sdd-mcp-server 2.2.0 → 3.0.0

package/README.md

@@ -6,11 +6,15 @@
 
 A Model Context Protocol (MCP) server implementing Spec-Driven Development (SDD) workflows for AI-agent CLIs and IDEs like Claude Code, Cursor, and others.
 
-> 🎯 **v2.2.0 - Unified Installation & Crash Safety**: New `npx sdd-mcp install` command installs both skills (to `.claude/skills/`) AND steering documents (to `.spec/steering/`) in one step! Skills now explicitly reference their relevant steering documents for better guidance. Also includes **atomic file writes** for spec.json crash safety - files are never left in a corrupted state even if the process is interrupted. (Thanks to @Lucas Wang for the atomic writes contribution!)
+> 🚀 **v3.0.0 - Comprehensive Plugin Architecture**: SDD-MCP is now a full-featured Claude Code plugin system! Adds **6 component types** (skills, steering, rules, contexts, agents, hooks), **4 new managers** (RulesManager, ContextManager, AgentManager, HookLoader), and **3 new skills** (sdd-review, sdd-security-check, sdd-test-gen). Unified install CLI supports `--rules`, `--contexts`, `--agents`, `--hooks`, `--all` flags. Inspired by everything-claude-code architecture.
 
-> 🔄 **v2.1.0 - Directory Migration**: The SDD specification directory has been renamed from `.kiro` to `.spec`. Use `npx sdd-mcp migrate-kiro` to migrate existing projects. Legacy `.kiro` directories are still supported for backwards compatibility.
+> 🔧 **v2.2.1 - CLI Fix**: Fixed `npx sdd-mcp` not working due to npm package name collision. Now use `npx sdd-mcp-server` for all CLI commands. The unified entry point handles both CLI commands and MCP server mode.
 
-> 🔧 **v2.0.3 - CLI Subcommand Support**: `npx sdd-mcp install-skills` now works correctly! Created proper CLI entry point with subcommand support.
+> 🎯 **v2.2.0 - Unified Installation & Crash Safety**: `npx sdd-mcp-server install` command installs both skills (to `.claude/skills/`) AND steering documents (to `.spec/steering/`) in one step! Skills now explicitly reference their relevant steering documents for better guidance. Also includes **atomic file writes** for spec.json crash safety - files are never left in a corrupted state even if the process is interrupted. (Thanks to @Lucas Wang for the atomic writes contribution!)
+
+> 🔄 **v2.1.0 - Directory Migration**: The SDD specification directory has been renamed from `.kiro` to `.spec`. Use `npx sdd-mcp-server migrate-kiro` to migrate existing projects. Legacy `.kiro` directories are still supported for backwards compatibility.
+
+> 🔧 **v2.0.3 - CLI Subcommand Support**: `npx sdd-mcp-server install-skills` now works correctly! Created proper CLI entry point with subcommand support.
 
 > 🚀 **v2.0.0 - Hybrid MCP + Agent Skills Architecture**: Restructured for token efficiency! Template/guidance tools (requirements, design, tasks, steering, implement) are now **Claude Code Agent Skills** loaded on-demand. Action-oriented tools remain as MCP tools. ~55% token savings in typical operations.
 
@@ -163,28 +167,42 @@ SDD now uses a **hybrid architecture** for better token efficiency:
 - **MCP Tools**: Action-oriented operations (init, status, approve, quality-check, validate, spec-impl)
 - **Agent Skills**: Template/guidance-heavy operations (requirements, design, tasks, steering, implement, commit)
 
-### Installing Agent Skills and Steering Documents
+### Installing Components (v3.0+)
 
 ```bash
-# Recommended: Install both skills AND steering documents
-npx sdd-mcp install
+# Recommended: Install ALL components (skills, steering, rules, contexts, agents, hooks)
+npx sdd-mcp-server install --all
+
+# Install specific component types
+npx sdd-mcp-server install --skills      # Skills to .claude/skills/
+npx sdd-mcp-server install --steering    # Steering to .spec/steering/
+npx sdd-mcp-server install --rules       # Rules to .claude/rules/
+npx sdd-mcp-server install --contexts    # Contexts to .claude/contexts/
+npx sdd-mcp-server install --agents      # Agents to .claude/agents/
+npx sdd-mcp-server install --hooks       # Hooks to .claude/hooks/
 
-# Install skills only (to .claude/skills/)
-npx sdd-mcp install --skills
+# Install multiple component types
+npx sdd-mcp-server install --skills --rules --agents
 
-# Install steering documents only (to .spec/steering/)
-npx sdd-mcp install --steering
+# Default: Install skills + steering (backward compatible)
+npx sdd-mcp-server install
 
-# List available skills and steering documents
-npx sdd-mcp install --list
+# List all available components
+npx sdd-mcp-server install --list
 
-# Legacy: Install skills only (same as --skills)
-npx sdd-mcp install-skills
+# Legacy: Install skills only
+npx sdd-mcp-server install-skills
 ```
 
