@ngxtm/devkit 3.19.0 → 3.21.0

package/merged-commands/deploy/production.md

@@ -1,5 +1,5 @@
 ---
-description: 🚀 Deploy Production — Production release with safety gates
+description: Deploy Production — Production release with safety gates
 version: "1.0"
 category: operations
 execution-mode: execute
@@ -11,55 +11,21 @@ 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 PROTOCOL (MANDATORY)
-
-> **Reference**: `{RULES_PATH}/ADAPTIVE-EXECUTION.md`
-
-```yaml
-tiered_execution:
-  principle: "Sub-agent FIRST (Tier 1). EMBODY ONLY on system failure (Tier 2)."
-  for_each_phase:
-    TIER_1_MANDATORY: "IF tool exists → MUST use SUB_AGENT_DELEGATION"
-    TIER_2_FALLBACK: "ONLY on system error—NOT complexity/preference/speed"
-  anti_lazy_fallback:
-    - ❌ NEVER use Tier 2 when Tier 1 tool is available
-    - ✅ ALWAYS attempt Tier 1 first when tool exists
-```
+## Execution
+One phase at a time, sequential. Each phase must complete before next begins.
 
 ---
 
-## ⛔ 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).
-
----
-
-## 🎭 Phase 1: FULL READINESS CHECK
+## Phase 1: FULL READINESS CHECK
 
 | Attribute | Value |
 |-----------|-------|
-| **Agent** | `devops-engineer` |
+| **Role** | `devops-engineer` |
 | **Goal** | Complete pre-production verification |
 
-### ⚡ TIERED EXECUTION
-
-**TIER 1 (MANDATORY when tool exists):**
-> Invoke runSubagent for `devops-engineer`. Context: ISOLATED.
+### Delegation
 
-**TIER 2 (FALLBACK on system error only):**
-> Load `{AGENTS_PATH}/devops-engineer.md`
-> EMBODY [devops-engineer] — Requires logged system error justification.
+> Task(subagent_type="general-purpose", prompt="You are a devops-engineer. Complete pre-production verification. Exit when all tests pass, security scan is clean, rollback plan is documented, and monitoring is ready.", description="devops-engineer: Complete pre-production verification")
 
 **Exit Criteria:**
 
@@ -70,21 +36,16 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 
 ---
 
-## 🎭 Phase 2: SECURITY GATE
+## Phase 2: SECURITY GATE
 
 | Attribute | Value |
 |-----------|-------|
-| **Agent** | `security-engineer` |
+| **Role** | `security-engineer` |
 | **Goal** | Final security verification |
 
-### ⚡ TIERED EXECUTION
+### Delegation
 
-**TIER 1 (MANDATORY when tool exists):**
-> Invoke runSubagent for `security-engineer`. Context: ISOLATED.
-
-**TIER 2 (FALLBACK on system error only):**
-> Load `{AGENTS_PATH}/security-engineer.md`
-> EMBODY [security-engineer] — Requires logged system error justification.
+> Task(subagent_type="general-purpose", prompt="You are a security-engineer. Perform final security verification before production deployment. Exit when no critical vulnerabilities exist, secrets are secured, and deployment is approved for production.", description="security-engineer: Final security verification")
 
 **Exit Criteria:**
 
@@ -94,21 +55,16 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 
 ---
 
-## 🎭 Phase 3: PRODUCTION DEPLOY
+## Phase 3: PRODUCTION DEPLOY
 
 | Attribute | Value |
 |-----------|-------|
-| **Agent** | `devops-engineer` |
+| **Role** | `devops-engineer` |
 | **Goal** | Execute production deployment |
 
-### ⚡ TIERED EXECUTION
-
-**TIER 1 (MANDATORY when tool exists):**
-> Invoke runSubagent for `devops-engineer`. Context: ISOLATED.
+### Delegation
 
-**TIER 2 (FALLBACK on system error only):**
-> Load `{AGENTS_PATH}/devops-engineer.md`
-> EMBODY [devops-engineer] — Requires logged system error justification.
+> Task(subagent_type="general-purpose", prompt="You are a devops-engineer. Execute production deployment. Exit when deployment is successful and zero-downtime is achieved (if applicable).", description="devops-engineer: Execute production deployment")
 
