@ngxtm/devkit 3.19.0 → 3.21.0

package/merged-commands/plan/parallel.md

@@ -13,14 +13,14 @@ $ARGUMENTS
 
 ## Workflow
 1. Create a directory using naming pattern from `## Naming` section in injected context.
-   Make sure you pass the directory path to every subagent during the process.
+   Make sure you pass the directory path to every Task agent during the process.
 2. Follow strictly to the "Plan Creation & Organization" rules of `planning` skill.
-3. Use multiple `researcher` agents (max 2 agents) in parallel to research for this task:
+3. Use multiple Task agents for research (max 2 agents) in parallel to research for this task: Task(subagent_type="general-purpose", prompt="You are a researcher. Research [aspect]...", description="Research [topic]")
    Each agent research for a different aspect of the task and are allowed to perform max 5 tool calls.
 4. Analyze the codebase by reading `codebase-summary.md`, `code-standards.md`, `system-architecture.md` and `project-overview-pdr.md` file.
    **ONLY PERFORM THIS FOLLOWING STEP IF `codebase-summary.md` is not available or older than 3 days**: Use `/scout <instructions>` slash command to search the codebase for files needed to complete the task.
-5. Main agent gathers all research and scout report filepaths, and pass them to `planner` subagent with the prompt to create a parallel-optimized implementation plan.
-6. Main agent receives the implementation plan from `planner` subagent, and ask user to review the plan
+5. Main agent gathers all research and scout report filepaths, and pass them to Task agent for planning with the prompt to create a parallel-optimized implementation plan: Task(subagent_type="general-purpose", prompt="You are a planner. Create parallel-optimized implementation plan...", description="Create parallel plan")
+6. Main agent receives the implementation plan from Task agent, and ask user to review the plan
 
 ## Post-Plan Validation (Optional)
 
@@ -39,7 +39,7 @@ After plan creation, offer validation interview to confirm decisions before impl
 
 ## Special Requirements for Parallel Execution
 
-**CRITICAL:** The planner subagent must create phases that:
+**CRITICAL:** The Task agent for planning must create phases that:
 1. **Can be executed independently** - Each phase should be self-contained with no runtime dependencies on other phases
 2. **Have clear boundaries** - No file overlap between phases (each file should only be modified in ONE phase)
 3. **Separate concerns logically** - Group by architectural layer, feature domain, or technology stack

package/merged-commands/plan/two.md

@@ -7,20 +7,20 @@ Think harder.
 Activate `planning` skill.
 
 ## Your mission
-Use the `planner` subagent to create 2 detailed implementation plans for this following task:
+Use the Task agent for planning to create 2 detailed implementation plans for this following task: Task(subagent_type="general-purpose", prompt="You are a planner. Create 2 implementation plans...", description="Create dual plans")
 <task>
  $ARGUMENTS
 </task>
 
 ## Workflow
 1. First: Create a directory using naming pattern from `## Naming` section in injected context.
-   Make sure you pass the directory path to every subagent during the process.
+   Make sure you pass the directory path to every Task agent during the process.
 2. Follow strictly to the "Plan Creation & Organization" rules of `planning` skill.
-3. Use multiple `researcher` agents in parallel to research for this task, each agent research for a different aspect of the task and perform max 5 researches (max 5 tool calls).
-4. Use `scout` agent to search the codebase for files needed to complete the task.
-5. Main agent gathers all research and scout report filepaths, and pass them to `planner` subagent with the detailed instructions prompt to create an implementation plan of this task.
+3. Use multiple Task agents for research in parallel to research for this task, each agent research for a different aspect of the task and perform max 5 researches (max 5 tool calls): Task(subagent_type="general-purpose", prompt="You are a researcher. Research [aspect]...", description="Research [topic]")
+4. Use Task agent for scouting to search the codebase for files needed to complete the task: Task(subagent_type="general-purpose", prompt="You are a scout. Search codebase...", description="Scout codebase")
+5. Main agent gathers all research and scout report filepaths, and pass them to Task agent for planning with the detailed instructions prompt to create an implementation plan of this task: Task(subagent_type="general-purpose", prompt="You are a planner. Create implementation plan...", description="Create plan")
   **Output:** Provide at least 2 implementation approaches with clear trade-offs, and explain the pros and cons of each approach, and provide a recommended approach.
-1. Main agent receives the implementation plan from `planner` subagent, and ask user to review the plan
+1. Main agent receives the implementation plan from Task agent, and ask user to review the plan
 