-**What gets installed:**
-- **Skills** (`.claude/skills/`): Workflow guidance for Claude Code - requirements, design, tasks, implement, etc.
-- **Steering** (`.spec/steering/`): Project-wide rules - TDD guidelines, SOLID principles, security checklist, etc.
+**Component Types (v3.0):**
+| Component | Install Path | Purpose |
+|-----------|--------------|---------|
+| **Skills** | `.claude/skills/` | Workflow guidance (requirements, design, tasks, implement, etc.) |
+| **Steering** | `.spec/steering/` | Project-wide conventions (TDD guidelines, SOLID principles, security) |
+| **Rules** | `.claude/rules/` | Always-active guidelines (coding-style, testing, security, git-workflow) |
+| **Contexts** | `.claude/contexts/` | Mode-specific prompts (dev, review, planning, security-audit, research) |
+| **Agents** | `.claude/agents/` | Specialized AI personas (planner, architect, reviewer, implementer) |
+| **Hooks** | `.claude/hooks/` | Event-driven automation (pre-tool-use, post-tool-use, session events) |
 
 ### Migrating from .kiro to .spec (v2.1.0+)
 
@@ -192,13 +210,13 @@ If you have existing projects using the legacy `.kiro` directory, migrate to the
 
 ```bash
 # Preview migration (dry run)
-npx sdd-mcp migrate-kiro --dry-run
+npx sdd-mcp-server migrate-kiro --dry-run
 
 # Perform migration
-npx sdd-mcp migrate-kiro
+npx sdd-mcp-server migrate-kiro
 
 # Migrate a specific project
-npx sdd-mcp migrate-kiro --path ./my-project
+npx sdd-mcp-server migrate-kiro --path ./my-project
 ```
 
 **Note**: Legacy `.kiro` directories are still supported for backwards compatibility, but new projects will use `.spec`.
@@ -217,6 +235,9 @@ After installation, use these skills in Claude Code:
 | `/sdd-steering` | Create/update project-specific steering documents |
 | `/sdd-steering-custom` | Create custom steering with inclusion modes |
 | `/sdd-commit` | Commit/PR guidelines with conventional commits |
+| `/sdd-review` | **NEW in v3.0** - Linus-style direct code review with severity levels |
+| `/sdd-security-check` | **NEW in v3.0** - OWASP Top 10 security audit checklist |
+| `/sdd-test-gen` | **NEW in v3.0** - TDD test generation with Red-Green-Refactor workflow |
 
 ### Token Efficiency
 
@@ -241,14 +262,14 @@ Once connected to your AI client, you can use these MCP tools:
 | `sdd-spec-impl` | Execute tasks with TDD | Kent Beck's Red-Green-Refactor methodology |
 | `sdd-list-skills` | List available Agent Skills | Shows skills that can be installed for Claude Code |
 
-> **Note**: Template/guidance tools (`sdd-requirements`, `sdd-design`, `sdd-tasks`, `sdd-steering`, `sdd-implement`) are now **Agent Skills**. Install them with `npx sdd-mcp install-skills` and use as `/sdd-requirements`, `/sdd-design`, etc.
+> **Note**: Template/guidance tools (`sdd-requirements`, `sdd-design`, `sdd-tasks`, `sdd-steering`, `sdd-implement`) are now **Agent Skills**. Install them with `npx sdd-mcp-server install-skills` and use as `/sdd-requirements`, `/sdd-design`, etc.
 
