@ngxtm/devkit 3.18.0 → 3.20.0

package/merged-commands/docs/audit.md

@@ -1,5 +1,5 @@
 ---
-description: 🔒 Audit Docs — Generate 4 security and compliance documentation files
+description: Audit Docs — Generate 4 security and compliance documentation files
 version: "1.0"
 category: documentation
 execution-mode: execute
@@ -13,42 +13,13 @@ 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
-```
-
----
-
-## 📦 DELIVERABLES (REQUIRED — ALL 4 FILES)
+## DELIVERABLES (REQUIRED — ALL 4 FILES)
 
 > [!CAUTION]
 > **MUST CREATE ALL 4 FILES**. Incomplete = FAILED execution.
 
-> **⛔ DOCUMENT LANGUAGE — NON-NEGOTIABLE**  
-> Every file under `./documents/` must be written in **English only**. Do not use the user's language (e.g. Vietnamese) for file content. (ORCHESTRATION-LAWS § LAW 6.)
+> **DOCUMENT LANGUAGE — NON-NEGOTIABLE**
+> Every file under `./documents/` must be written in **English only**. Do not use the user's language (e.g. Vietnamese) for file content.
 
 | File                                         | Purpose                          |
 | -------------------------------------------- | -------------------------------- |
@@ -59,29 +30,21 @@ tiered_execution:
 
 ---
 
-## ⛔ 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: SECURITY ANALYSIS
+## Phase 1: SECURITY ANALYSIS
 
 | Attribute | Value                        |
 | --------- | ---------------------------- |
-| **Agent** | `security-engineer`          |
+| **Role**  | `security-engineer`          |
 | **Goal**  | Complete security assessment |
 
-### ⚡ TIERED EXECUTION
-
-**TIER 1 (MANDATORY when tool exists):**
+### Delegation
 
-> 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 a complete security assessment. Exit when vulnerabilities are identified, OWASP checklist is complete, and risk assessment is done.", description="security-engineer: Complete security assessment")
 
 **Exit Criteria:**
 
@@ -91,23 +54,16 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 
 ---
 
-## 🎭 Phase 2: CODEBASE SCAN
+## Phase 2: CODEBASE SCAN
 
 | Attribute | Value                              |
 | --------- | ---------------------------------- |
-| **Agent** | `scouter`                          |
+| **Role**  | `scouter`                          |
 | **Goal**  | Map data flows and sensitive areas |
 
-### ⚡ 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 data flows and sensitive areas in the codebase. Exit when data flows are mapped, sensitive data is identified, and integration points are cataloged.", description="scouter: Map data flows and sensitive areas")
 
 **Exit Criteria:**
 
@@ -117,23 +73,16 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 
 ---
 
-## 🎭 Phase 3: GENERATE ALL 4 DOCUMENTS
+## Phase 3: GENERATE ALL 4 DOCUMENTS
 
 | Attribute | Value                                                                                          |
 | --------- | ---------------------------------------------------------------------------------------------- |
-| **Agent** | `docs-manager`                                                                                 |
+| **Role**  | `docs-manager`                                                                                 |
 | **Goal**  | Create all 4 audit documentation files in **English only** (no user-language content in files) |
 
-### ⚡ TIERED EXECUTION
-
-**TIER 1 (MANDATORY when tool exists):**
-
-> Invoke runSubagent for `docs-manager`. Context: ISOLATED.
-
-**TIER 2 (FALLBACK on system error only):**
+### Delegation
 
-> Load `{AGENTS_PATH}/docs-manager.md`
-> EMBODY [docs-manager] — Requires logged system error justification.
+> Task(subagent_type="general-purpose", prompt="You are a docs-manager. Create all 4 audit documentation files in English only: audit-security.md, audit-compliance.md, audit-dataflow.md, audit-recommendations.md. Exit when all 4 files are created.", description="docs-manager: Create all 4 audit documentation files")
 