 **Exit Criteria:**
 
@@ -117,21 +73,16 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 
 ---
 
-## 🎭 Phase 4: POST-DEPLOY VERIFICATION
+## Phase 4: POST-DEPLOY VERIFICATION
 
 | Attribute | Value |
 |-----------|-------|
-| **Agent** | `devops-engineer` |
+| **Role** | `devops-engineer` |
 | **Goal** | Production health verification |
 
-### ⚡ TIERED EXECUTION
-
-**TIER 1 (MANDATORY when tool exists):**
-> Invoke runSubagent for `devops-engineer`. Context: ISOLATED.
+### Delegation
 
-**TIER 2 (FALLBACK on system error only):**
-> Load `{AGENTS_PATH}/devops-engineer.md`
-> EMBODY [devops-engineer] — Requires logged system error justification.
+> Task(subagent_type="general-purpose", prompt="You are a devops-engineer. Verify production health after deployment. Exit when health checks pass, core paths are verified, and monitoring is normal.", description="devops-engineer: Production health verification")
 
 **Exit Criteria:**
 
@@ -155,6 +106,6 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 
 Present deployment result with:
 
-1. ✅ **Success** — Production deployed
-2. ⏪ **Rollback** → `/deploy:rollback` if issues
-3. 📊 **Monitor** — Watch dashboards
+1. **Success** — Production deployed
+2. **Rollback** → `/deploy:rollback` if issues
+3. **Monitor** — Watch dashboards

package/merged-commands/deploy/rollback.md

@@ -1,5 +1,5 @@
 ---
-description: ⏪ Deploy Rollback — Revert to previous deployment
+description: Deploy Rollback — Revert to previous deployment
 version: "1.0"
 category: operations
 execution-mode: execute
@@ -11,55 +11,21 @@ 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 PROTOCOL (MANDATORY)
-
-> **Reference**: `{RULES_PATH}/ADAPTIVE-EXECUTION.md`
-
-```yaml
-tiered_execution:
-  principle: "Sub-agent FIRST (Tier 1). EMBODY ONLY on system failure (Tier 2)."
-  for_each_phase:
-    TIER_1_MANDATORY: "IF tool exists → MUST use SUB_AGENT_DELEGATION"
-    TIER_2_FALLBACK: "ONLY on system error—NOT complexity/preference/speed"
-  anti_lazy_fallback:
-    - ❌ NEVER use Tier 2 when Tier 1 tool is available
-    - ✅ ALWAYS attempt Tier 1 first when tool exists
-```
+## Execution
+One phase at a time, sequential. Each phase must complete before next begins.
 
 ---
 
-## ⛔ 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).
-
----
-
-## 🎭 Phase 1: ASSESS SITUATION
+## Phase 1: ASSESS SITUATION
 
 | Attribute | Value |
 |-----------|-------|
-| **Agent** | `devops-engineer` |
+| **Role** | `devops-engineer` |
 | **Goal** | Identify rollback target |
 
-### ⚡ TIERED EXECUTION
-
-**TIER 1 (MANDATORY when tool exists):**
-> Invoke runSubagent for `devops-engineer`. Context: ISOLATED.
+### Delegation
 
-**TIER 2 (FALLBACK on system error only):**
-> Load `{AGENTS_PATH}/devops-engineer.md`
-> EMBODY [devops-engineer] — Requires logged system error justification.
+> Task(subagent_type="general-purpose", prompt="You are a devops-engineer. Identify the rollback target. Exit when current state is documented, rollback target is identified, and impact is assessed.", description="devops-engineer: Identify rollback target")
 
 **Exit Criteria:**
 
@@ -69,21 +35,16 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 
 ---
 
-## 🎭 Phase 2: EXECUTE ROLLBACK
+## Phase 2: EXECUTE ROLLBACK
 
 | Attribute | Value |
 |-----------|-------|
-| **Agent** | `devops-engineer` |
+| **Role** | `devops-engineer` |
 | **Goal** | Execute rollback procedure |
 
-### ⚡ TIERED EXECUTION
+### Delegation
 
-**TIER 1 (MANDATORY when tool exists):**
-> Invoke runSubagent for `devops-engineer`. Context: ISOLATED.
-
-**TIER 2 (FALLBACK on system error only):**
-> Load `{AGENTS_PATH}/devops-engineer.md`
-> EMBODY [devops-engineer] — Requires logged system error justification.
+> Task(subagent_type="general-purpose", prompt="You are a devops-engineer. Execute the rollback procedure. Exit when rollback is complete and previous version is deployed.", description="devops-engineer: Execute rollback procedure")
 
