musubi-sdd 5.0.0 → 5.6.1

package/src/templates/agents/claude-code/skills/orchestrator/SKILL.md

@@ -96,32 +96,32 @@ The Orchestrator can leverage all MUSUBI CLI commands to execute tasks efficient
 
 ### Advanced Commands (v3.5.0 NEW)
 
-| Command             | Purpose                           | Example                                    |
-| ------------------- | --------------------------------- | ------------------------------------------ |
-| `musubi-orchestrate`| Multi-skill workflow orchestration| `musubi-orchestrate auto <task>`           |
-| `musubi-browser`    | Browser automation & E2E testing  | `musubi-browser run "click login button"`  |
-| `musubi-gui`        | Web GUI dashboard                 | `musubi-gui start`                         |
-| `musubi-remember`   | Agent memory management           | `musubi-remember extract`                  |
-| `musubi-resolve`    | GitHub Issue auto-resolution      | `musubi-resolve <issue-number>`            |
-| `musubi-convert`    | Format conversion (Spec Kit)      | `musubi-convert to-speckit`                |
+| Command              | Purpose                            | Example                                   |
+| -------------------- | ---------------------------------- | ----------------------------------------- |
+| `musubi-orchestrate` | Multi-skill workflow orchestration | `musubi-orchestrate auto <task>`          |
+| `musubi-browser`     | Browser automation & E2E testing   | `musubi-browser run "click login button"` |
+| `musubi-gui`         | Web GUI dashboard                  | `musubi-gui start`                        |
+| `musubi-remember`    | Agent memory management            | `musubi-remember extract`                 |
+| `musubi-resolve`     | GitHub Issue auto-resolution       | `musubi-resolve <issue-number>`           |
+| `musubi-convert`     | Format conversion (Spec Kit)       | `musubi-convert to-speckit`               |
 
 ### Replanning Commands (v3.6.0 NEW)
 
-| Command                        | Purpose                      | Example                                           |
-| ------------------------------ | ---------------------------- | ------------------------------------------------- |
-| `musubi-orchestrate replan`    | Execute dynamic replanning   | `musubi-orchestrate replan <context-id>`          |
-| `musubi-orchestrate goal`      | Goal management              | `musubi-orchestrate goal register --name "Deploy"`|
-| `musubi-orchestrate optimize`  | Path optimization            | `musubi-orchestrate optimize run <path-id>`       |
-| `musubi-orchestrate path`      | Path analysis                | `musubi-orchestrate path analyze <path-id>`       |
+| Command                       | Purpose                    | Example                                            |
+| ----------------------------- | -------------------------- | -------------------------------------------------- |
+| `musubi-orchestrate replan`   | Execute dynamic replanning | `musubi-orchestrate replan <context-id>`           |
+| `musubi-orchestrate goal`     | Goal management            | `musubi-orchestrate goal register --name "Deploy"` |
+| `musubi-orchestrate optimize` | Path optimization          | `musubi-orchestrate optimize run <path-id>`        |
+| `musubi-orchestrate path`     | Path analysis              | `musubi-orchestrate path analyze <path-id>`        |
 
 ### Guardrails Commands (v3.9.0 NEW)
 
-| Command                                    | Purpose                        | Example                                               |
-| ------------------------------------------ | ------------------------------ | ----------------------------------------------------- |
-| `musubi-validate guardrails`               | Input/Output validation        | `musubi-validate guardrails --type input`             |
-| `musubi-validate guardrails --type output` | Output content validation      | `echo "content" \| musubi-validate guardrails --type output` |
-| `musubi-validate guardrails --type safety` | Safety check with constitutional| `musubi-validate guardrails --type safety --constitutional` |
-| `musubi-validate guardrails-chain`         | Chain multiple guardrails      | `musubi-validate guardrails-chain --parallel`         |
+| Command                                    | Purpose                          | Example                                                      |
+| ------------------------------------------ | -------------------------------- | ------------------------------------------------------------ |
+| `musubi-validate guardrails`               | Input/Output validation          | `musubi-validate guardrails --type input`                    |
+| `musubi-validate guardrails --type output` | Output content validation        | `echo "content" \| musubi-validate guardrails --type output` |
+| `musubi-validate guardrails --type safety` | Safety check with constitutional | `musubi-validate guardrails --type safety --constitutional`  |
+| `musubi-validate guardrails-chain`         | Chain multiple guardrails        | `musubi-validate guardrails-chain --parallel`                |
 
 ### Detailed Command Options
 
@@ -265,20 +265,21 @@ Orchestrator can leverage advanced AI agent modules inspired by OpenHands:
 