 **Exit Criteria:**
 
@@ -144,16 +93,16 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 
 ---
 
-## ✅ VERIFICATION
+## VERIFICATION
 
 Before completion, verify ALL 4 files exist:
 
 ```
 ./documents/audit/
-├── ✅ audit-security.md
-├── ✅ audit-compliance.md
-├── ✅ audit-dataflow.md
-└── ✅ audit-recommendations.md
+├── audit-security.md
+├── audit-compliance.md
+├── audit-dataflow.md
+└── audit-recommendations.md
 ```
 
 ---
@@ -162,6 +111,6 @@ Before completion, verify ALL 4 files exist:
 
 Report status:
 
-1. ✅ **Complete** — All 4 audit docs created
-2. ❌ **Incomplete** — List missing files
-3. 🔒 **Follow-up** — Address critical findings
+1. **Complete** — All 4 audit docs created
+2. **Incomplete** — List missing files
+3. **Follow-up** — Address critical findings

package/merged-commands/docs/business.md

@@ -1,5 +1,5 @@
 ---
-description: 📊 Business Docs — Generate 4 business documentation files
+description: Business Docs — Generate 4 business documentation files
 version: "1.0"
 category: documentation
 execution-mode: execute
@@ -13,42 +13,13 @@ 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
-```
-
----
-
-## 📦 DELIVERABLES (REQUIRED — ALL 4 FILES)
+## DELIVERABLES (REQUIRED — ALL 4 FILES)
 
 > [!CAUTION]
 > **MUST CREATE ALL 4 FILES**. Incomplete = FAILED execution.
 
-> **⛔ DOCUMENT LANGUAGE — NON-NEGOTIABLE**  
-> Every file under `./documents/` must be written in **English only**. Do not use the user's language (e.g. Vietnamese) for file content. (ORCHESTRATION-LAWS § LAW 6.)
+> **DOCUMENT LANGUAGE — NON-NEGOTIABLE**
+> Every file under `./documents/` must be written in **English only**. Do not use the user's language (e.g. Vietnamese) for file content.
 
 | File                                         | Purpose                       |
 | -------------------------------------------- | ----------------------------- |
@@ -59,29 +30,21 @@ tiered_execution:
 
 ---
 
-## ⛔ 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: CODEBASE & REQUIREMENTS ANALYSIS
+## Phase 1: CODEBASE & REQUIREMENTS ANALYSIS
 
 | Attribute | Value                                |
 | --------- | ------------------------------------ |
-| **Agent** | `scouter`                            |
+| **Role**  | `scouter`                            |
 | **Goal**  | Identify business logic and features |
 
-### ⚡ 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. Identify business logic and features in the codebase. Exit when business logic is identified, features are cataloged, and domain terms are noted.", description="scouter: Identify business logic and features")
 
 **Exit Criteria:**
 
@@ -91,23 +54,16 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 
 ---
 
-## 🎭 Phase 2: BUSINESS ANALYSIS
+## Phase 2: BUSINESS ANALYSIS
 
 | Attribute | Value                    |
 | --------- | ------------------------ |
-| **Agent** | `business-analyst`       |
+| **Role**  | `business-analyst`       |
 | **Goal**  | Analyze business context |
 
-### ⚡ TIERED EXECUTION
-
-**TIER 1 (MANDATORY when tool exists):**
+### Delegation
 
-> Invoke runSubagent for `business-analyst`. Context: ISOLATED.
-
-**TIER 2 (FALLBACK on system error only):**
-
-> Load `{AGENTS_PATH}/business-analyst.md`
-> EMBODY [business-analyst] — Requires logged system error justification.
+> Task(subagent_type="general-purpose", prompt="You are a business-analyst. Analyze business context. Exit when business goals are understood, stakeholders are identified, and workflows are mapped.", description="business-analyst: Analyze business context")
 