 ## 💡 Basic Workflow
 
 1. **Setup: Install Skills & Steering, Initialize Project**
    ```bash
    # Install skills and steering documents (recommended)
-   npx sdd-mcp install
+   npx sdd-mcp-server install
 
    # Initialize project with MCP tool
    Use sdd-init to create a new SDD project
@@ -300,40 +321,57 @@ Once connected to your AI client, you can use these MCP tools:
    Use sdd-context-load to restore project memory
    ```
 
-## Latest Updates (v2.2.0)
+## Latest Updates (v3.0.0)
 
-**What's New**:
-- 🎯 **Unified Installation**: `npx sdd-mcp install` installs both skills AND steering documents
-- ✅ **Skill-Steering References**: Each skill now explicitly references relevant steering documents
-- ✅ **Steering Source Files**: Static steering docs moved to package for consistent installation
-- ✅ **Improved `/sdd-steering` Output**: Clearer distinction between dynamic and static documents
+**What's New - Comprehensive Plugin Architecture**:
+- 🚀 **6 Component Types**: Skills, Steering, Rules, Contexts, Agents, Hooks
+- 🤖 **4 New Managers**: RulesManager, ContextManager, AgentManager, HookLoader
+- ✨ **3 New Skills**: sdd-review (Linus-style review), sdd-security-check (OWASP audit), sdd-test-gen (TDD)
+- 🎯 **Unified CLI**: `--rules`, `--contexts`, `--agents`, `--hooks`, `--all` flags
+- 📦 **Plugin Manifest**: `.claude-plugin/plugin.json` for Claude Code integration
+- ✅ **199 Tests**: 58 new tests for component managers, full TDD coverage
+
+**New Component Details**:
+| Component | Count | Examples |
+|-----------|-------|----------|
+| Rules | 6 | coding-style, testing, security, git-workflow, error-handling, sdd-workflow |
+| Contexts | 5 | dev, review, planning, security-audit, research |
+| Agents | 6 | planner, architect, reviewer, implementer, security-auditor, tdd-guide |
+| Hooks | 7 | validate-sdd-workflow, check-test-coverage, update-spec-status, load-project-context |
 
 **Upgrade Commands**:
 ```bash
-# Install skills AND steering (recommended)
-npx sdd-mcp install
-
-# Install skills only
-npx sdd-mcp install --skills
+# Install ALL components (recommended for v3.0)
+npx sdd-mcp-server install --all
 
-# Install steering only
-npx sdd-mcp install --steering
+# Install specific components
+npx sdd-mcp-server install --skills --rules --agents
 
-# List available content
-npx sdd-mcp install --list
+# List all available components
+npx sdd-mcp-server install --list
 
 # Show CLI help
-npx sdd-mcp --help
+npx sdd-mcp-server --help
 ```
 
-**Previous Versions (v2.0.x)**:
-- v2.0.3: CLI subcommand support (`npx sdd-mcp install-skills` works)
+**Previous Versions (v2.x)**:
+- v2.2.1: CLI fix for npm package name collision
+- v2.2.0: Unified installation, atomic file writes, skill-steering references
+- v2.1.0: Directory migration from .kiro to .spec
+- v2.0.3: CLI subcommand support
 - v2.0.0: Hybrid MCP + Agent Skills architecture, ~55% token savings
 
 ## Previous Versions
 
+### v2.2.x
+- v2.2.1: CLI fix for npm package name collision
+- v2.2.0: Unified installation, atomic file writes, skill-steering references
+
+### v2.1.x
+- v2.1.0: Directory migration from `.kiro` to `.spec`
+
 ### v2.0.x
-- v2.0.3: CLI subcommand support (`npx sdd-mcp install-skills` works)
+- v2.0.3: CLI subcommand support (`npx sdd-mcp-server install-skills` works)
 - v2.0.2: ESM compatibility fix for install-skills CLI
 - v2.0.1: Codebase simplification, removed 7,131 lines of dead code
 - v2.0.0: Hybrid MCP + Agent Skills architecture, ~55% token savings
@@ -421,15 +459,28 @@ claude mcp add sdd "sdd-mcp-server"
 