 **Exit Criteria:**
 
@@ -92,21 +53,16 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 
 ---
 
-## 🎭 Phase 3: VERIFICATION
+## Phase 3: VERIFICATION
 
 | Attribute | Value |
 |-----------|-------|
-| **Agent** | `devops-engineer` |
+| **Role** | `devops-engineer` |
 | **Goal** | Verify rollback success |
 
-### ⚡ TIERED EXECUTION
-
-**TIER 1 (MANDATORY when tool exists):**
-> Invoke runSubagent for `devops-engineer`. Context: ISOLATED.
+### Delegation
 
-**TIER 2 (FALLBACK on system error only):**
-> Load `{AGENTS_PATH}/devops-engineer.md`
-> EMBODY [devops-engineer] — Requires logged system error justification.
+> Task(subagent_type="general-purpose", prompt="You are a devops-engineer. Verify rollback success. Exit when health checks pass, previous functionality is restored, and issue is resolved.", description="devops-engineer: Verify rollback success")
 
 **Exit Criteria:**
 
@@ -116,21 +72,16 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 
 ---
 
-## 🎭 Phase 4: ROOT CAUSE ANALYSIS
+## Phase 4: ROOT CAUSE ANALYSIS
 
 | Attribute | Value |
 |-----------|-------|
-| **Agent** | `debugger` |
+| **Role** | `debugger` |
 | **Goal** | Document what went wrong |
 
-### ⚡ TIERED EXECUTION
-
-**TIER 1 (MANDATORY when tool exists):**
-> Invoke runSubagent for `debugger`. Context: ISOLATED.
+### Delegation
 
-**TIER 2 (FALLBACK on system error only):**
-> Load `{AGENTS_PATH}/debugger.md`
-> EMBODY [debugger] — Requires logged system error justification.
+> Task(subagent_type="general-purpose", prompt="You are a debugger. Document what went wrong with the deployment. Exit when failure is documented, root cause is identified, and prevention plan is noted.", description="debugger: Document what went wrong")
 
 **Exit Criteria:**
 
@@ -144,6 +95,6 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 
 Present rollback result with:
 
-1. ✅ **Rolled Back** — System stable
-2. 🐛 **Debug** → `/debug:hard` for root cause
-3. 📝 **Document** — Post-mortem documentation
+1. **Rolled Back** — System stable
+2. **Debug** → `/debug:hard` for root cause
+3. **Document** — Post-mortem documentation

package/merged-commands/deploy.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/design/3d.md

@@ -3,7 +3,7 @@ description: Create immersive interactive 3D designs with Three.js
 argument-hint: [tasks]
 ---
 
-Think hard to plan & start working on these tasks follow the Orchestration Protocol, Core Responsibilities, Subagents Team and Development Rules:
+Think hard to plan & start working on these tasks follow the Orchestration Protocol, Core Responsibilities, Task Agents Team and Development Rules:
 <tasks>$ARGUMENTS</tasks>
 
 ## Required Skills (Priority Order)
@@ -20,12 +20,12 @@ Think hard to plan & start working on these tasks follow the Orchestration Proto
    python3 .claude/skills/ui-ux-pro-max/scripts/search.py "immersive 3d" --domain style
    python3 .claude/skills/ui-ux-pro-max/scripts/search.py "animation" --domain ux
    ```
-1. Use `ui-ux-designer` subagent and `researcher` subagent to create a comprehensive 3D design plan following the progressive disclosure structure:
+1. Use a Task agent for UI/UX design and a Task agent for research to create a comprehensive 3D design plan following the progressive disclosure structure:
    - 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).
    - Keep every research markdown report concise (≤150 lines) while covering all requested topics and citations.
-2. Then use `ui-ux-designer` subagent to implement the plan step by step.
+2. Then use a Task agent for UI/UX design: Task(subagent_type="general-purpose", prompt="You are a ui-ux-designer. Implement the plan step by step.", description="Implement 3D design") to implement the plan step by step.
 3. Create immersive 3D experiences using Three.js with particle effects, custom shaders, and interactive elements.
 4. Leverage all available Gemini skills (ai-multimodal, ai-multimodal) for asset generation and validation.
 5. Report back to user with a summary of the changes and explain everything briefly, ask user to review the changes and approve them.