 ## Plan File Specification
 - Every `plan.md` MUST start with YAML frontmatter:

package/merged-commands/recover.md

@@ -0,0 +1,22 @@
+---
+description: "\U0001F504 Recover context from a previous session checkpoint"
+---
+
+Look for checkpoint files in `.claude/sessions/` directory and recover context from a previous session.
+
+## Workflow
+
+1. **Check git**: Run `git rev-parse --is-inside-work-tree 2>/dev/null` to detect git repo
+2. **Get branch**: If git repo, run `git branch --show-current` to get current branch
+3. **Find checkpoints**: Glob `.claude/sessions/*.md` to list all checkpoint files
+4. **Cleanup stale**: Delete any checkpoint files older than 7 days (abandoned sessions)
+5. **Check results**: If no checkpoints remain → tell user "No active checkpoints found"
+6. **Filter by branch**: If git repo, filter checkpoints matching `branch:{current-branch}` in the first line. If no match on current branch, show all checkpoints with branch labels.
+7. **Show recent**: Display max 5 most recent checkpoints (sorted by filename date prefix `YYMMDD-HHMM`)
+8. **Select**: If only 1 match → read it automatically. If multiple → always list them and let user pick using `AskUserQuestion`.
+9. **Validate**: Verify the checkpoint file has a `#` header line and a `## Next Action` section. If malformed, skip it and try the next one.
+10. **Display summary**: Show the checkpoint's task description, current phase, progress (done/pending), next action, and referenced plan file
+11. **Confirm**: Ask user "Continue from this checkpoint?"
+12. **Resume**: If yes → read the referenced plan file (if any) and proceed with the Next Action from the checkpoint
+
+**IMPORTANT**: For non-git projects, skip branch filtering and show all checkpoints.

package/merged-commands/requesting-code-review.md

@@ -7,14 +7,14 @@ source: community
 
 # Requesting Code Review
 
-Dispatch superpowers:code-reviewer subagent to catch issues before they cascade.
+Dispatch superpowers:code-reviewer Task agent to catch issues before they cascade.
 
 **Core principle:** Review early, review often.
 
 ## When to Request Review
 
 **Mandatory:**
-- After each task in subagent-driven development
+- After each task in Task agent-driven development
 - After completing major feature
 - Before merge to main
 