 **Exit Criteria:**
 
@@ -117,23 +73,16 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 
 ---
 
-## 🎭 Phase 3: GENERATE ALL 4 DOCUMENTS
+## Phase 3: GENERATE ALL 4 DOCUMENTS
 
 | Attribute | Value                                                                                             |
 | --------- | ------------------------------------------------------------------------------------------------- |
-| **Agent** | `docs-manager`                                                                                    |
+| **Role**  | `docs-manager`                                                                                    |
 | **Goal**  | Create all 4 business documentation files in **English only** (no user-language content in files) |
 
-### ⚡ TIERED EXECUTION
-
-**TIER 1 (MANDATORY when tool exists):**
-
-> Invoke runSubagent for `docs-manager`. Context: ISOLATED.
-
-**TIER 2 (FALLBACK on system error only):**
+### Delegation
 
-> Load `{AGENTS_PATH}/docs-manager.md`
-> EMBODY [docs-manager] — Requires logged system error justification.
+> Task(subagent_type="general-purpose", prompt="You are a docs-manager. Create all 4 business documentation files in English only: business-prd.md, business-features.md, business-workflows.md, business-glossary.md. Exit when all 4 files are created.", description="docs-manager: Create all 4 business documentation files")
 
 **Exit Criteria:**
 
@@ -144,16 +93,16 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 
 ---
 
-## ✅ VERIFICATION
+## VERIFICATION
 
 Before completion, verify ALL 4 files exist:
 
 ```
 ./documents/business/
-├── ✅ business-prd.md
-├── ✅ business-features.md
-├── ✅ business-workflows.md
-└── ✅ business-glossary.md
+├── business-prd.md
+├── business-features.md
+├── business-workflows.md
+└── business-glossary.md
 ```
 
 ---
@@ -162,6 +111,6 @@ Before completion, verify ALL 4 files exist:
 
 Report status:
 
-1. ✅ **Complete** — All 4 business docs created
-2. ❌ **Incomplete** — List missing files
-3. 📝 **Continue** → `/docs:audit` for audit docs
+1. **Complete** — All 4 business docs created
+2. **Incomplete** — List missing files
+3. **Continue** → `/docs:audit` for audit docs

package/merged-commands/docs/core.md

@@ -1,5 +1,5 @@
 ---
-description: 💻 Core Docs — Generate 5 essential technical documentation files
+description: Core Docs — Generate 5 essential technical documentation files
 version: "1.0"
 category: documentation
 execution-mode: execute
@@ -13,42 +13,13 @@ 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
-```
-
----
-
-## 📦 DELIVERABLES (REQUIRED — ALL 5 FILES)
+## DELIVERABLES (REQUIRED — ALL 5 FILES)
 
 > [!CAUTION]
 > **MUST CREATE ALL 5 FILES**. Incomplete = FAILED execution.
 
-> **⛔ DOCUMENT LANGUAGE — NON-NEGOTIABLE**  
-> Every file under `./documents/` must be written in **English only**. Headings, body text, tables, and lists must be in English. Do not use the user's language (e.g. Vietnamese) for file content. Chat/UI may follow user language; document files do not. (ORCHESTRATION-LAWS § LAW 6.)
+> **DOCUMENT LANGUAGE — NON-NEGOTIABLE**
+> Every file under `./documents/` must be written in **English only**. Headings, body text, tables, and lists must be in English. Do not use the user's language (e.g. Vietnamese) for file content. Chat/UI may follow user language; document files do not.
 
 | File                                    | Purpose                                                       |
 | --------------------------------------- | ------------------------------------------------------------- |
@@ -58,7 +29,7 @@ tiered_execution:
 | `./documents/knowledge-source-base.md`  | Directory structure, file purposes, entry points, key modules |
 | `./documents/knowledge-standards.md`    | Code style, naming conventions, commit format, guidelines     |
 
-### 📋 File Purpose Details
+### File Purpose Details
 
 | File | AI Uses It For | Key Sections |
 |------|----------------|--------------|
@@ -70,29 +41,21 @@ tiered_execution:
 