package/merged-commands/design/describe.md

@@ -16,7 +16,7 @@ Think hard to describe the design based on this screenshot/video:
 1. Use `ai-multimodal` skills to describe super details of the screenshot/video so the developer can implement it easily.
    - Be specific about design style, every element, elements' positions, every interaction, every animation, every transition, every color, every border, every icon, every font style, font size, font weight, every spacing, every padding, every margin, every size, every shape, every texture, every material, every light, every shadow, every reflection, every refraction, every blur, every glow, every image, background transparency, etc.
    - **IMPORTANT:** Try to predict the font name (Google Fonts) and font size in the given screenshot, don't just use Inter or Poppins.
-2. Use `ui-ux-designer` subagent to create a design implementation plan following the progressive disclosure structure so the result matches the screenshot/video:
+2. Use a Task agent for UI/UX design: Task(subagent_type="general-purpose", prompt="You are a ui-ux-designer. Create a design implementation plan following the progressive disclosure structure so the result matches the screenshot/video.", description="Create design plan") to create a design implementation plan following the progressive disclosure structure so the result matches the screenshot/video:
    - 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).

package/merged-commands/design/fast.md

@@ -3,7 +3,7 @@ description: Create a quick design
 argument-hint: [tasks]
 ---
 
-Think hard to plan & start working on these tasks follow the Orchestration Protocol, Core Responsibilities, Subagents Team and Development Rules: 
+Think hard to plan & start working on these tasks follow the Orchestration Protocol, Core Responsibilities, Task Agents Team and Development Rules: 
 <tasks>$ARGUMENTS</tasks>
 
 ## Required Skills (Priority Order)
@@ -20,7 +20,7 @@ Think hard to plan & start working on these tasks follow the Orchestration Proto
    python3 .claude/skills/ui-ux-pro-max/scripts/search.py "<mood>" --domain typography
    python3 .claude/skills/ui-ux-pro-max/scripts/search.py "<industry>" --domain color
    ```
-2. Use `ui-ux-designer` subagent to start the design process.
+2. Use a Task agent for UI/UX design: Task(subagent_type="general-purpose", prompt="You are a ui-ux-designer. Start the design process.", description="Design") to start the design process.
 3. If user doesn't specify, create the design in pure HTML/CSS/JS.
 4. Report back to user with a summary of the changes and explain everything briefly, ask user to review the changes and approve them.
 5. If user approves the changes, update the `./docs/design-guidelines.md` docs if needed.

package/merged-commands/design/good.md

@@ -3,7 +3,7 @@ description: Create an immersive design
 argument-hint: [tasks]
 ---
 
-Think hard to plan & start working on these tasks follow the Orchestration Protocol, Core Responsibilities, Subagents Team and Development Rules: 
+Think hard to plan & start working on these tasks follow the Orchestration Protocol, Core Responsibilities, Task Agents Team and Development Rules: 
 <tasks>$ARGUMENTS</tasks>
 
 ## Required Skills (Priority Order)
@@ -20,8 +20,8 @@ Think hard to plan & start working on these tasks follow the Orchestration Proto
    python3 .claude/skills/ui-ux-pro-max/scripts/search.py "<mood>" --domain typography
    python3 .claude/skills/ui-ux-pro-max/scripts/search.py "<industry>" --domain color
    ```
-2. Use `researcher` subagent to research about design style, trends, fonts, colors, border, spacing, elements' positions, etc.
-3. Use `ui-ux-designer` subagent to implement the design step by step based on the research.
+2. Use a Task agent for research: Task(subagent_type="general-purpose", prompt="You are a researcher. Research about design style, trends, fonts, colors, border, spacing, elements' positions, etc.", description="Research design") to research about design style, trends, fonts, colors, border, spacing, elements' positions, etc.
+3. Use a Task agent for UI/UX design: Task(subagent_type="general-purpose", prompt="You are a ui-ux-designer. Implement the design step by step based on the research.", description="Implement design") to implement the design step by step based on the research.
 4. If user doesn't specify, create the design in pure HTML/CSS/JS.
 5. Report back to user with a summary of the changes and explain everything briefly, ask user to review the changes and approve them.
 6. If user approves the changes, update the `./docs/design-guidelines.md` docs if needed.