@@ -31,7 +31,7 @@ BASE_SHA=$(git rev-parse HEAD~1)  # or origin/main
 HEAD_SHA=$(git rev-parse HEAD)
 ```
 
-**2. Dispatch code-reviewer subagent:**
+**2. Dispatch code-reviewer Task agent:**
 
 Use Task tool with superpowers:code-reviewer type, fill template at `code-reviewer.md`
 
@@ -58,14 +58,14 @@ You: Let me request code review before proceeding.
 BASE_SHA=$(git log --oneline | grep "Task 1" | head -1 | awk '{print $1}')
 HEAD_SHA=$(git rev-parse HEAD)
 
-[Dispatch superpowers:code-reviewer subagent]
+[Dispatch superpowers:code-reviewer Task agent]
   WHAT_WAS_IMPLEMENTED: Verification and repair functions for conversation index
   PLAN_OR_REQUIREMENTS: Task 2 from docs/plans/deployment-plan.md
   BASE_SHA: a7981ec
   HEAD_SHA: 3df7661
   DESCRIPTION: Added verifyIndex() and repairIndex() with 4 issue types
 
-[Subagent returns]:
+[Task agent returns]:
   Strengths: Clean architecture, real tests
   Issues:
     Important: Missing progress indicators
@@ -78,7 +78,7 @@ You: [Fix progress indicators]
 
 ## Integration with Workflows
 
-**Subagent-Driven Development:**
+**Task Agent-Driven Development:**
 - Review after EACH task
 - Catch issues before they compound
 - Fix before moving to next task

package/merged-commands/review/codebase/parallel.md

@@ -3,7 +3,7 @@ description: ⚡⚡⚡ Ultrathink edge cases, then parallel verify with code-rev
 argument-hint: [scope-or-prompt]
 ---
 
-**Ultrathink** to exhaustively list ALL potential edge cases, then dispatch parallel `code-reviewer` agents to verify: <scope>$ARGUMENTS</scope>
+**Ultrathink** to exhaustively list ALL potential edge cases, then dispatch parallel Task agents for code review to verify: <scope>$ARGUMENTS</scope>
 
 **IMPORTANT:** Activate needed skills. Ensure token efficiency. Sacrifice grammar for concision.
 
@@ -39,13 +39,13 @@ Main agent deeply analyzes the scope to LIST all potential edge cases FIRST:
 ### 2. Categorize & Assign
 
 Group edge cases by similar scope for parallel verification:
-- Each category → one `code-reviewer` agent
+- Each category → one Task agent for code review
 - Max 6 categories (merge small ones)
 - Each reviewer gets specific edge cases to VERIFY, not discover
 
 ### 3. Parallel Verification
 
-Launch N `code-reviewer` subagents simultaneously:
+Launch N Task agents for code review simultaneously: Task(subagent_type="general-purpose", prompt="You are a code-reviewer. Verify these edge cases...", description="Verify edge cases for [category]")
 - Pass: category name, list of edge cases, relevant files
 - Task: **VERIFY** if each edge case is properly handled in code
 - Report: which edge cases are handled vs unhandled
@@ -93,7 +93,7 @@ Collect all verification reports:
 ### 6. Final Report
 
 - Summary of verification
-- Ask: "Commit? [Y/n]" → use `git-manager`
+- Ask: "Commit? [Y/n]" → use Task agent for git management
 
 ## Example
 
@@ -112,7 +112,7 @@ User: /review:codebase:parallel auth module
    - Token handling (5 cases)
    - Session management (3 cases)
 
-3. Parallel → 3 code-reviewers verify simultaneously
+3. Parallel → 3 Task agents for code review verify simultaneously
 
 4. Aggregate → 8 handled, 3 unhandled, 1 partial
 

package/merged-commands/review/codebase.md

@@ -3,7 +3,7 @@ description: ⚡⚡⚡ Scan & analyze the codebase.
 argument-hint: [tasks-or-prompt]
 ---
 
-Think harder to scan the codebase and analyze it follow the Orchestration Protocol, Core Responsibilities, Subagents Team and Development Rules: 
+Think harder to scan the codebase and analyze it follow the Orchestration Protocol, Core Responsibilities, and Development Rules:
 <tasks>$ARGUMENTS</tasks>
 
 ---
@@ -22,26 +22,26 @@ Think harder to scan the codebase and analyze it follow the Orchestration Protoc
 
 ### Research
 
-* Use 2 `researcher` subagents in parallel to search up to max 5 sources for the user's request, idea validation, best practices, challenges, and find the best possible solutions.
+* Use 2 Task agents in parallel to search up to max 5 sources for the user's request, idea validation, best practices, challenges, and find the best possible solutions: Task(subagent_type="general-purpose", prompt="You are a researcher. Search for...", description="Research [topic]")
 * Keep every research markdown report concise (≤150 lines) while covering all requested topics and citations.
 * Use `/scout:ext` (preferred) or `/scout` (fallback) slash command to search the codebase for files needed to complete the task
 
 ### Code Review
 
-* After finishing, use multiple `code-reviewer` subagents in parallel to review code. 
+* After finishing, use multiple Task agents in parallel to review code: Task(subagent_type="general-purpose", prompt="You are a code-reviewer. Review...", description="Code review")
 * If there are any issues, duplicate code, or security vulnerabilities, ask main agent to improve the code and repeat the "Testing" process until all tests pass. 
 * When all tests pass, code is reviewed, the tasks are completed, report back to user with a summary of the changes and explain everything briefly, ask user to review the changes and approve them.
 * **IMPORTANT:** Sacrifice grammar for the sake of concision when writing outputs.
 
 ### Plan
-* Use `planner` subagent to analyze reports from `researcher` and `scout` subagents to create an improvement plan following the progressive disclosure structure:
+* Use Task agent to analyze reports from researcher and scout Task agents to create an improvement plan following the progressive disclosure structure: Task(subagent_type="general-purpose", prompt="You are a planner. Analyze reports and create improvement plan...", description="Create improvement plan")
   - Create a directory using naming pattern from `## Naming` section.
   - Save the overview access point at `plan.md`, keep it generic, under 80 lines, and list each phase with status/progress and links.
   - For each phase, add `phase-XX-phase-name.md` files containing sections (Context links, Overview with date/priority/statuses, Key Insights, Requirements, Architecture, Related code files, Implementation Steps, Todo list, Success Criteria, Risk Assessment, Security Considerations, Next steps).
 
 ### Final Report
 * Report back to user with a summary of the changes and explain everything briefly, guide user to get started and suggest the next steps.
-* Ask the user if they want to commit and push to git repository, if yes, use `git-manager` subagent to commit and push to git repository.
+* Ask the user if they want to commit and push to git repository, if yes, use Task agent to commit and push to git repository: Task(subagent_type="general-purpose", prompt="You are a git-manager. Commit and push...", description="Git commit and push")
 
 **REMEMBER**:
 - You can always generate images with `ai-multimodal` skill on the fly for visual assets.

package/merged-commands/review/fast.md

@@ -1,5 +1,5 @@
 ---
-description: ⚡ Quick Review — Fast PR/file review
+description: Quick Review — Fast PR/file review
 version: "1.0"
 category: validation
 execution-mode: execute
@@ -13,38 +13,22 @@ execution-mode: execute
 
 ---
 
-## 🛑 PRE-FLIGHT (DO FIRST — BLOCKS PHASE 1)
-
-**LOAD now** (in order; path `./rules/` or `~/.{TOOL}/skills/agent-assistant/rules/`):
-1. ORCHESTRATION-LAWS.md  
-2. ADAPTIVE-EXECUTION.md  
-3. EXECUTION-PROTOCOL.md  
-
-**⛔ Do not run Phase 1 until all are loaded.** Follow **all** rules in those files; they override any conflicting instructions in this file.
-
----
-
-## 🔀 TIERED EXECUTION
-
-| Tier | When | Action |
-|------|------|--------|
-| **TIER 1** | runSubagent EXISTS | Invoke sub-agent (MANDATORY) |
-| **TIER 2** | Tool MISSING | EMBODY agent file (FALLBACK) |
+## Execution
+One phase at a time, sequential. Each phase must complete before next begins.
 
 ---
 
-## ⛔ INCREMENTAL EXECUTION (MANDATORY)
+## Phase 1: CODE REVIEW
 
-One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in one reply. No batching (load only what each phase needs). **Within each phase:** when doing a part, output it in format so user sees what’s happening (announce before doing).
-
----
+| Attribute | Value |
+|-----------|-------|
+| **Role** | `reviewer` |
+| **Goal** | Review code quality |
+| **Exit** | Issues documented, recommendations provided |
 
-## 🎭 Phase 1: CODE REVIEW
+### Delegation
 
-| Agent | `reviewer` |
-|-------|------------|
-| Goal | Review code quality |
-| Exit | Issues documented, recommendations provided |
+> Task(subagent_type="general-purpose", prompt="You are a reviewer. Review code quality. Exit when issues are documented and recommendations are provided.", description="reviewer: Review code quality")
 
 ---
 
@@ -61,5 +45,5 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 
 Present review with:
 
-1. ✅ **Approved** — Code ready
-2. 🔧 **Fix needed** → `/fix:fast`
+1. **Approved** — Code ready
+2. **Fix needed** → `/fix:fast`

package/merged-commands/review/hard.md

@@ -1,5 +1,5 @@
 ---
-description: ⚡⚡⚡ Full Review — Deep code analysis with architecture review
+description: Full Review — Deep code analysis with architecture review
 version: "1.0"
 category: validation
 execution-mode: execute
@@ -13,27 +13,7 @@ execution-mode: execute
 
 ---
 
-## 🛑 PRE-FLIGHT (DO FIRST — BLOCKS PHASE 1)
-
-**LOAD now** (in order; path `./rules/` or `~/.{TOOL}/skills/agent-assistant/rules/`):
-1. ORCHESTRATION-LAWS.md  
-2. ADAPTIVE-EXECUTION.md  
-3. EXECUTION-PROTOCOL.md  
-
-**⛔ Do not run Phase 1 until all are loaded.** Follow **all** rules in those files; they override any conflicting instructions in this file.
-
----
-
-## 🔀 TIERED EXECUTION
-
-| Tier | When | Action |
-|------|------|--------|
-| **TIER 1** | runSubagent EXISTS | Invoke sub-agent (MANDATORY) |
-| **TIER 2** | Tool MISSING | EMBODY agent file (FALLBACK) |
-
----
-
-## 📁 PLAN COMPLIANCE CHECK
+## PLAN COMPLIANCE CHECK
 
 ```
 IF ./reports/plans/PLAN-{scope}.md exists:
@@ -44,46 +24,65 @@ IF ./reports/plans/PLAN-{scope}.md exists:
 
 ---
 
-## ⛔ INCREMENTAL EXECUTION (MANDATORY)
-
-One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in one reply. No batching (load only what each phase needs). **Within each phase:** when doing a part, output it in format so user sees what’s happening (announce before doing).
+## Execution
+One phase at a time, sequential. Each phase must complete before next begins.
 
 ---
 
-## 🎭 Phase 1: ARCHITECTURE REVIEW
+## Phase 1: ARCHITECTURE REVIEW
+
+| Attribute | Value |
+|-----------|-------|
+| **Role** | `tech-lead` |
+| **Goal** | Review architecture decisions |
+| **Exit** | Architecture assessed, patterns validated |
+
+### Delegation
 
-| Agent | `tech-lead` |
-|-------|-------------|
-| Goal | Review architecture decisions |
-| Exit | Architecture assessed, patterns validated |
+> Task(subagent_type="general-purpose", prompt="You are a tech-lead. Review architecture decisions. Exit when architecture is assessed and patterns are validated.", description="tech-lead: Review architecture decisions")
 
 ---
 
-## 🎭 Phase 2: CODE REVIEW
+## Phase 2: CODE REVIEW
+
+| Attribute | Value |
+|-----------|-------|
+| **Role** | `reviewer` |
+| **Prerequisite** | READ PLAN file if exists |
+| **Goal** | Deep code analysis |
+| **Exit** | Code quality assessed, issues documented |
+
+### Delegation
 
-| Agent | `reviewer` |
-|-------|------------|
-| Prerequisite | READ PLAN file if exists |
-| Goal | Deep code analysis |
-| Exit | Code quality assessed, issues documented |
+> Task(subagent_type="general-purpose", prompt="You are a reviewer. Perform deep code analysis. Read the PLAN file if it exists. Exit when code quality is assessed and issues are documented.", description="reviewer: Deep code analysis")
 
 ---
 
-## 🎭 Phase 3: SECURITY REVIEW
+## Phase 3: SECURITY REVIEW
 
-| Agent | `security-engineer` |
-|-------|----------------------|
-| Goal | Security assessment |
-| Exit | Security reviewed, vulnerabilities documented |
+| Attribute | Value |
+|-----------|-------|
+| **Role** | `security-engineer` |
+| **Goal** | Security assessment |
+| **Exit** | Security reviewed, vulnerabilities documented |
+
+### Delegation
+
+> Task(subagent_type="general-purpose", prompt="You are a security-engineer. Perform a security assessment. Exit when security is reviewed and vulnerabilities are documented.", description="security-engineer: Security assessment")
 
 ---
 
-## 🎭 Phase 4: PERFORMANCE REVIEW
+## Phase 4: PERFORMANCE REVIEW
+
+| Attribute | Value |
+|-----------|-------|
+| **Role** | `performance-engineer` |
+| **Goal** | Performance assessment |
+| **Exit** | Performance issues identified |
+
+### Delegation
 
-| Agent | `performance-engineer` |
-|-------|------------------------|
-| Goal | Performance assessment |
-| Exit | Performance issues identified |
+> Task(subagent_type="general-purpose", prompt="You are a performance-engineer. Perform a performance assessment. Exit when performance issues are identified.", description="performance-engineer: Performance assessment")
 
 ---
 
@@ -91,6 +90,6 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 
 Present review with:
 
-1. ✅ **Approved** — Code ready
-2. 🔧 **Fix** → `/fix`
-3. 🧪 **Test** → `/test`
+1. **Approved** — Code ready
+2. **Fix** → `/fix`
+3. **Test** → `/test`