 ## 🏗️ Key Features
 
+### Core SDD Workflow
 - **5-Phase SDD Workflow**: INIT → REQUIREMENTS → DESIGN → TASKS → IMPLEMENTATION
-- **Comprehensive Multi-Language Analysis**: Automatic detection of TypeScript, JavaScript, Java, Python, Go, Ruby, PHP, Rust, C#, Scala projects with framework-specific insights
-- **Framework Detection**: Recognizes Spring Boot, Django, FastAPI, Flask, Rails, Laravel, Express, React, Vue, Angular, Next.js, and 20+ other frameworks
 - **TDD-First Task Generation**: All implementation tasks follow Test-Driven Development (RED-GREEN-REFACTOR) methodology
-- **Coding Principles Enforcement**: Built-in SOLID, DRY, KISS, YAGNI, Separation of Concerns, and Modularity guidance
-- **Context-Aware Generation**: Analyzes package.json, dependencies, build tools, test frameworks, and project structure for real content
 - **EARS-Formatted Requirements**: Generate acceptance criteria based on actual npm scripts and dependencies
-- **Architecture Pattern Recognition**: Detects DDD, MVC, Microservices, Clean Architecture patterns in your codebase
 - **Quality Enforcement**: Linus-style 5-layer code review system with security (OWASP Top 10) checks
+
+### Plugin Architecture (v3.0)
+- **6 Component Types**: Skills, Steering, Rules, Contexts, Agents, Hooks for comprehensive AI guidance
+- **Specialized Agents**: Planner, Architect, Reviewer, Implementer, Security-Auditor, TDD-Guide personas
+- **Always-Active Rules**: Coding-style, Testing, Security, Git-workflow, Error-handling enforcement
+- **Mode-Specific Contexts**: Development, Review, Planning, Security-audit, Research modes
+- **Event-Driven Hooks**: Pre/post tool-use and session lifecycle automation
+- **Plugin Manifest**: `.claude-plugin/plugin.json` for Claude Code integration
+
+### Codebase Analysis
+- **Comprehensive Multi-Language Analysis**: Automatic detection of TypeScript, JavaScript, Java, Python, Go, Ruby, PHP, Rust, C#, Scala projects with framework-specific insights
+- **Framework Detection**: Recognizes Spring Boot, Django, FastAPI, Flask, Rails, Laravel, Express, React, Vue, Angular, Next.js, and 20+ other frameworks
+- **Architecture Pattern Recognition**: Detects DDD, MVC, Microservices, Clean Architecture patterns in your codebase
+- **Context-Aware Generation**: Analyzes package.json, dependencies, build tools, test frameworks, and project structure for real content
+
+### Guidelines & Standards
+- **Coding Principles Enforcement**: Built-in SOLID, DRY, KISS, YAGNI, Separation of Concerns, and Modularity guidance
 - **Comprehensive Steering Documents**: 8 auto-generated guidance docs (product, tech, structure, linus-review, commit, tdd-guideline, security-check, principles)
 - **Multi-Language Support**: 10 languages with cultural adaptation (en, es, fr, de, it, pt, ru, ja, zh, ko)
 - **Template Engine**: Handlebars-based file generation with project-specific data
@@ -556,10 +607,20 @@ As of v1.4.3, comprehensive codebase analysis is automatic with multi-language d
 ## 📖 Advanced Documentation
 
 For detailed documentation on:
+- **📥 Installation Guide**: See [docs/INSTALL-GUIDE.md](docs/INSTALL-GUIDE.md) for complete CLI usage examples with real output
 - **🤖 AI Agent Guide**: See [AGENTS.md](AGENTS.md) for detailed instructions on using this server with AI agents
 - **🏗️ Architecture Overview**: See [ARCHITECTURE.md](ARCHITECTURE.md) for complete system design, layered architecture, module loading, and Mermaid diagrams
+- **📦 Plugin Manifest**: See [.claude-plugin/plugin.json](.claude-plugin/plugin.json) for Claude Code plugin configuration
 - **Plugin Development**: See [DEPLOYMENT.md](DEPLOYMENT.md)
 - **Docker Deployment**: See [Dockerfile](Dockerfile) and [docker-compose.yml](docker-compose.yml)
+
+**Component Documentation (v3.0)**:
+- **Rules**: See `rules/*.md` for always-active coding guidelines
+- **Contexts**: See `contexts/*.md` for mode-specific system prompts
+- **Agents**: See `agents/*.md` for specialized AI personas
+- **Hooks**: See `hooks/**/*.md` for event-driven automation
+
+**Steering Documents**:
 - **Code Quality Standards**: Review `.spec/steering/linus-review.md`
 - **TDD Guidelines**: See `.spec/steering/tdd-guideline.md` for complete Test-Driven Development workflow
 - **Coding Principles**: Review `.spec/steering/principles.md` for SOLID, DRY, KISS, YAGNI, SoC, and Modularity guidance

package/dist/adapters/cli/SDDToolAdapter.js

@@ -445,7 +445,7 @@ let SDDToolAdapter = class SDDToolAdapter {
 - Existing steering: Updated preserving customizations
 
 **Tip**: For a unified installation of skills and steering documents, run:
-\`npx sdd-mcp install\`
+\`npx sdd-mcp-server install\`
 
 This installs both \`.claude/skills/\` (workflow guides) and \`.spec/steering/\` (project rules).`;
         }

package/dist/agents/AgentManager.d.ts

@@ -0,0 +1,61 @@
+import { BaseManager, ComponentDescriptor } from '../shared/BaseManager.js';
+/**
+ * Descriptor for an agent component
+ */
+export interface AgentDescriptor extends ComponentDescriptor {
+    /** Agent name */
+    name: string;
+    /** Brief description of the agent */
+    description: string;
+    /** Path to the agent file */
+    path: string;
+    /** Role identifier (planner, architect, reviewer, implementer, etc.) */
+    role: string;
+    /** Area of expertise */
+    expertise: string;
+}
+/**
+ * Manages agent components - discovery, listing, and installation
+ *
+ * Agents are specialized AI personas that can be invoked for different tasks.
+ * Each agent has a specific role and expertise area.
+ *
+ * @example
+ * ```typescript
+ * const manager = new AgentManager('/path/to/agents');
+ * const agents = await manager.listComponents();
+ * const reviewer = await manager.getAgentByRole('reviewer');
+ * await manager.installComponents('/project/.claude/agents');
+ * ```
+ */
+export declare class AgentManager extends BaseManager<AgentDescriptor> {
+    /**
+     * Create a new AgentManager
+     * @param agentsPath - Path to the agents directory
+     */
+    constructor(agentsPath: string);
+    /**
+     * Parse metadata from agent file content
+     * @param content - Raw content of the agent file
+     * @param filePath - Path to the agent file
+     * @returns Parsed agent descriptor
+     */
+    protected parseMetadata(content: string, filePath: string): AgentDescriptor;
+    /**
+     * Get an agent by its role identifier
+     * @param role - Role identifier to search for
+     * @returns Agent descriptor if found, null otherwise
+     */
+    getAgentByRole(role: string): Promise<AgentDescriptor | null>;
+    /**
+     * Get all available roles
+     * @returns Array of unique role identifiers
+     */
+    listRoles(): Promise<string[]>;
+    /**
+     * Get agents filtered by expertise keyword
+     * @param keyword - Keyword to search in expertise field
+     * @returns Array of agents with matching expertise
+     */
+    findByExpertise(keyword: string): Promise<AgentDescriptor[]>;
+}

package/dist/agents/AgentManager.js

@@ -0,0 +1,75 @@
+import * as path from 'path';
+import { BaseManager } from '../shared/BaseManager.js';
+/**
+ * Manages agent components - discovery, listing, and installation
+ *
+ * Agents are specialized AI personas that can be invoked for different tasks.
+ * Each agent has a specific role and expertise area.
+ *
+ * @example
+ * ```typescript
+ * const manager = new AgentManager('/path/to/agents');
+ * const agents = await manager.listComponents();
+ * const reviewer = await manager.getAgentByRole('reviewer');
+ * await manager.installComponents('/project/.claude/agents');
+ * ```
+ */
+export class AgentManager extends BaseManager {
+    /**
+     * Create a new AgentManager
+     * @param agentsPath - Path to the agents directory
+     */
+    constructor(agentsPath) {
+        super({
+            componentPath: agentsPath,
+            structureType: 'file',
+            fileExtension: '.md',
+        });
+    }
+    /**
+     * Parse metadata from agent file content
+     * @param content - Raw content of the agent file
+     * @param filePath - Path to the agent file
+     * @returns Parsed agent descriptor
+     */
+    parseMetadata(content, filePath) {
+        const metadata = this.parseYamlFrontmatter(content);
+        const fileName = path.basename(filePath, this.config.fileExtension);
+        return {
+            name: metadata.name || fileName,
+            description: metadata.description || '',
+            path: filePath,
+            role: metadata.role || 'assistant', // Default role
+            expertise: metadata.expertise || '',
+        };
+    }
+    /**
+     * Get an agent by its role identifier
+     * @param role - Role identifier to search for
+     * @returns Agent descriptor if found, null otherwise
+     */
+    async getAgentByRole(role) {
+        const agents = await this.listComponents();
+        return agents.find(agent => agent.role === role) || null;
+    }
+    /**
+     * Get all available roles
+     * @returns Array of unique role identifiers
+     */
+    async listRoles() {
+        const agents = await this.listComponents();
+        const roles = agents.map(agent => agent.role);
+        return [...new Set(roles)]; // Return unique roles
+    }
+    /**
+     * Get agents filtered by expertise keyword
+     * @param keyword - Keyword to search in expertise field
+     * @returns Array of agents with matching expertise
+     */
+    async findByExpertise(keyword) {
+        const agents = await this.listComponents();
+        const lowerKeyword = keyword.toLowerCase();
+        return agents.filter(agent => agent.expertise.toLowerCase().includes(lowerKeyword));
+    }
+}
+//# sourceMappingURL=AgentManager.js.map

package/dist/agents/AgentManager.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"AgentManager.js","sourceRoot":"","sources":["../../src/agents/AgentManager.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,IAAI,MAAM,MAAM,CAAC;AAC7B,OAAO,EAAE,WAAW,EAAuB,MAAM,0BAA0B,CAAC;AAkB5E;;;;;;;;;;;;;GAaG;AACH,MAAM,OAAO,YAAa,SAAQ,WAA4B;IAC5D;;;OAGG;IACH,YAAY,UAAkB;QAC5B,KAAK,CAAC;YACJ,aAAa,EAAE,UAAU;YACzB,aAAa,EAAE,MAAM;YACrB,aAAa,EAAE,KAAK;SACrB,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACO,aAAa,CAAC,OAAe,EAAE,QAAgB;QACvD,MAAM,QAAQ,GAAG,IAAI,CAAC,oBAAoB,CAAC,OAAO,CAAC,CAAC;QACpD,MAAM,QAAQ,GAAG,IAAI,CAAC,QAAQ,CAAC,QAAQ,EAAE,IAAI,CAAC,MAAM,CAAC,aAAa,CAAC,CAAC;QAEpE,OAAO;YACL,IAAI,EAAG,QAAQ,CAAC,IAAe,IAAI,QAAQ;YAC3C,WAAW,EAAG,QAAQ,CAAC,WAAsB,IAAI,EAAE;YACnD,IAAI,EAAE,QAAQ;YACd,IAAI,EAAG,QAAQ,CAAC,IAAe,IAAI,WAAW,EAAE,eAAe;YAC/D,SAAS,EAAG,QAAQ,CAAC,SAAoB,IAAI,EAAE;SAChD,CAAC;IACJ,CAAC;IAED;;;;OAIG;IACH,KAAK,CAAC,cAAc,CAAC,IAAY;QAC/B,MAAM,MAAM,GAAG,MAAM,IAAI,CAAC,cAAc,EAAE,CAAC;QAC3C,OAAO,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,EAAE,CAAC,KAAK,CAAC,IAAI,KAAK,IAAI,CAAC,IAAI,IAAI,CAAC;IAC3D,CAAC;IAED;;;OAGG;IACH,KAAK,CAAC,SAAS;QACb,MAAM,MAAM,GAAG,MAAM,IAAI,CAAC,cAAc,EAAE,CAAC;QAC3C,MAAM,KAAK,GAAG,MAAM,CAAC,GAAG,CAAC,KAAK,CAAC,EAAE,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;QAC9C,OAAO,CAAC,GAAG,IAAI,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,sBAAsB;IACpD,CAAC;IAED;;;;OAIG;IACH,KAAK,CAAC,eAAe,CAAC,OAAe;QACnC,MAAM,MAAM,GAAG,MAAM,IAAI,CAAC,cAAc,EAAE,CAAC;QAC3C,MAAM,YAAY,GAAG,OAAO,CAAC,WAAW,EAAE,CAAC;QAC3C,OAAO,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,EAAE,CAC3B,KAAK,CAAC,SAAS,CAAC,WAAW,EAAE,CAAC,QAAQ,CAAC,YAAY,CAAC,CACrD,CAAC;IACJ,CAAC;CACF"}

package/dist/agents/index.d.ts

@@ -0,0 +1 @@
+export { AgentManager, AgentDescriptor } from './AgentManager.js';

package/dist/agents/index.js

@@ -0,0 +1,3 @@
+// Agents module exports
+export { AgentManager } from './AgentManager.js';
+//# sourceMappingURL=index.js.map

package/dist/agents/index.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../../src/agents/index.ts"],"names":[],"mappings":"AAAA,wBAAwB;AAExB,OAAO,EAAE,YAAY,EAAmB,MAAM,mBAAmB,CAAC"}

package/dist/cli/install-skills.d.ts

@@ -1,4 +1,8 @@
 #!/usr/bin/env node
+/**
+ * Component types that can be installed
+ */
+export type ComponentType = 'skills' | 'steering' | 'rules' | 'contexts' | 'agents' | 'hooks';
 /**
  * CLI options for install-skills command
  */
@@ -7,6 +11,14 @@ export interface CLIOptions {
     targetPath: string;
     /** Target path for steering installation */
     steeringPath: string;
+    /** Target path for rules installation */
+    rulesPath: string;
+    /** Target path for contexts installation */
+    contextsPath: string;
+    /** Target path for agents installation */
+    agentsPath: string;
+    /** Target path for hooks installation */
+    hooksPath: string;
     /** Only list skills, don't install */
     listOnly: boolean;
     /** Show help message */
@@ -15,12 +27,26 @@ export interface CLIOptions {
     skillsOnly: boolean;
     /** Install steering only (for unified install) */
     steeringOnly: boolean;
+    /** Install rules only */
+    rulesOnly: boolean;
+    /** Install contexts only */
+    contextsOnly: boolean;
+    /** Install agents only */
+    agentsOnly: boolean;
+    /** Install hooks only */
+    hooksOnly: boolean;
+    /** Components to install (empty means all) */
+    components: ComponentType[];
 }
 /**
- * CLI for installing SDD skills to a project
+ * CLI for installing SDD components to a project
  */
 export declare class InstallSkillsCLI {
     private skillManager;
+    private rulesManager;
+    private contextManager;
+    private agentManager;
+    private hookLoader;
     private steeringPath;
     /**
      * Create CLI instance
@@ -29,13 +55,10 @@ export declare class InstallSkillsCLI {
      */
     constructor(skillsPath?: string, steeringPath?: string);
     /**
-     * Get the default skills path based on package location
-     */
-    private getDefaultSkillsPath;
-    /**
-     * Get the default steering path based on package location
+     * Get the default path for a component type based on package location
+     * @param componentDir - The component directory name (skills, steering, rules, etc.)
      */
-    private getDefaultSteeringPath;
+    private getDefaultPath;
     /**
      * Parse command line arguments
      * @param args - Command line arguments (process.argv.slice(2))
@@ -48,7 +71,7 @@ export declare class InstallSkillsCLI {
      */
     run(options: CLIOptions): Promise<void>;
     /**
-     * Run unified install (skills + steering)
+     * Run unified install (all components)
      * @param options - CLI options
      */
     runUnified(options: CLIOptions): Promise<void>;
@@ -61,7 +84,7 @@ export declare class InstallSkillsCLI {
      */
     private listSteering;
     /**
-     * List all available skills and steering documents
+     * List all available components
      */
     private listAll;
     /**
@@ -74,6 +97,26 @@ export declare class InstallSkillsCLI {
      * @param targetPath - Target directory (e.g., .spec/steering)
      */
     private installSteering;
+    /**
+     * Install rules to target directory
+     * @param targetPath - Target directory (e.g., .claude/rules)
+     */
+    private installRules;
+    /**
+     * Install contexts to target directory
+     * @param targetPath - Target directory (e.g., .claude/contexts)
+     */
+    private installContexts;
+    /**
+     * Install agents to target directory
+     * @param targetPath - Target directory (e.g., .claude/agents)
+     */
+    private installAgents;
+    /**
+     * Install hooks to target directory
+     * @param targetPath - Target directory (e.g., .claude/hooks)
+     */
+    private installHooks;
     /**
      * Get help text
      * @returns Help message