package/merged-commands/design/hard.md

@@ -13,35 +13,6 @@ 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 PROTOCOL (MANDATORY)
-
-> **Reference**: `{RULES_PATH}/ADAPTIVE-EXECUTION.md`
-
-```yaml
-tiered_execution:
-  principle: "Sub-agent FIRST (Tier 1). EMBODY ONLY on system failure (Tier 2)."
-  for_each_phase:
-    TIER_1_MANDATORY: "IF tool exists → MUST use SUB_AGENT_DELEGATION"
-    TIER_2_FALLBACK: "ONLY on system error—NOT complexity/preference/speed"
-  anti_lazy_fallback:
-    - ❌ NEVER use Tier 2 when Tier 1 tool is available
-    - ✅ ALWAYS attempt Tier 1 first when tool exists
-```
-
----
-
 ## ⚠️ CRITICAL: DELIVERABLE FILE RULES
 
 ```yaml
@@ -59,29 +30,16 @@ All files in `./reports/` → English only.
 
 ---
 
-## ⛔ 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).
-
----
-
 ## 🎭 Phase 1: REQUIREMENTS DISCOVERY
 
 | Attribute | Value                       |
 | --------- | --------------------------- |
-| **Agent** | `brainstormer`              |
+| **Role**  | `brainstormer`              |
 | **Goal**  | Clarify design requirements |
 
-### ⚡ TIERED EXECUTION
-
-**TIER 1 (MANDATORY when tool exists):**
-
-> Invoke runSubagent for `brainstormer`. Context: ISOLATED.
-
-**TIER 2 (FALLBACK on system error only):**
+### Delegation
 
-> Load `{AGENTS_PATH}/brainstormer.md`
-> EMBODY [brainstormer] — Requires logged system error justification.
+> Task(subagent_type="general-purpose", prompt="You are a brainstormer. Clarify design requirements. [See exit criteria below]", description="brainstormer")
 
 **Exit Criteria:**
 
@@ -96,19 +54,12 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 
 | Attribute | Value                           |
 | --------- | ------------------------------- |
-| **Agent** | `researcher`                    |
+| **Role**  | `researcher`                    |
 | **Goal**  | Research design patterns and UX |
 
-### ⚡ TIERED EXECUTION
+### Delegation
 
-**TIER 1 (MANDATORY when tool exists):**
-
-> Invoke runSubagent for `researcher`. Context: ISOLATED.
-
-**TIER 2 (FALLBACK on system error only):**
-
-> Load `{AGENTS_PATH}/researcher.md`
-> EMBODY [researcher] — Requires logged system error justification.
+> Task(subagent_type="general-purpose", prompt="You are a researcher. Research design patterns and UX. [See exit criteria below]", description="researcher")
 
 **Exit Criteria:**
 
@@ -122,19 +73,12 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 
 | Attribute | Value                      |
 | --------- | -------------------------- |
-| **Agent** | `scouter`                  |
+| **Role**  | `scouter`                  |
 | **Goal**  | Map existing design system |
 
-### ⚡ TIERED EXECUTION
-
-**TIER 1 (MANDATORY when tool exists):**
+### Delegation
 
-> Invoke runSubagent for `scouter`. Context: ISOLATED.
-
-**TIER 2 (FALLBACK on system error only):**
-
-> Load `{AGENTS_PATH}/scouter.md`
-> EMBODY [scouter] — Requires logged system error justification.
+> Task(subagent_type="general-purpose", prompt="You are a scouter. Map existing design system. [See exit criteria below]", description="scouter")
 
 **Exit Criteria:**
 
@@ -149,19 +93,12 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 
 | Attribute | Value                  |
 | --------- | ---------------------- |
-| **Agent** | `designer`             |
+| **Role**  | `designer`             |
 | **Goal**  | Full design with specs |
 
-### ⚡ TIERED EXECUTION
-
-**TIER 1 (MANDATORY when tool exists):**
-
-> Invoke runSubagent for `designer`. Context: ISOLATED.
+### Delegation
 
-**TIER 2 (FALLBACK on system error only):**
-
-> Load `{AGENTS_PATH}/designer.md`
-> EMBODY [designer] — Requires logged system error justification.
+> Task(subagent_type="general-purpose", prompt="You are a designer. Create full design with specs. [See exit criteria below]", description="designer")
 
 **Exit Criteria:**
 
@@ -177,19 +114,12 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 
 | Attribute | Value                 |
 | --------- | --------------------- |
-| **Agent** | `reviewer`            |
+| **Role**  | `reviewer`            |
 | **Goal**  | Review design quality |
 
-### ⚡ TIERED EXECUTION
-
-**TIER 1 (MANDATORY when tool exists):**
-
-> Invoke runSubagent for `reviewer`. Context: ISOLATED.
-
-**TIER 2 (FALLBACK on system error only):**
+### Delegation
 
-> Load `{AGENTS_PATH}/reviewer.md`
-> EMBODY [reviewer] — Requires logged system error justification.
+> Task(subagent_type="general-purpose", prompt="You are a reviewer. Review design quality. [See exit criteria below]", description="reviewer")
 