 ---
 
-## ⛔ 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: CODEBASE ANALYSIS
+## Phase 1: CODEBASE ANALYSIS
 
 | Attribute | Value                                     |
 | --------- | ----------------------------------------- |
-| **Agent** | `scouter`                                 |
+| **Role**  | `scouter`                                 |
 | **Goal**  | Scan entire project structure and content |
 
-### ⚡ TIERED EXECUTION
-
-**TIER 1 (MANDATORY when tool exists):**
-
-> Invoke runSubagent for `scouter`. Context: ISOLATED.
+### Delegation
 
-**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. Scan the entire project structure and content. List all directories and files, identify tech stack from package.json/config files, map dependencies and relationships, and note patterns and conventions used. Exit when project structure is mapped, tech stack is identified, and key files are located.", description="scouter: Scan entire project structure and content")
 
 **Actions**:
 
@@ -109,23 +72,16 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 
 ---
 
-## 🎭 Phase 2: GENERATE ALL 5 DOCUMENTS
+## Phase 2: GENERATE ALL 5 DOCUMENTS
 
 | Attribute | Value                                                                                                           |
 | --------- | --------------------------------------------------------------------------------------------------------------- |
-| **Agent** | `docs-manager`                                                                                                  |
+| **Role**  | `docs-manager`                                                                                                  |
 | **Goal**  | Create all 5 documentation files in **English only** (headings, body, tables—no user-language content in files) |
 
-### ⚡ TIERED EXECUTION
-
-**TIER 1 (MANDATORY when tool exists):**
-
-> Invoke runSubagent for `docs-manager`. Context: ISOLATED.
-
-**TIER 2 (FALLBACK on system error only):**
+### Delegation
 
-> Load `{AGENTS_PATH}/docs-manager.md`
-> EMBODY [docs-manager] — Requires logged system error justification.
+> Task(subagent_type="general-purpose", prompt="You are a docs-manager. Create all 5 documentation files in English only: knowledge-overview.md, knowledge-architecture.md, knowledge-domain.md, knowledge-source-base.md, knowledge-standards.md. Exit when all 5 files are created.", description="docs-manager: Create all 5 documentation files")
 
 **Exit Criteria:**
 
@@ -137,17 +93,17 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 
 ---
 
-## ✅ VERIFICATION
+## VERIFICATION
 
 Before completion, verify ALL 5 files exist:
 
 ```
 ./documents/
-├── ✅ knowledge-overview.md
-├── ✅ knowledge-architecture.md
-├── ✅ knowledge-domain.md
-├── ✅ knowledge-source-base.md
-└── ✅ knowledge-standards.md
+├── knowledge-overview.md
+├── knowledge-architecture.md
+├── knowledge-domain.md
+├── knowledge-source-base.md
+└── knowledge-standards.md
 ```
 
 ---
@@ -156,6 +112,6 @@ Before completion, verify ALL 5 files exist:
 
 Report status:
 
-1. ✅ **Complete** — All 5 core docs created
-2. ❌ **Incomplete** — List missing files
-3. 📝 **Continue** → `/docs:business` for business docs
+1. **Complete** — All 5 core docs created
+2. **Incomplete** — List missing files
+3. **Continue** → `/docs:business` for business docs

package/merged-commands/docs/init.md

@@ -6,16 +6,16 @@ description: ⚡⚡⚡⚡ Analyze the codebase and create initial documentation
 
 1. Scan the codebase and calculate the number of files with LOC in each directory (skip credentials, cache or external modules directories, such as `.claude`, `.opencode`, `.git`, `tests`, `node_modules`, `__pycache__`, `secrets`, etc.)
 2. Target directories **that actually exist** - adapt to project structure, don't hardcode paths
-3. Main agent spawns multiple `scout` subagents via Task tool:
-   - Write a detailed instructions prompt for each scout subagent with exact directories or files it should read
-   - Each scout subagent has less than 200K tokens of context window
-   - Amount of scouts depends on the current system resources available and project size in step 1
-   - Each scout subagent must return a detailed summary report to a main agent
-5. Main agent merges scout reports into context summary and delegate to `docs-manager` agent to update documentation (next phase)
+3. Main agent spawns multiple Task agents for scouting via Task tool: Task(subagent_type="general-purpose", prompt="You are a scout. Read and analyze these directories...", description="Scout [area]")
+   - Write a detailed instructions prompt for each Task agent with exact directories or files it should read
+   - Each Task agent has less than 200K tokens of context window
+   - Amount of Task agents depends on the current system resources available and project size in step 1
+   - Each Task agent must return a detailed summary report to a main agent
+5. Main agent merges scout reports into context summary and delegate to Task agent for docs management to update documentation (next phase)
 
-## Phase 2: Documentation Creation (docs-manager Agent)
+## Phase 2: Documentation Creation (Task Agent for Docs Management)
 
-Pass the gathered file list to `docs-manager` agent to create initial documentation:
+Pass the gathered file list to Task agent for docs management to create initial documentation: Task(subagent_type="general-purpose", prompt="You are a docs-manager. Create initial documentation...", description="Create documentation")
 - `README.md`: Update README with initial documentation (keep it under 300 lines)
 - `docs/project-overview-pdr.md`: Project overview and PDR (Product Development Requirements)
 - `docs/codebase-summary.md`: Codebase summary

package/merged-commands/docs/update.md

@@ -6,25 +6,25 @@ description: ⚡⚡⚡ Analyze the codebase and update documentation
 
 1. Scan the codebase and calculate the number of files with LOC in each directory (skip credentials, cache or external modules directories, such as `.claude`, `.opencode`, `.git`, `tests`, `node_modules`, `__pycache__`, `secrets`, etc.)
 2. Target directories **that actually exist** - adapt to project structure, don't hardcode paths
-3. Main agent spawns multiple `scout` subagents via Task tool:
-   - Write a detailed instructions prompt for each scout subagent with exact directories or files it should read
-   - Each scout subagent has less than 200K tokens of context window
-   - Amount of scouts depends on the current system resources available and project size in step 1
-   - Each scout subagent must return a detailed summary report to a main agent
-5. Main agent merges scout reports into context summary and delegate to `docs-manager` agent to update documentation (next phase)
+3. Main agent spawns multiple Task agents for scouting via Task tool: Task(subagent_type="general-purpose", prompt="You are a scout. Read and analyze these directories...", description="Scout [area]")
+   - Write a detailed instructions prompt for each Task agent with exact directories or files it should read
+   - Each Task agent has less than 200K tokens of context window
+   - Amount of Task agents depends on the current system resources available and project size in step 1
+   - Each Task agent must return a detailed summary report to a main agent
+5. Main agent merges scout reports into context summary and delegate to Task agent for docs management to update documentation (next phase)
 
 ## Phase 1.5: Parallel Documentation Reading
 
-**You (main agent) must spawn readers** - subagents cannot spawn subagents.
+**You (main agent) must spawn readers** - Task agents cannot spawn Task agents.
 
 1. Count docs: `ls docs/*.md 2>/dev/null | wc -l`
 2. Get LOC: `wc -l docs/*.md 2>/dev/null | sort -rn`
 3. Strategy:
    - 1-3 files: Skip parallel reading, docs-manager reads directly
-   - 4-6 files: Spawn 2-3 `Explore` agents
-   - 7+ files: Spawn 4-5 `Explore` agents (max 5)
-4. Distribute files by LOC (larger files get dedicated agent)
-5. Each agent prompt: "Read these docs, extract: purpose, key sections, areas needing update. Files: {list}"
+   - 4-6 files: Spawn 2-3 Task agents for exploration: Task(subagent_type="general-purpose", prompt="You are an explorer. Read these docs...", description="Explore docs")
+   - 7+ files: Spawn 4-5 Task agents for exploration (max 5)
+4. Distribute files by LOC (larger files get dedicated Task agent)
+5. Each Task agent prompt: "Read these docs, extract: purpose, key sections, areas needing update. Files: {list}"
 6. Merge results into context for docs-manager
 