package/merged-commands/review.md

@@ -13,17 +13,6 @@ execution-mode: router
 
 ---
 
-## 🛑 PRE-FLIGHT (DO FIRST — BLOCKS EXECUTION)
-
-**LOAD now** (in order; path `./rules/` or `~/.{TOOL}/skills/agent-assistant/rules/`):
-1. ORCHESTRATION-LAWS.md  
-2. ADAPTIVE-EXECUTION.md  
-3. EXECUTION-PROTOCOL.md  
-
-**⛔ Do not run any workflow phase until all are loaded.** Follow **all** rules in those files. Then run this file's ROUTING LOGIC, LOAD the chosen variant workflow, and execute it.
-
----
-
 ## ROUTING LOGIC
 
 ```

package/merged-commands/security-scanning-security-hardening.md

@@ -36,19 +36,19 @@ Implement comprehensive security hardening with defense-in-depth strategy throug
 ## Phase 1: Comprehensive Security Assessment
 
 ### 1. Initial Vulnerability Scanning
-- Use Task tool with subagent_type="security-auditor"
+- Use Task tool with subagent_type="general-purpose"
 - Prompt: "Perform comprehensive security assessment on: $ARGUMENTS. Execute SAST analysis with Semgrep/SonarQube, DAST scanning with OWASP ZAP, dependency audit with Snyk/Trivy, secrets detection with GitLeaks/TruffleHog. Generate SBOM for supply chain analysis. Identify OWASP Top 10 vulnerabilities, CWE weaknesses, and CVE exposures."
 - Output: Detailed vulnerability report with CVSS scores, exploitability analysis, attack surface mapping, secrets exposure report, SBOM inventory
 - Context: Initial baseline for all remediation efforts
 
 ### 2. Threat Modeling and Risk Analysis
-- Use Task tool with subagent_type="security-auditor"
+- Use Task tool with subagent_type="general-purpose"
 - Prompt: "Conduct threat modeling using STRIDE methodology for: $ARGUMENTS. Analyze attack vectors, create attack trees, assess business impact of identified vulnerabilities. Map threats to MITRE ATT&CK framework. Prioritize risks based on likelihood and impact."
 - Output: Threat model diagrams, risk matrix with prioritized vulnerabilities, attack scenario documentation, business impact analysis
 - Context: Uses vulnerability scan results to inform threat priorities
 
 ### 3. Architecture Security Review
-- Use Task tool with subagent_type="backend-api-security::backend-architect"
+- Use Task tool with subagent_type="general-purpose"
 - Prompt: "Review architecture for security weaknesses in: $ARGUMENTS. Evaluate service boundaries, data flow security, authentication/authorization architecture, encryption implementation, network segmentation. Design zero-trust architecture patterns. Reference threat model and vulnerability findings."
 - Output: Security architecture assessment, zero-trust design recommendations, service mesh security requirements, data classification matrix
 - Context: Incorporates threat model to address architectural vulnerabilities
@@ -56,25 +56,25 @@ Implement comprehensive security hardening with defense-in-depth strategy throug
 ## Phase 2: Vulnerability Remediation
 
 ### 4. Critical Vulnerability Fixes
-- Use Task tool with subagent_type="security-auditor"
+- Use Task tool with subagent_type="general-purpose"
 - Prompt: "Coordinate immediate remediation of critical vulnerabilities (CVSS 7+) in: $ARGUMENTS. Fix SQL injections with parameterized queries, XSS with output encoding, authentication bypasses with secure session management, insecure deserialization with input validation. Apply security patches for CVEs."
 - Output: Patched code with vulnerability fixes, security patch documentation, regression test requirements
 - Context: Addresses high-priority items from vulnerability assessment
 
 ### 5. Backend Security Hardening
-- Use Task tool with subagent_type="backend-api-security::backend-security-coder"
+- Use Task tool with subagent_type="general-purpose"
 - Prompt: "Implement comprehensive backend security controls for: $ARGUMENTS. Add input validation with OWASP ESAPI, implement rate limiting and DDoS protection, secure API endpoints with OAuth2/JWT validation, add encryption for data at rest/transit using AES-256/TLS 1.3. Implement secure logging without PII exposure."
 - Output: Hardened API endpoints, validation middleware, encryption implementation, secure configuration templates
 - Context: Builds upon vulnerability fixes with preventive controls
 
 ### 6. Frontend Security Implementation
-- Use Task tool with subagent_type="frontend-mobile-security::frontend-security-coder"
+- Use Task tool with subagent_type="general-purpose"
 - Prompt: "Implement frontend security measures for: $ARGUMENTS. Configure CSP headers with nonce-based policies, implement XSS prevention with DOMPurify, secure authentication flows with PKCE OAuth2, add SRI for external resources, implement secure cookie handling with SameSite/HttpOnly/Secure flags."
 - Output: Secure frontend components, CSP policy configuration, authentication flow implementation, security headers configuration
 - Context: Complements backend security with client-side protections
 
 ### 7. Mobile Security Hardening
-- Use Task tool with subagent_type="frontend-mobile-security::mobile-security-coder"
+- Use Task tool with subagent_type="general-purpose"
 - Prompt: "Implement mobile app security for: $ARGUMENTS. Add certificate pinning, implement biometric authentication, secure local storage with encryption, obfuscate code with ProGuard/R8, implement anti-tampering and root/jailbreak detection, secure IPC communications."
 - Output: Hardened mobile application, security configuration files, obfuscation rules, certificate pinning implementation
 - Context: Extends security to mobile platforms if applicable
@@ -82,19 +82,19 @@ Implement comprehensive security hardening with defense-in-depth strategy throug
 ## Phase 3: Security Controls Implementation
 
 ### 8. Authentication and Authorization Enhancement
-- Use Task tool with subagent_type="security-auditor"
+- Use Task tool with subagent_type="general-purpose"
 - Prompt: "Implement modern authentication system for: $ARGUMENTS. Deploy OAuth2/OIDC with PKCE, implement MFA with TOTP/WebAuthn/FIDO2, add risk-based authentication, implement RBAC/ABAC with principle of least privilege, add session management with secure token rotation."
 - Output: Authentication service configuration, MFA implementation, authorization policies, session management system
 - Context: Strengthens access controls based on architecture review
 
 ### 9. Infrastructure Security Controls
-- Use Task tool with subagent_type="deployment-strategies::deployment-engineer"
+- Use Task tool with subagent_type="general-purpose"
 - Prompt: "Deploy infrastructure security controls for: $ARGUMENTS. Configure WAF rules for OWASP protection, implement network segmentation with micro-segmentation, deploy IDS/IPS systems, configure cloud security groups and NACLs, implement DDoS protection with rate limiting and geo-blocking."
 - Output: WAF configuration, network security policies, IDS/IPS rules, cloud security configurations
 - Context: Implements network-level defenses
 
 ### 10. Secrets Management Implementation
-- Use Task tool with subagent_type="deployment-strategies::deployment-engineer"
+- Use Task tool with subagent_type="general-purpose"
 - Prompt: "Implement enterprise secrets management for: $ARGUMENTS. Deploy HashiCorp Vault or AWS Secrets Manager, implement secret rotation policies, remove hardcoded secrets, configure least-privilege IAM roles, implement encryption key management with HSM support."
 - Output: Secrets management configuration, rotation policies, IAM role definitions, key management procedures
 - Context: Eliminates secrets exposure vulnerabilities
@@ -102,19 +102,19 @@ Implement comprehensive security hardening with defense-in-depth strategy throug
 ## Phase 4: Validation and Compliance
 
 ### 11. Penetration Testing and Validation
-- Use Task tool with subagent_type="security-auditor"
+- Use Task tool with subagent_type="general-purpose"
 - Prompt: "Execute comprehensive penetration testing for: $ARGUMENTS. Perform authenticated and unauthenticated testing, API security testing, business logic testing, privilege escalation attempts. Use Burp Suite, Metasploit, and custom exploits. Validate all security controls effectiveness."
 - Output: Penetration test report, proof-of-concept exploits, remediation validation, security control effectiveness metrics
 - Context: Validates all implemented security measures
 
 ### 12. Compliance and Standards Verification
-- Use Task tool with subagent_type="security-auditor"
+- Use Task tool with subagent_type="general-purpose"
 - Prompt: "Verify compliance with security frameworks for: $ARGUMENTS. Validate against OWASP ASVS Level 2, CIS Benchmarks, SOC2 Type II requirements, GDPR/CCPA privacy controls, HIPAA/PCI-DSS if applicable. Generate compliance attestation reports."
 - Output: Compliance assessment report, gap analysis, remediation requirements, audit evidence collection
 - Context: Ensures regulatory and industry standard compliance
 
 ### 13. Security Monitoring and SIEM Integration
-- Use Task tool with subagent_type="incident-response::devops-troubleshooter"
+- Use Task tool with subagent_type="general-purpose"
 - Prompt: "Implement security monitoring and SIEM for: $ARGUMENTS. Deploy Splunk/ELK/Sentinel integration, configure security event correlation, implement behavioral analytics for anomaly detection, set up automated incident response playbooks, create security dashboards and alerting."
 - Output: SIEM configuration, correlation rules, incident response playbooks, security dashboards, alert definitions
 - Context: Establishes continuous security monitoring

package/merged-commands/skill/add.md

@@ -4,7 +4,7 @@ argument-hint: [skill-name] [reference-or-script-prompt]
 ---
 
 Think harder.
-Use `skill-creator` skill and `claude-code-guide` subagent.
+Use `skill-creator` skill and Task agent for Claude Code guidance: Task(subagent_type="general-purpose", prompt="You are a claude-code-guide...", description="Claude Code guidance").
 Use `docs-seeker` skills to search for documentation if needed.
 
 ## Arguments
@@ -24,11 +24,11 @@ $2
 Base on the requirements:
 - Always keep in mind that `SKILL.md` and reference files should be token consumption efficient, so that **progressive disclosure** can be leveraged at best.
 - `SKILL.md` is always short and concise, straight to the point, treat it as a quick reference guide.
-- If you're given nothing, use `AskUserQuestion` tool for clarifications and `researcher` subagent to research about the topic.
-- If you're given an URL, it's documentation page, use `Explore` subagent to explore every internal link and report back to main agent, don't skip any link.
-- If you receive a lot of URLs, use multiple `Explore` subagents to explore them in parallel, then report back to main agent.
-- If you receive a lot of files, use multiple `Explore` subagents to explore them in parallel, then report back to main agent.
-- If you're given a Github URL, use [`repomix`](https://repomix.com/guide/usage) command to summarize ([install it](https://repomix.com/guide/installation) if needed) and spawn multiple `Explore` subagents to explore it in parallel, then report back to main agent.
+- If you're given nothing, use `AskUserQuestion` tool for clarifications and Task agent for research to research about the topic: Task(subagent_type="general-purpose", prompt="You are a researcher. Research...", description="Research topic").
+- If you're given an URL, it's documentation page, use Task agent for exploration to explore every internal link and report back to main agent, don't skip any link: Task(subagent_type="general-purpose", prompt="You are an explorer. Explore all internal links...", description="Explore URL").
+- If you receive a lot of URLs, use multiple Task agents for exploration to explore them in parallel, then report back to main agent.
+- If you receive a lot of files, use multiple Task agents for exploration to explore them in parallel, then report back to main agent.
+- If you're given a Github URL, use [`repomix`](https://repomix.com/guide/usage) command to summarize ([install it](https://repomix.com/guide/installation) if needed) and spawn multiple Task agents for exploration to explore it in parallel, then report back to main agent.
 
 **IMPORTANT:**
 - Skills are not documentation, they are practical instructions for Claude Code to use the tools, packages, plugins or APIs to achieve the tasks.

package/merged-commands/skill/create.md

@@ -4,7 +4,7 @@ argument-hint: [prompt-or-llms-or-github-url]
 ---
 
 Ultrathink.
-Use `skill-creator` skill and `claude-code-guide` subagent.
+Use `skill-creator` skill and Task agent for Claude Code guidance: Task(subagent_type="general-purpose", prompt="You are a claude-code-guide...", description="Claude Code guidance").
 Use `docs-seeker` skills to search for documentation if needed.
 
 ## Your mission
@@ -17,11 +17,11 @@ Create a new skill in `.claude/skills/` directory.
 Base on the requirements:
 - Always keep in mind that `SKILL.md` and reference files should be token consumption efficient, so that **progressive disclosure** can be leveraged at best.
 - `SKILL.md` is always short and concise, straight to the point, treat it as a quick reference guide.
-- If you're given nothing, use `AskUserQuestion` tool for clarifications and `researcher` subagent to research about the topic.
-- If you're given an URL, it's documentation page, use `Explore` subagent to explore every internal link and report back to main agent, don't skip any link.
-- If you receive a lot of URLs, use multiple `Explore` subagents to explore them in parallel, then report back to main agent.
-- If you receive a lot of files, use multiple `Explore` subagents to explore them in parallel, then report back to main agent.
-- If you're given a Github URL, use [`repomix`](https://repomix.com/guide/usage) command to summarize ([install it](https://repomix.com/guide/installation) if needed) and spawn multiple `Explore` subagents to explore it in parallel, then report back to main agent.
+- If you're given nothing, use `AskUserQuestion` tool for clarifications and Task agent for research to research about the topic: Task(subagent_type="general-purpose", prompt="You are a researcher. Research...", description="Research topic").
+- If you're given an URL, it's documentation page, use Task agent for exploration to explore every internal link and report back to main agent, don't skip any link: Task(subagent_type="general-purpose", prompt="You are an explorer. Explore all internal links...", description="Explore URL").
+- If you receive a lot of URLs, use multiple Task agents for exploration to explore them in parallel, then report back to main agent.
+- If you receive a lot of files, use multiple Task agents for exploration to explore them in parallel, then report back to main agent.
+- If you're given a Github URL, use [`repomix`](https://repomix.com/guide/usage) command to summarize ([install it](https://repomix.com/guide/installation) if needed) and spawn multiple Task agents for exploration to explore it in parallel, then report back to main agent.
 
 **IMPORTANT:**
 - Skills are not documentation, they are practical instructions for Claude Code to use the tools, packages, plugins or APIs to achieve the tasks.

package/merged-commands/skill/fix-logs.md

@@ -4,7 +4,7 @@ argument-hint: [prompt-or-path-to-skill]
 ---
 
 Think harder.
-Use `skill-creator` skill and `claude-code-guide` subagent.
+Use `skill-creator` skill and Task agent for Claude Code guidance: Task(subagent_type="general-purpose", prompt="You are a claude-code-guide...", description="Claude Code guidance").
 Use `docs-seeker` skills to search for documentation if needed.
 
 ## Your mission
@@ -15,8 +15,8 @@ Fix the agent skill based on the current `logs.txt` file (in the project root di
 
 ## Rules of Skill Fixing:
 Base on the requirements:
-- If you're given nothing, use `AskUserQuestion` tool for clarifications and `researcher` subagent to research about the topic.
-- If you're given an URL, it's documentation page, use `Explorer` subagent to explore every internal link and report back to main agent, don't skip any link.
-- If you receive a lot of URLs, use multiple `Explorer` subagents to explore them in parallel, then report back to main agent.
-- If you receive a lot of files, use multiple `Explorer` subagents to explore them in parallel, then report back to main agent.
-- If you're given a Github URL, use [`repomix`](https://repomix.com/guide/usage) command to summarize ([install it](https://repomix.com/guide/installation) if needed) and spawn multiple `Explorer` subagents to explore it in parallel, then report back to main agent.
+- If you're given nothing, use `AskUserQuestion` tool for clarifications and Task agent for research to research about the topic: Task(subagent_type="general-purpose", prompt="You are a researcher. Research...", description="Research topic").
+- If you're given an URL, it's documentation page, use Task agent for exploration to explore every internal link and report back to main agent, don't skip any link: Task(subagent_type="general-purpose", prompt="You are an explorer. Explore all internal links...", description="Explore URL").
+- If you receive a lot of URLs, use multiple Task agents for exploration to explore them in parallel, then report back to main agent.
+- If you receive a lot of files, use multiple Task agents for exploration to explore them in parallel, then report back to main agent.
+- If you're given a Github URL, use [`repomix`](https://repomix.com/guide/usage) command to summarize ([install it](https://repomix.com/guide/installation) if needed) and spawn multiple Task agents for exploration to explore it in parallel, then report back to main agent.

package/merged-commands/skill/optimize/auto.md

@@ -4,7 +4,7 @@ argument-hint: [skill-name] [prompt]
 ---
 
 Think harder.
-Use `skill-creator` skill and `claude-code-guide` subagent.
+Use `skill-creator` skill and Task agent for Claude Code guidance: Task(subagent_type="general-purpose", prompt="You are a claude-code-guide...", description="Claude Code guidance").
 Use `docs-seeker` skills to search for documentation if needed.
 
 ## Arguments