 ### Available Modules
 
-| Module | Purpose | Use Case |
-|--------|---------|----------|
-| **StuckDetector** | Detect agent stuck states | When agent loops or doesn't progress |
-| **MemoryCondenser** | Compress session history | Long sessions exceeding context |
-| **AgentMemoryManager** | Extract & persist learnings | Session knowledge capture |
-| **CriticSystem** | Evaluate SDD stage quality | Quality gates before transitions |
-| **SecurityAnalyzer** | Detect security risks | Pre-commit/deployment checks |
-| **IssueResolver** | GitHub Issue analysis | Issue → SDD workflow |
-| **SkillLoader** | Load keyword-triggered skills | Dynamic skill activation |
-| **RepoSkillManager** | Manage .musubi/skills/ | Project-specific skills |
+| Module                 | Purpose                       | Use Case                             |
+| ---------------------- | ----------------------------- | ------------------------------------ |
+| **StuckDetector**      | Detect agent stuck states     | When agent loops or doesn't progress |
+| **MemoryCondenser**    | Compress session history      | Long sessions exceeding context      |
+| **AgentMemoryManager** | Extract & persist learnings   | Session knowledge capture            |
+| **CriticSystem**       | Evaluate SDD stage quality    | Quality gates before transitions     |
+| **SecurityAnalyzer**   | Detect security risks         | Pre-commit/deployment checks         |
+| **IssueResolver**      | GitHub Issue analysis         | Issue → SDD workflow                 |
+| **SkillLoader**        | Load keyword-triggered skills | Dynamic skill activation             |
+| **RepoSkillManager**   | Manage .musubi/skills/        | Project-specific skills              |
 
 ### Module Integration Examples
 
 #### Stuck Detection
+
 ```javascript
 const { StuckDetector } = require('musubi/src/analyzers/stuck-detector');
 const detector = new StuckDetector();
@@ -291,6 +292,7 @@ if (analysis) {
 ```
 
 #### Quality Evaluation
+
 ```javascript
 const { CriticSystem } = require('musubi/src/validators/critic-system');
 const critic = new CriticSystem();
@@ -301,6 +303,7 @@ if (result.success) {
 ```
 
 #### Security Pre-check
+
 ```javascript
 const { SecurityAnalyzer } = require('musubi/src/analyzers/security-analyzer');
 const analyzer = new SecurityAnalyzer({ strictMode: true });
@@ -504,15 +507,97 @@ codegraph-mcp community "/path/to/project"
 
 ---
 
+## MUSUBI CodeGraphMCP Module (v5.5.0+)
+
+**Available Module**: `src/integrations/codegraph-mcp.js`
+
+The CodeGraphMCP module provides programmatic integration with CodeGraph MCP server.
+
+### Module Usage
+
+```javascript
+const { CodeGraphMCP } = require('musubi-sdd');
+
+const codegraph = new CodeGraphMCP({
+  mcpEndpoint: 'http://localhost:3000',
+  repoPath: '/path/to/project',
+});
+
+// Generate call graph
+const callGraph = await codegraph.generateCallGraph('src/main.c', { depth: 3 });
+
+// Analyze impact of changes
+const impact = await codegraph.analyzeImpact('src/utils.c');
+
+// Detect circular dependencies
+const cycles = await codegraph.detectCircularDependencies('src/');
+
+// Identify hotspots (highly-connected entities)
+const hotspots = await codegraph.identifyHotspots(5);
+
+// Detect code communities
+const communities = await codegraph.detectCommunities();
+```
+
+### Features
+
+| Feature                   | Description                                               |
+| ------------------------- | --------------------------------------------------------- |
+| **Call Graph**            | Track callers and callees with configurable depth         |
+| **Impact Analysis**       | Identify affected files when code changes                 |
+| **Circular Dependencies** | Find cycles in module dependencies                        |
+| **Hotspots**              | Detect highly-connected entities (refactoring candidates) |
+| **Community Detection**   | Group related code modules                                |
+
+---
+
+## MUSUBI HierarchicalReporter Module (v5.5.0+)
+
+**Available Module**: `src/reporters/hierarchical-reporter.js`
+
+The HierarchicalReporter module generates hierarchical analysis reports for large projects.
+
+### Module Usage
+
+```javascript
+const { HierarchicalReporter } = require('musubi-sdd');
+
+const reporter = new HierarchicalReporter();
+const report = await reporter.generateReport('/path/to/project', {
+  format: 'markdown', // markdown, json, html
+  includeHotspots: true,
+  maxDepth: 5,
+});
+
+console.log(report.content);
+```
+
+### Output Formats
+
+- **Markdown**: Human-readable hierarchical report
+- **JSON**: Structured data for further processing
+- **HTML**: Interactive report with navigation
+
+### Hotspot Analysis
+
+The reporter identifies:
+
+- Files with highest complexity
+- Most frequently changed files
+- Largest files by line count
+- Files with most dependencies
+
+---
+
 ## Managed Agents Overview (25 Types)
 
 ### Orchestration & Governance (3 agents)
 
-| Agent                     | Specialty                 | Key Deliverables                        | CLI Command           |
-| ------------------------- | ------------------------- | --------------------------------------- | --------------------- |
-| **Orchestrator**          | Multi-agent coordination  | Execution plans, integrated reports     | `musubi-orchestrate`  |
-| **Steering**              | Project memory management | Steering files (structure/tech/product) | `musubi-remember`     |
-| **Constitution Enforcer** | Constitutional validation | Compliance reports, violation alerts    | `musubi-validate`     |
+| Agent                     | Specialty                 | Key Deliverables                        | CLI Command          |
+| ------------------------- | ------------------------- | --------------------------------------- | -------------------- |
+| **Orchestrator**          | Multi-agent coordination  | Execution plans, integrated reports     | `musubi-orchestrate` |
+| **Steering**              | Project memory management | Steering files (structure/tech/product) | `musubi-remember`    |
+| **Constitution Enforcer** | Constitutional validation | Compliance reports, violation alerts    | `musubi-validate`    |
 
 ### Design & Architecture (5 agents)
 
@@ -526,25 +611,25 @@ codegraph-mcp community "/path/to/project"
 
 ### Development & Quality (7 agents)
 
-| Agent                     | Specialty                    | Key Deliverables                                              | CLI Command        |
-| ------------------------- | ---------------------------- | ------------------------------------------------------------- | ------------------ |
-| **Software Developer**    | Code implementation          | Production-ready source code, unit tests, integration tests   | -                  |
-| **Code Reviewer**         | Code review                  | Review reports, improvement suggestions, refactoring plans    | -                  |
-| **Test Engineer**         | Test design & implementation | Test code, test design documents, test cases                  | `musubi-tasks`     |
-| **Security Auditor**      | Security auditing            | Vulnerability reports, remediation plans, security guidelines | -                  |
-| **Quality Assurance**     | Quality assurance strategy   | Test plans, quality metrics, QA reports                       | `musubi-validate`  |
-| **Bug Hunter**            | Bug investigation & fixes    | Bug reports, root cause analysis, fix code                    | `musubi-resolve`   |
-| **Performance Optimizer** | Performance optimization     | Performance reports, optimization code, benchmarks            | -                  |
+| Agent                     | Specialty                    | Key Deliverables                                              | CLI Command       |
+| ------------------------- | ---------------------------- | ------------------------------------------------------------- | ----------------- |
+| **Software Developer**    | Code implementation          | Production-ready source code, unit tests, integration tests   | -                 |
+| **Code Reviewer**         | Code review                  | Review reports, improvement suggestions, refactoring plans    | -                 |
+| **Test Engineer**         | Test design & implementation | Test code, test design documents, test cases                  | `musubi-tasks`    |
+| **Security Auditor**      | Security auditing            | Vulnerability reports, remediation plans, security guidelines | -                 |
+| **Quality Assurance**     | Quality assurance strategy   | Test plans, quality metrics, QA reports                       | `musubi-validate` |
+| **Bug Hunter**            | Bug investigation & fixes    | Bug reports, root cause analysis, fix code                    | `musubi-resolve`  |
+| **Performance Optimizer** | Performance optimization     | Performance reports, optimization code, benchmarks            | -                 |
 
 ### Operations & Infrastructure (5 agents)
 
-| Agent                         | Specialty                         | Key Deliverables                                     | CLI Command      |
-| ----------------------------- | --------------------------------- | ---------------------------------------------------- | ---------------- |
-| **Project Manager**           | Project management                | Project plans, WBS, Gantt charts, risk registers     | `musubi-tasks`   |
-| **DevOps Engineer**           | CI/CD & infrastructure automation | Pipeline definitions, Dockerfiles, K8s manifests     | -                |
-| **Technical Writer**          | Technical documentation           | API docs, README, user guides, runbooks              | -                |
-| **Site Reliability Engineer** | SRE & observability               | SLI/SLO/SLA definitions, monitoring configs          | `musubi-gui`     |
-| **Release Coordinator**       | Release management                | Release notes, deployment plans, rollback procedures | -                |
+| Agent                         | Specialty                         | Key Deliverables                                     | CLI Command    |
+| ----------------------------- | --------------------------------- | ---------------------------------------------------- | -------------- |
+| **Project Manager**           | Project management                | Project plans, WBS, Gantt charts, risk registers     | `musubi-tasks` |
+| **DevOps Engineer**           | CI/CD & infrastructure automation | Pipeline definitions, Dockerfiles, K8s manifests     | -              |
+| **Technical Writer**          | Technical documentation           | API docs, README, user guides, runbooks              | -              |
+| **Site Reliability Engineer** | SRE & observability               | SLI/SLO/SLA definitions, monitoring configs          | `musubi-gui`   |
+| **Release Coordinator**       | Release management                | Release notes, deployment plans, rollback procedures | -              |
 
 ### Specialized Experts (5 agents)
 
@@ -638,18 +723,18 @@ musubi-workflow next implementation
 
 ### 10ステージ ワークフロー
 
-| Stage | Name | Description | CLI Command |
-|-------|------|-------------|-------------|
-| 0 | Spike/PoC | 調査・プロトタイピング | `musubi-workflow next spike` |
-| 1 | Requirements | 要件定義 | `musubi-requirements` |
-| 2 | Design | 設計（C4 + ADR） | `musubi-design` |
-| 3 | Tasks | タスク分解 | `musubi-tasks` |
-| 4 | Implementation | 実装 | - |
-| 5 | Review | コードレビュー | `musubi-workflow next review` |
-| 6 | Testing | テスト | `musubi-validate` |
-| 7 | Deployment | デプロイ | - |
-| 8 | Monitoring | モニタリング | - |
-| 9 | Retrospective | 振り返り | `musubi-workflow complete` |
+| Stage | Name           | Description            | CLI Command                   |
+| ----- | -------------- | ---------------------- | ----------------------------- |
+| 0     | Spike/PoC      | 調査・プロトタイピング | `musubi-workflow next spike`  |
+| 1     | Requirements   | 要件定義               | `musubi-requirements`         |
+| 2     | Design         | 設計（C4 + ADR）       | `musubi-design`               |
+| 3     | Tasks          | タスク分解             | `musubi-tasks`                |
+| 4     | Implementation | 実装                   | -                             |
+| 5     | Review         | コードレビュー         | `musubi-workflow next review` |
+| 6     | Testing        | テスト                 | `musubi-validate`             |
+| 7     | Deployment     | デプロイ               | -                             |
+| 8     | Monitoring     | モニタリング           | -                             |
+| 9     | Retrospective  | 振り返り               | `musubi-workflow complete`    |
 
 ### フィードバックループ
 

package/src/templates/agents/claude-code/skills/orchestrator/patterns.md

@@ -23,11 +23,13 @@ Consolidate Results
 ```
 
 **Use When**:
+
 - User request is complex or ambiguous
 - Multiple agents might be needed
 - Optimal agent selection is unclear
 
 **Example**:
+
 ```
 User: "Create a new authentication feature"
 
@@ -51,6 +53,7 @@ Agent A → Agent B → Agent C → Result
 ```
 
 **Use When**:
+
 - Clear dependency chain exists
 - Output of one agent is input for next
 - Order is non-negotiable
@@ -58,6 +61,7 @@ Agent A → Agent B → Agent C → Result
 **Common Chains**:
 
 ### SDD Full Workflow Chain
+
 ```
 1. steering          → Analyze project context
 2. requirements-analyst → Create EARS requirements
@@ -70,6 +74,7 @@ Agent A → Agent B → Agent C → Result
 ```
 
 ### Quick Implementation Chain
+
 ```
 1. requirements-analyst → EARS requirements
 2. software-developer   → Implementation
@@ -92,11 +97,13 @@ Orchestrator
 ```
 
 **Use When**:
+
 - Complex task requires sub-delegation
 - Specialized sub-agents needed for specific aspects
 - Hierarchical coordination is natural
 
 **Example**:
+
 ```
 User: "Design the entire backend architecture"
 
@@ -120,11 +127,13 @@ Orchestrator
 ```
 
 **Use When**:
+
 - Multiple perspectives needed
 - Collaborative refinement required
 - Cross-domain expertise needed
 
 **Example**:
+
 ```
 User: "Review and improve the authentication design"
 
@@ -153,11 +162,13 @@ Request ────┼── Agent B ──┼── Consolidate → Result
 ```
 
 **Use When**:
+
 - Subtasks are independent
 - Time efficiency is critical
 - No dependencies between agents
 
 **Example**:
+
 ```
 User: "Audit the codebase for security, performance, and code quality"
 
@@ -180,6 +191,7 @@ Agent Work → Validation Gate → Human Review → Continue/Reject
 ```
 
 **Use When**:
+
 - Critical decisions require human approval
 - Constitutional gates require validation
 - High-risk changes need oversight
@@ -187,6 +199,7 @@ Agent Work → Validation Gate → Human Review → Continue/Reject
 **Validation Gates**:
 
 ### Phase -1 Gates (Constitution Enforcer)
+
 ```
 Before Implementation:
 □ Library-First validated
@@ -197,6 +210,7 @@ Before Implementation:
 ```
 
 ### Design Review Gate
+
 ```
 After Architecture Design:
 □ C4 diagrams reviewed
@@ -206,6 +220,7 @@ After Architecture Design:
 ```
 
 ### Release Gate
+
 ```
 Before Production Release:
 □ All tests passing
@@ -218,16 +233,16 @@ Before Production Release:
 
 ## Pattern Selection Matrix
 
-| Scenario | Recommended Pattern | Reason |
-|----------|-------------------|--------|
-| New feature development | Sequential | Clear workflow stages |
-| Codebase audit | Swarm | Independent analysis |
-| Architecture design | Nested | Hierarchical delegation |
-| Design review | Group Chat | Multi-perspective feedback |
-| Production release | Human-in-Loop | Critical validation |
-| Unclear request | Auto | Let orchestrator decide |
-| Long-running workflows | Replanning | Handle failures gracefully |
-| Resilient execution | Replanning | Automatic recovery |
+| Scenario                | Recommended Pattern | Reason                     |
+| ----------------------- | ------------------- | -------------------------- |
+| New feature development | Sequential          | Clear workflow stages      |
+| Codebase audit          | Swarm               | Independent analysis       |
+| Architecture design     | Nested              | Hierarchical delegation    |
+| Design review           | Group Chat          | Multi-perspective feedback |
+| Production release      | Human-in-Loop       | Critical validation        |
+| Unclear request         | Auto                | Let orchestrator decide    |
+| Long-running workflows  | Replanning          | Handle failures gracefully |
+| Resilient execution     | Replanning          | Automatic recovery         |
 
 ---
 
@@ -288,6 +303,7 @@ Execute Alternative
 ```
 
 **Use When**:
+
 - Tasks may fail or timeout
 - Alternative approaches exist
 - Resilience is critical
@@ -295,14 +311,15 @@ Execute Alternative
 
 **Components**:
 
-| Component | Purpose | CLI Command |
-|-----------|---------|-------------|
-| ReplanningEngine | Core replanning logic | `musubi-orchestrate replan <context-id>` |
-| GoalProgressTracker | Track goal completion | `musubi-orchestrate goal status` |
+| Component              | Purpose                  | CLI Command                                 |
+| ---------------------- | ------------------------ | ------------------------------------------- |
+| ReplanningEngine       | Core replanning logic    | `musubi-orchestrate replan <context-id>`    |
+| GoalProgressTracker    | Track goal completion    | `musubi-orchestrate goal status`            |
 | ProactivePathOptimizer | Optimize execution paths | `musubi-orchestrate optimize run <path-id>` |
-| AdaptiveGoalModifier | Adjust goals dynamically | `musubi-orchestrate goal update <goal-id>` |
+| AdaptiveGoalModifier   | Adjust goals dynamically | `musubi-orchestrate goal update <goal-id>`  |
 
 **Example**:
+
 ```
 User: "Deploy API to production"
 
@@ -324,6 +341,7 @@ Continue:
 ```
 
 **Trigger Types**:
+
 - `failure` - Task execution failed
 - `timeout` - Task exceeded time limit
 - `quality` - Output quality below threshold
@@ -331,6 +349,7 @@ Continue:
 - `dependency` - Dependency unavailable
 
 **Decision Types**:
+
 - `continue` - Proceed with next task
 - `retry` - Retry the failed task
 - `alternative` - Use alternative approach
@@ -338,6 +357,7 @@ Continue:
 - `human` - Escalate to human decision
 
 **CLI Usage**:
+
 ```bash
 # Execute replanning for a context
 musubi-orchestrate replan ctx-12345
@@ -352,4 +372,3 @@ musubi-orchestrate path analyze path-1
 musubi-orchestrate optimize suggest path-1
 musubi-orchestrate optimize run path-1
 ```
-