 ### Workload Distribution Example
@@ -35,9 +35,9 @@ description: ⚡⚡⚡ Analyze the codebase and update documentation
 | 2 | system-architecture.md (400), code-standards.md (300) | 700 |
 | 3 | project-overview-pdr.md (500), project-roadmap.md (200) | 700 |
 
-## Phase 2: Documentation Update (docs-manager Agent)
+## Phase 2: Documentation Update (Task Agent for Docs Management)
 
-Pass the gathered file list to `docs-manager` agent to update documentation:
+Pass the gathered file list to Task agent for docs management to update documentation: Task(subagent_type="general-purpose", prompt="You are a docs-manager. Update documentation...", description="Update documentation")
 - `README.md`: Update README (keep it under 300 lines)
 - `docs/project-overview-pdr.md`: Update project overview and PDR (Product Development Requirements)
 - `docs/codebase-summary.md`: Update codebase summary

package/merged-commands/docs.md

@@ -13,18 +13,6 @@ execution-mode: execute
 
 ---
 
-## 🛑 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 (e.g. docs/core.md), and execute it.
-
----
-
 ## ⚠️ EXECUTION RULES (NON-NEGOTIABLE)
 
 > [!CAUTION]

package/merged-commands/error-debugging-multi-agent-review.md

@@ -59,7 +59,7 @@ The Multi-Agent Review Tool leverages a distributed, specialized agent network t
 - **Dynamic Agent Matching**:
   - Analyze input characteristics
   - Select most appropriate agent types
-  - Configure specialized sub-agents dynamically
+  - Configure specialized Task agents dynamically
 - **Expertise Routing**:
   ```python
   def route_agents(code_context):

package/merged-commands/error-diagnostics-smart-debug.md

@@ -39,7 +39,7 @@ Parse for:
 ## Workflow
 
 ### 1. Initial Triage
-Use Task tool (subagent_type="debugger") for AI-powered analysis:
+Use Task tool (subagent_type="general-purpose") for AI-powered analysis:
 - Error pattern recognition
 - Stack trace analysis with probable causes
 - Component dependency analysis

package/merged-commands/finishing-a-development-branch.md

@@ -195,7 +195,7 @@ git worktree remove <worktree-path>
 ## Integration
 
 **Called by:**
-- **subagent-driven-development** (Step 7) - After all tasks complete
+- **Task agent-driven-development** (Step 7) - After all tasks complete
 - **executing-plans** (Step 5) - After all batches complete
 
 **Pairs with:**

package/merged-commands/fix/ci.md

@@ -7,9 +7,9 @@ argument-hint: [github-actions-url]
 <url>$ARGUMENTS</url>
 
 ## Workflow
-1. Use `debugger` subagent to read the github actions logs with `gh` command, analyze and find the root cause of the issues and report back to main agent.
+1. Use a Task agent for debugging: Task(subagent_type="general-purpose", prompt="You are a debugger. Read the github actions logs with gh command, analyze and find the root cause of the issues and report back to main agent.", description="Analyze CI logs") to read the github actions logs with `gh` command, analyze and find the root cause of the issues and report back to main agent.
 2. Start implementing the fix based the reports and solutions.
-3. Use `tester` agent to test the fix and make sure it works, then report back to main agent.
+3. Use a Task agent for testing: Task(subagent_type="general-purpose", prompt="You are a tester. Test the fix and make sure it works, then report back to main agent.", description="Test fix") to test the fix and make sure it works, then report back to main agent.
 4. If there are issues or failed tests, repeat from step 2.
 5. After finishing, respond back to user with a summary of the changes and explain everything briefly, guide user to get started and suggest the next steps.