 **Exit Criteria:**
 

package/merged-commands/design/screenshot.md

@@ -15,7 +15,7 @@ Think hard to plan & start designing follow exactly this screenshot:
 ## Workflow:
 1. Use `ai-multimodal` skills to describe super details of the screenshot (design style, trends, fonts, colors, border, spacing, elements' positions, size, shape, texture, material, light, shadow, reflection, refraction, blur, glow, image, background transparency, transition, etc.)
    - **IMPORTANT:** Try to predict the font name (Google Fonts) and font size in the given screenshot, don't just use Inter or Poppins.
-2. Use `ui-ux-designer` subagent to create a design plan following the progressive disclosure structure so the final result matches the screenshot:
+2. Use a Task agent for UI/UX design: Task(subagent_type="general-purpose", prompt="You are a ui-ux-designer. Create a design plan following the progressive disclosure structure so the final result matches the screenshot.", description="Create design plan") to create a design plan following the progressive disclosure structure so the final result matches the screenshot:
    - 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).

package/merged-commands/design/video.md

@@ -15,7 +15,7 @@ Think hard to plan & start designing follow exactly this video:
 ## Workflow:
 1. Use `ai-multimodal` skills to describe super details of the video: be specific about describing every element, every interaction, every animation, every transition, every color, every font, every border, every spacing, every size, every shape, every texture, every material, every light, every shadow, every reflection, every refraction, every blur, every glow, every image, background transparency, etc.
    - **IMPORTANT:** Try to predict the font name (Google Fonts) and font size in the given video, don't just use Inter or Poppins.
-2. Use `ui-ux-designer` subagent to create a design plan following the progressive disclosure structure so the final result matches the video:
+2. Use a Task agent for UI/UX design: Task(subagent_type="general-purpose", prompt="You are a ui-ux-designer. Create a design plan following the progressive disclosure structure so the final result matches the video.", description="Create design plan") to create a design plan following the progressive disclosure structure so the final result matches the video:
    - 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).

package/merged-commands/design.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/doc-coauthoring.md

@@ -250,7 +250,7 @@ Explain that testing will now occur to see if the document actually works for re
 
 ### Testing Approach
 
-**If access to sub-agents is available (e.g., in Claude Code):**
+**If access to Task agents is available (e.g., in Claude Code):**
 
 Perform the testing directly without user involvement.
 
@@ -260,11 +260,11 @@ Announce intention to predict what questions readers might ask when trying to di
 
 Generate 5-10 questions that readers would realistically ask.
 
-### Step 2: Test with Sub-Agent
+### Step 2: Test with Task Agent
 
 Announce that these questions will be tested with a fresh Claude instance (no context from this conversation).
 
-For each question, invoke a sub-agent with just the document content and the question.
+For each question, invoke a Task agent with just the document content and the question.
 
 Summarize what Reader Claude got right/wrong for each question.
 
@@ -272,7 +272,7 @@ Summarize what Reader Claude got right/wrong for each question.
 
 Announce additional checks will be performed.
 
-Invoke sub-agent to check for ambiguity, false assumptions, contradictions.
+Invoke Task agent to check for ambiguity, false assumptions, contradictions.
 
 Summarize any issues found.
 
@@ -289,7 +289,7 @@ Loop back to refinement for problematic sections.
 
 ---
 
-**If no access to sub-agents (e.g., claude.ai web interface):**
+**If no access to Task agents (e.g., claude.ai web interface):**
 
 The user will need to do the testing manually.
 

package/merged-commands/docker-expert.md

@@ -21,7 +21,7 @@ You are an advanced Docker containerization expert with comprehensive, practical
    - Database containerization with complex persistence → database-expert
 
    Example to output:
-   "This requires Kubernetes orchestration expertise. Please invoke: 'Use the kubernetes-expert subagent.' Stopping here."
+   "This requires Kubernetes orchestration expertise. Please invoke: 'Use the kubernetes-expert Task agent.' Stopping here."
 
 1. Analyze container setup comprehensively: