omgkit 2.24.0 → 2.24.2

package/README.md

@@ -37,9 +37,9 @@ All coordinated through **Omega-level thinking** - a framework for finding break
 | Component | Count | Description |
 |-----------|-------|-------------|
 | **Agents** | 41 | Specialized AI team members with distinct roles |
-| **Commands** | 151 | Slash commands for every development task |
-| **Workflows** | 67 | Complete development processes from idea to deploy |
-| **Skills** | 157 | Domain expertise modules across 24 categories |
+| **Commands** | 160 | Slash commands for every development task |
+| **Workflows** | 69 | Complete development processes from idea to deploy |
+| **Skills** | 161 | Domain expertise modules across 24 categories |
 | **Modes** | 10 | Behavioral configurations for different contexts |
 | **Archetypes** | 14 | Project templates for autonomous development |
 
@@ -88,6 +88,53 @@ OMGKIT brings agile methodology to AI-assisted development:
 - **Sprints**: Time-boxed development cycles
 - **AI Team**: Autonomous execution with human oversight
 
+### 4. Testing Automation (New)
+
+OMGKIT includes a comprehensive testing automation system:
+
+#### Auto-Generate Test Tasks
+When you create a feature, OMGKIT automatically generates corresponding test tasks:
+
+```yaml
+# workflow.yaml
+testing:
+  auto_generate_tasks: true
+  required_test_types:
+    - unit
+    - integration
+```
+
+Feature tasks automatically spawn test tasks based on feature type (API → Contract tests, UI → Snapshot tests, etc.)
+
+#### Enforce Tests Before Done
+No task can be marked "done" without passing tests:
+
+```yaml
+testing:
+  enforcement:
+    level: standard  # soft | standard | strict
+  blocking:
+    on_test_failure: true
+    on_coverage_below_minimum: true
+```
+
+#### Coverage Gates
+Set minimum and target coverage thresholds:
+
+```yaml
+testing:
+  coverage_gates:
+    unit:
+      minimum: 80
+      target: 90
+    integration:
+      minimum: 60
+      target: 75
+    overall:
+      minimum: 75
+      target: 85
+```
+
 ---
 
 ## Installation
@@ -222,7 +269,7 @@ Agents are specialized AI team members, each with distinct expertise and respons
 
 ---
 
-## Commands (151)
+## Commands (160)
 
 Commands are slash-prefixed actions organized by namespace.
 
@@ -260,10 +307,13 @@ Commands are slash-prefixed actions organized by namespace.
 ### Quality (`/quality:*`)
 
 ```bash
-/quality:security-scan  # Scan for vulnerabilities
+/quality:security-scan   # Scan for vulnerabilities
 /quality:refactor <file> # Improve code structure
 /quality:optimize <file> # Performance optimization
-/quality:lint           # Run linting
+/quality:lint            # Run linting
+/quality:verify-done     # Verify test requirements before completion
+/quality:coverage-check  # Check coverage against gates
+/quality:test-plan       # Generate comprehensive test plan
 ```
 
 ### Omega (`/omega:*`)
@@ -370,7 +420,7 @@ Commands are slash-prefixed actions organized by namespace.
 
 ---
 
-## Workflows (67)
+## Workflows (69)
 
 Workflows are orchestrated sequences of agents, commands, and skills.
 
@@ -383,6 +433,12 @@ Workflows are orchestrated sequences of agents, commands, and skills.
 | `development/refactor` | Code improvement and restructuring |
 | `development/code-review` | Comprehensive code review |
 
+### Testing Automation (New)
+
+| Workflow | Description |
+|----------|-------------|
+| `testing/automated-testing` | End-to-end testing automation with task generation, enforcement, and coverage gates |
+
 ### AI Engineering
 
 | Workflow | Description |
@@ -454,7 +510,7 @@ Workflows are orchestrated sequences of agents, commands, and skills.
 
 ---
 
-## Skills (157)
+## Skills (161)
 
 Skills are domain expertise modules organized in 24 categories.
 
@@ -498,7 +554,7 @@ Based on Chip Huyen's "Designing ML Systems" and Stanford CS 329S:
 | `ml-systems/robust-ai` | Reliability, monitoring, drift detection |
 | `ml-systems/deployment-paradigms` | Batch vs real-time vs streaming |
 
-### Methodology (17 skills)
+### Methodology (19 skills)
 
 | Skill | Description |
 |-------|-------------|
@@ -507,6 +563,8 @@ Based on Chip Huyen's "Designing ML Systems" and Stanford CS 329S:
 | `methodology/debugging` | Systematic debugging approach |
 | `methodology/code-review` | Review standards and checklists |
 | `methodology/tdd` | Test-driven development |
+| `methodology/test-task-generation` | Auto-generate test tasks from features |
+| `methodology/test-enforcement` | Enforce tests before task completion |
 
 ### Frameworks (10 skills)
 
@@ -735,7 +793,7 @@ If any sync issue is detected (missing pages, wrong counts, broken links), the v
 
 ## Validation & Testing
 
-OMGKIT has 5700+ automated tests ensuring system integrity.
+OMGKIT has 7300+ automated tests ensuring system integrity.
 
 ### Run Tests
 

package/bin/omgkit.js

@@ -56,12 +56,13 @@ ${COLORS.bright}EXAMPLES${COLORS.reset}
 ${COLORS.bright}AFTER INSTALLATION${COLORS.reset}
   In Claude Code, type / to see all OMGKIT commands:
 
-  Core: /feature, /fix, /plan, /test, /review
-  Omega: /10x, /100x, /1000x, /principles
-  Sprint: /vision:set, /sprint:new, /team:run
+  Core: /dev:feature, /dev:fix, /planning:plan, /quality:test, /dev:review
+  Omega: /omega:10x, /omega:100x, /omega:1000x, /omega:principles
+  Sprint: /sprint:vision-set, /sprint:sprint-new, /sprint:team-run
+  Workflow: /workflow:init, /workflow:status, /hooks:setup
 
 ${COLORS.bright}DOCUMENTATION${COLORS.reset}
-  https://github.com/user/omgkit
+  https://omg.mintlify.app
 `);
 }
 

package/lib/cli.js

@@ -51,7 +51,7 @@ ${COLORS.magenta}╔════════════════════
 ║                                                              ║
 ║   🔮 OMGKIT - Omega-Level Development Kit                   ║
 ║                                                              ║
-║   23 Agents • 58 Commands • 88 Skills • 10 Modes            ║
+║   41 Agents • 156 Commands • 159 Skills • 10 Modes          ║
 ║   "Think Omega. Build Omega. Be Omega."                     ║
 ║                                                              ║
 ╚════════════════════════════════════════════════════════════╝${COLORS.reset}
@@ -499,7 +499,15 @@ export function doctor(options = {}) {
 
   // Count commands
   if (existsSync(commandsDir)) {
-    const commandPrefixes = ['dev:', 'git:', 'planning:', 'quality:', 'context:', 'design:', 'omega:', 'sprint:', 'mode:'];
+    const commandPrefixes = [
+      // All command namespaces
+      'alignment:', 'auto:', 'context:', 'data:', 'design:', 'dev:', 'domain:',
+      'game:', 'git:', 'hooks:', 'iot:', 'ml:', 'omega:', 'omgdata:', 'omgdeploy:',
+      'omgfeature:', 'omgml:', 'omgops:', 'omgoptim:', 'omgtrain:', 'perf:',
+      'planning:', 'platform:', 'quality:', 'security:', 'sprint:', 'sre:', 'workflow:',
+      // Modes
+      'mode:'
+    ];
     const files = readdirSync(commandsDir).filter(f =>
       f.endsWith('.md') && commandPrefixes.some(p => f.startsWith(p))
     );
@@ -517,7 +525,14 @@ export function doctor(options = {}) {
 
   // Count skills
   if (existsSync(skillsDir)) {
-    const skillPrefixes = ['databases-', 'devops-', 'tools-', 'languages-', 'frameworks-', 'frontend-', 'backend-', 'mobile-', 'integrations-', 'security-', 'testing-', 'methodology-', 'ai-engineering-', 'omega-'];
+    const skillPrefixes = [
+      // All skill categories
+      'ai-engineering-', 'ai-ml-', 'autonomous-', 'backend-', 'databases-',
+      'devops-', 'event-driven-', 'frameworks-', 'frontend-', 'game-',
+      'integrations-', 'iot-', 'languages-', 'methodology-', 'microservices-',
+      'ml-systems-', 'mobile-', 'mobile-advanced-', 'omega-', 'security-',
+      'simulation-', 'testing-', 'tools-'
+    ];
     const dirs = readdirSync(skillsDir).filter(f => {
       const fullPath = join(skillsDir, f);
       return statSync(fullPath).isDirectory() && skillPrefixes.some(p => f.startsWith(p));
@@ -537,13 +552,19 @@ export function doctor(options = {}) {
   // Count agents
   if (existsSync(agentsDir)) {
     const agentFiles = [
-      'code-reviewer.md', 'architect.md', 'debugger.md', 'api-designer.md',
-      'database-admin.md', 'cicd-manager.md', 'oracle.md', 'researcher.md',
-      'project-manager.md', 'copywriter.md', 'vulnerability-scanner.md',
-      'security-auditor.md', 'journal-writer.md', 'sprint-master.md',
-      'tester.md', 'fullstack-developer.md', 'planner.md', 'docs-manager.md',
-      'git-manager.md', 'ui-ux-designer.md', 'scout.md', 'brainstormer.md',
-      'pipeline-architect.md'
+      // All 41 agents
+      'ai-architect-agent.md', 'api-designer.md', 'architect.md', 'brainstormer.md',
+      'cicd-manager.md', 'code-reviewer.md', 'copywriter.md', 'data-engineer.md',
+      'data-scientist-agent.md', 'database-admin.md', 'debugger.md', 'devsecops.md',
+      'docs-manager.md', 'domain-decomposer.md', 'embedded-systems.md',
+      'experiment-analyst-agent.md', 'fullstack-developer.md', 'game-systems-designer.md',
+      'git-manager.md', 'journal-writer.md', 'ml-engineer-agent.md', 'ml-engineer.md',
+      'mlops-engineer-agent.md', 'model-optimizer-agent.md', 'observability-engineer.md',
+      'oracle.md', 'performance-engineer.md', 'pipeline-architect.md', 'planner.md',
+      'platform-engineer.md', 'production-engineer-agent.md', 'project-manager.md',
+      'research-scientist-agent.md', 'researcher.md', 'scientific-computing.md',
+      'scout.md', 'security-auditor.md', 'sprint-master.md', 'tester.md',
+      'ui-ux-designer.md', 'vulnerability-scanner.md'
     ];
     const installed = agentFiles.filter(f => existsSync(join(agentsDir, f)));
     result.claudeCode.agents = installed.length;
@@ -663,31 +684,40 @@ export function uninstallPlugin(options = {}) {
     agents: 0
   };
 
-  // Command prefixes from our categories (both old hyphen and new colon separator)
+  // Command prefixes from our categories
   const commandPrefixes = [
-    'dev:', 'git:', 'planning:', 'quality:', 'context:',
-    'design:', 'omega:', 'sprint:', 'mode:',
-    // Also clean up old hyphen-separated format
-    'dev-', 'git-', 'planning-', 'quality-', 'context-',
-    'design-', 'omega-', 'sprint-', 'mode-'
+    // All command namespaces
+    'alignment:', 'auto:', 'context:', 'data:', 'design:', 'dev:', 'domain:',
+    'game:', 'git:', 'hooks:', 'iot:', 'ml:', 'omega:', 'omgdata:', 'omgdeploy:',
+    'omgfeature:', 'omgml:', 'omgops:', 'omgoptim:', 'omgtrain:', 'perf:',
+    'planning:', 'platform:', 'quality:', 'security:', 'sprint:', 'sre:', 'workflow:',
+    // Modes
+    'mode:'
   ];
 
   // Skill prefixes from our categories
   const skillPrefixes = [
-    'databases-', 'devops-', 'tools-', 'languages-', 'frameworks-',
-    'frontend-', 'backend-', 'mobile-', 'integrations-', 'security-',
-    'testing-', 'methodology-', 'ai-engineering-', 'omega-'
+    'ai-engineering-', 'ai-ml-', 'autonomous-', 'backend-', 'databases-',
+    'devops-', 'event-driven-', 'frameworks-', 'frontend-', 'game-',
+    'integrations-', 'iot-', 'languages-', 'methodology-', 'microservices-',
+    'ml-systems-', 'mobile-', 'mobile-advanced-', 'omega-', 'security-',
+    'simulation-', 'testing-', 'tools-'
   ];
 
-  // Agent files we installed
+  // Agent files we installed (all 41 agents)
   const agentFiles = [
-    'code-reviewer.md', 'architect.md', 'debugger.md', 'api-designer.md',
-    'database-admin.md', 'cicd-manager.md', 'oracle.md', 'researcher.md',
-    'project-manager.md', 'copywriter.md', 'vulnerability-scanner.md',
-    'security-auditor.md', 'journal-writer.md', 'sprint-master.md',
-    'tester.md', 'fullstack-developer.md', 'planner.md', 'docs-manager.md',
-    'git-manager.md', 'ui-ux-designer.md', 'scout.md', 'brainstormer.md',
-    'pipeline-architect.md'
+    'ai-architect-agent.md', 'api-designer.md', 'architect.md', 'brainstormer.md',
+    'cicd-manager.md', 'code-reviewer.md', 'copywriter.md', 'data-engineer.md',
+    'data-scientist-agent.md', 'database-admin.md', 'debugger.md', 'devsecops.md',
+    'docs-manager.md', 'domain-decomposer.md', 'embedded-systems.md',
+    'experiment-analyst-agent.md', 'fullstack-developer.md', 'game-systems-designer.md',
+    'git-manager.md', 'journal-writer.md', 'ml-engineer-agent.md', 'ml-engineer.md',
+    'mlops-engineer-agent.md', 'model-optimizer-agent.md', 'observability-engineer.md',
+    'oracle.md', 'performance-engineer.md', 'pipeline-architect.md', 'planner.md',
+    'platform-engineer.md', 'production-engineer-agent.md', 'project-manager.md',
+    'research-scientist-agent.md', 'researcher.md', 'scientific-computing.md',
+    'scout.md', 'security-auditor.md', 'sprint-master.md', 'tester.md',
+    'ui-ux-designer.md', 'vulnerability-scanner.md'
   ];
 
   // Remove backup location
@@ -805,10 +835,10 @@ export function listComponents(type, options = {}) {
   }
 
   const componentTypes = {
-    commands: { title: 'Commands', count: 54 },
-    agents: { title: 'Agents', count: 23 },
-    skills: { title: 'Skills', count: 43 },
-    modes: { title: 'Modes', count: 9 }
+    commands: { title: 'Commands' },
+    agents: { title: 'Agents' },
+    skills: { title: 'Skills' },
+    modes: { title: 'Modes' }
   };
 
   const result = { success: true, components: {} };
@@ -818,7 +848,7 @@ export function listComponents(type, options = {}) {
   typesToList.forEach(key => {
     if (!componentTypes[key]) return;
 
-    const { title, count } = componentTypes[key];
+    const { title } = componentTypes[key];
     const dir = join(pluginDir, key);
 
     if (existsSync(dir)) {

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "omgkit",
-  "version": "2.24.0",
-  "description": "Omega-Level Development Kit - AI Team System for Claude Code. 41 agents, 156 commands, 157 skills, 68 workflows.",
+  "version": "2.24.2",
+  "description": "Omega-Level Development Kit - AI Team System for Claude Code. 41 agents, 160 commands, 161 skills, 69 workflows.",
   "keywords": [
     "claude-code",
     "ai",

package/plugin/commands/dev/feature-tested.md

@@ -0,0 +1,208 @@
+---
+name: Feature Tested
+description: Create a feature with automatically generated test tasks. Ensures every implementation task has corresponding test coverage before the feature can be marked complete.
+category: dev
+related_skills:
+  - methodology/test-task-generation
+  - methodology/test-enforcement
+  - methodology/executing-plans
+related_commands:
+  - /quality:test-plan
+  - /quality:verify-done
+  - /dev:feature
+  - /dev:test
+allowed-tools: Task, Read, Write, Bash, Grep, Glob
+---
+
+# /dev:feature-tested
+
+Build a feature with automatically generated test tasks. This command ensures comprehensive test coverage by creating test tasks alongside implementation tasks.
+
+## Usage
+
+```bash
+/dev:feature-tested <feature-description>
+/dev:feature-tested "Add user authentication" --coverage 90
+/dev:feature-tested "Payment processing" --test-types unit,integration,e2e
+```
+
+## Options
+
+| Option | Description | Default |
+|--------|-------------|---------|
+| `--coverage` | Minimum coverage target | 80% |
+| `--test-types` | Required test types | unit,integration |
+| `--tdd` | Use TDD approach (tests first) | false |
+| `--strict` | Strict enforcement (no overrides) | false |
+
+## How It Works
+
+### 1. Feature Analysis
+Analyzes the feature description to determine:
+- Feature type (API, UI, business logic, etc.)
+- Required test types
+- Coverage targets
+- Acceptance criteria
+
+### 2. Task Generation
+Creates implementation tasks AND corresponding test tasks:
+
+```
+Feature: Add user profile API
+
+Generated Tasks:
+┌─────────────────────────────────────────────────────────────┐
+│ Implementation Tasks                                         │
+├─────────────────────────────────────────────────────────────┤
+│ ☐ TASK-001: Create profile database schema                  │
+│ ☐ TASK-002: Implement profile service                       │
+│ ☐ TASK-003: Create profile API endpoints                    │
+│ ☐ TASK-004: Add input validation                            │
+└─────────────────────────────────────────────────────────────┘
+
+┌─────────────────────────────────────────────────────────────┐
+│ Test Tasks (Auto-Generated)                                  │
+├─────────────────────────────────────────────────────────────┤
+│ ☐ TEST-001: Unit tests for profile service                  │
+│ ☐ TEST-002: Integration tests for profile API               │
+│ ☐ TEST-003: Contract tests for API schema                   │
+│ ☐ TEST-004: Security tests for profile endpoints            │
+└─────────────────────────────────────────────────────────────┘
+```
+
+### 3. Enforcement
+- Cannot mark feature as "done" until all test tasks complete
+- Coverage must meet minimum threshold
+- All tests must pass
+
+## Output Format
+
+```
+╔══════════════════════════════════════════════════════════════╗
+║              FEATURE WITH TESTS CREATED                       ║
+╚══════════════════════════════════════════════════════════════╝
+
+Feature: Add user profile API
+ID: FEAT-042
+Coverage Target: 90%
+
+┌─────────────────────────────────────────────────────────────┐
+│ Implementation Tasks (4)                                     │
+├─────────────────────────────────────────────────────────────┤
+│ TASK-001: Create profile database schema          [Pending] │
+│ TASK-002: Implement profile service               [Pending] │
+│ TASK-003: Create profile API endpoints            [Pending] │
+│ TASK-004: Add input validation                    [Pending] │
+└─────────────────────────────────────────────────────────────┘
+
+┌─────────────────────────────────────────────────────────────┐
+│ Test Tasks (4) - Auto-Generated                              │
+├─────────────────────────────────────────────────────────────┤
+│ TEST-001: Unit tests for profile service          [Pending] │
+│   → Coverage target: 90% for src/services/profile.ts       │
+│   → Test file: tests/unit/services/profile.test.ts         │
+│                                                              │
+│ TEST-002: Integration tests for profile API       [Pending] │
+│   → Coverage target: 75% for API endpoints                 │
+│   → Test file: tests/integration/api/profile.int.test.ts   │
+│                                                              │
+│ TEST-003: Contract tests for API schema           [Pending] │
+│   → Validates: Request/response schemas                    │
+│   → Test file: tests/contract/profile.contract.test.ts     │
+│                                                              │
+│ TEST-004: Security tests for profile endpoints    [Pending] │
+│   → Checks: Auth, injection, XSS                           │
+│   → Test file: tests/security/profile.security.test.ts     │
+└─────────────────────────────────────────────────────────────┘
+
+┌─────────────────────────────────────────────────────────────┐
+│ Completion Requirements                                      │
+├─────────────────────────────────────────────────────────────┤
+│ ☐ All implementation tasks complete                         │
+│ ☐ All test tasks complete                                   │
+│ ☐ Overall coverage ≥ 90%                                    │
+│ ☐ All tests passing                                         │
+│ ☐ No security vulnerabilities                               │
+│ ☐ Code review approved                                      │
+└─────────────────────────────────────────────────────────────┘
+
+Next: Start with TASK-001 or use --tdd to write tests first
+```
+
+## TDD Mode
+
+With `--tdd` flag, tests are created and executed first:
+
+```bash
+/dev:feature-tested "Add user profile API" --tdd
+```
+
+Flow:
+1. Generate test tasks first
+2. Write failing tests (Red)
+3. Implement to pass tests (Green)
+4. Refactor (Refactor)
+5. Verify coverage
+
+## Workflow Integration
+
+### Sprint Planning
+```bash
+/sprint:sprint-new
+# Add feature with tests
+/dev:feature-tested "User profile management"
+```
+
+### Daily Development
+```bash
+# Check what's needed
+/quality:verify-done FEAT-042
+
+# Work on implementation
+# Work on tests
+# Verify completion
+/quality:verify-done FEAT-042
+```
+
+### Feature Completion
+```bash
+# Attempt to complete
+/quality:verify-done FEAT-042
+
+# If all requirements met:
+# ✅ Feature FEAT-042 marked as DONE
+
+# If requirements not met:
+# ❌ Cannot complete: Coverage 75% below 90% minimum
+```
+
+## Examples
+
+### Basic feature with tests
+```bash
+/dev:feature-tested "Add user authentication"
+```
+
+### With strict coverage
+```bash
+/dev:feature-tested "Payment processing" --coverage 95 --strict
+```
+
+### TDD approach
+```bash
+/dev:feature-tested "Shopping cart" --tdd
+```
+
+### Specific test types
+```bash
+/dev:feature-tested "Admin dashboard" --test-types unit,e2e,security
+```
+
+## Comparison with /dev:feature
+
+| Aspect | /dev:feature | /dev:feature-tested |
+|--------|-------------|---------------------|
+| Test tasks | Manual | Auto-generated |
+| Enforcement | Soft | Hard (blocking) |
+| Coverage tracking | Manual | Automatic |
+| Completion check | Manual | Automatic |