+    error_count = 0
+
+    print(f"🔍 Scanning: {commands_dir}")
+    print(f"{'='*60}")
+
+    # Process all .md files
+    for md_file in sorted(commands_dir.glob("*.md")):
+        processed_count += 1
+
+        try:
+            # Read file content
+            content = md_file.read_text(encoding='utf-8')
+
+            # Clean name attributes
+            cleaned_content, was_modified = clean_name_attributes(content)
+
+            if was_modified:
+                # Write cleaned content back
+                md_file.write_text(cleaned_content, encoding='utf-8')
+                modified_count += 1
+                print(f"✅ Modified: {md_file.name}")
+            else:
+                print(f"⏭️  Skipped:  {md_file.name} (no name attribute)")
+
+        except Exception as e:
+            error_count += 1
+            print(f"❌ Error:    {md_file.name} - {e}", file=sys.stderr)
+
+    print(f"{'='*60}")
+    print(f"📊 Summary:")
+    print(f"   • Processed: {processed_count} files")
+    print(f"   • Modified:  {modified_count} files")
+    print(f"   • Errors:    {error_count} files")
+
+    return modified_count if error_count == 0 else -1
+
+
+def main() -> int:
+    """
+    Main execution function.
+
+    Returns:
+        Exit code (0 for success, 1 for error)
+    """
+    print("🚀 SuperClaude Plugin - Command Name Cleanup")
+    print()
+
+    try:
+        # Find project root and commands directory
+        project_root = find_project_root()
+        commands_dir = project_root / "commands"
+
+        print(f"📁 Project root: {project_root}")
+        print()
+
+        # Process commands directory
+        result = process_commands_directory(commands_dir)
+
+        if result < 0:
+            print("\n❌ Cleanup failed with errors", file=sys.stderr)
+            return 1
+
+        print(f"\n✅ Cleanup completed successfully")
+        return 0
+
+    except FileNotFoundError as e:
+        print(f"❌ Error: {e}", file=sys.stderr)
+        return 1
+    except Exception as e:
+        print(f"❌ Unexpected error: {e}", file=sys.stderr)
+        import traceback
+        traceback.print_exc()
+        return 1
+
+
+if __name__ == "__main__":
+    sys.exit(main())

src/superclaude/scripts/session-init.sh

@@ -0,0 +1,30 @@
+#!/bin/bash
+# SuperClaude SessionStart initialization script
+# Auto-executed when Claude Code session starts
+
+# 1. Check git status
+if git status --porcelain > /dev/null 2>&1; then
+    status=$(git status --porcelain)
+    if [ -z "$status" ]; then
+        echo "📊 Git: clean"
+    else
+        count=$(echo "$status" | wc -l | tr -d ' ')
+        echo "📊 Git: ${count} files"
+    fi
+else
+    echo "📊 Git: not a repo"
+fi
+
+# 2. Remind token budget
+echo "💡 Use /context to confirm token budget."
+
+# 3. Report core services
+echo ""
+echo "🛠️ Core Services Available:"
+echo "  ✅ Confidence Check (pre-implementation validation)"
+echo "  ✅ Deep Research (web/MCP integration)"
+echo "  ✅ Repository Index (token-efficient exploration)"
+echo ""
+echo "SC Agent ready — awaiting task assignment."
+
+exit 0