@ngxtm/devkit 3.18.0 → 3.20.0

package/merged-commands/brainstorm/hard.md

@@ -1,5 +1,5 @@
 ---
-description: ⚡⚡⚡ Deep Ideation — Research-backed exploration
+description: Deep Ideation — Research-backed exploration
 version: "1.0"
 category: planning
 execution-mode: execute
@@ -13,36 +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 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
+## CRITICAL: DELIVERABLE FILE RULES
 
 ```yaml
 deliverable_files:
@@ -61,29 +32,22 @@ All files in `./reports/` → English only.
 
 ---
 
-## ⛔ INCREMENTAL EXECUTION (MANDATORY)
+## Execution
 
-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).
+One phase at a time, sequential. Each phase must complete before next begins.
 
 ---
 
-## 🎭 Phase 1: REQUIREMENTS DISCOVERY
+## Phase 1: REQUIREMENTS DISCOVERY
 
 | Attribute | Value                           |
 | --------- | ------------------------------- |
-| **Agent** | `brainstormer`                  |
+| **Role**  | `brainstormer`                  |
 | **Goal**  | Deep requirements clarification |
 
-### ⚡ ADAPTIVE EXECUTION
+### Delegation
 
-**IF platform supports subagents:**
-
-> Delegate to `brainstormer` subagent. Do NOT read agent file directly.
-
-**ELSE (EMBODY fallback):**
-
-> Load `{AGENTS_PATH}/brainstormer.md`
-> EMBODY [brainstormer] — Apply methodology from agent file.
+> Task(subagent_type="general-purpose", prompt="You are a brainstormer. Perform deep requirements clarification using Socratic questioning and assumption surfacing. Exit when: requirements fully understood, stakeholders identified, constraints documented, success metrics defined.", description="brainstormer: Deep requirements clarification")
 
 **Exit Criteria:**
 
@@ -91,27 +55,19 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 - [ ] Stakeholders identified
 - [ ] Constraints documented
 - [ ] Success metrics defined
-- [ ] **METHODOLOGY CHECK**: Output aligns with `brainstormer` Thinking Protocol (Socratic questioning, assumption surfacing)
 
 ---
 
-## 🎭 Phase 2: RESEARCH
+## Phase 2: RESEARCH
 
 | Attribute | Value                                |
 | --------- | ------------------------------------ |
-| **Agent** | `researcher`                         |
+| **Role**  | `researcher`                         |
 | **Goal**  | Research best practices and patterns |
 
-### ⚡ TIERED EXECUTION
-
-**TIER 1 (MANDATORY when tool exists):**
-
-> Invoke runSubagent for `researcher`. Context: ISOLATED.
-
-**TIER 2 (FALLBACK on system error only):**
+### Delegation
 
-> Load `{AGENTS_PATH}/researcher.md`
-> EMBODY [researcher] — Requires logged system error justification.
+> Task(subagent_type="general-purpose", prompt="You are a researcher. Research best practices and patterns. CREATE ./reports/researchers/RESEARCH-{topic}.md with findings. Exit when: research file created, industry patterns researched, best practices documented, sources cited.", description="researcher: Research best practices and patterns")
 
 **MANDATORY**: CREATE `./reports/researchers/RESEARCH-{topic}.md`
 
@@ -121,55 +77,39 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 - [ ] Industry patterns researched
 - [ ] Best practices documented
 - [ ] Sources cited
-- [ ] **METHODOLOGY CHECK**: Output aligns with `researcher` Thinking Protocol (sources cited, cross-referenced, evidence-based)
 
 ---
 
-## 🎭 Phase 3: CODEBASE ANALYSIS
+## Phase 3: CODEBASE ANALYSIS
 
 | Attribute | Value                                  |
 | --------- | -------------------------------------- |
-| **Agent** | `scouter`                              |
+| **Role**  | `scouter`                              |
 | **Goal**  | Map existing architecture and patterns |
 
-### ⚡ TIERED EXECUTION
+### Delegation
 
-**TIER 1 (MANDATORY when tool exists):**
-
-> 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 architecture and patterns in the codebase. Exit when: architecture understood, existing patterns documented, integration points identified.", description="scouter: Map existing architecture and patterns")
 
 **Exit Criteria:**
 
 - [ ] Architecture understood
 - [ ] Existing patterns documented
 - [ ] Integration points identified
-- [ ] **METHODOLOGY CHECK**: Output aligns with `scouter` Thinking Protocol (file locations, patterns as constraints)
 
 ---
 
-## 🎭 Phase 4: SOLUTION SYNTHESIS
+## Phase 4: SOLUTION SYNTHESIS
 
 | Attribute        | Value                                                                                  |
 | ---------------- | -------------------------------------------------------------------------------------- |
-| **Agent**        | `brainstormer`                                                                         |
+| **Role**         | `brainstormer`                                                                         |
 | **Goal**         | Synthesize ideas with trade-off analysis                                               |
 | **Prerequisite** | READ `./reports/researchers/RESEARCH-{topic}.md` + `./reports/scouts/SCOUT-{topic}.md` |
 
-### ⚡ 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. READ all prior phase deliverables. Synthesize ideas with trade-off analysis. CREATE ./reports/brainstorms/BRAINSTORM-{topic}.md. Exit when: brainstorm file created, ideas synthesized incorporating research, trade-offs analyzed, recommendations provided.", description="brainstormer: Synthesize ideas with trade-off analysis")
 
 **MANDATORY**:
 
@@ -182,7 +122,6 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 - [ ] Ideas synthesized incorporating research
 - [ ] Trade-offs analyzed
 - [ ] Recommendations provided
-- [ ] **METHODOLOGY CHECK**: Output aligns with `brainstormer` Thinking Protocol (structured analysis, trade-off documentation)
 
 ---
 
@@ -190,6 +129,6 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 
 Present comprehensive analysis with:
 
-1. ✅ **Analysis Complete** — Proceed with recommendation
-2. 📋 **Plan** → `/plan:hard` for detailed planning
-3. 🔄 **Iterate** — Refine based on feedback
+1. **Analysis Complete** — Proceed with recommendation
+2. **Plan** → `/plan:hard` for detailed planning
+3. **Iterate** — Refine based on feedback

package/merged-commands/c4-architecture-c4-architecture.md

@@ -54,7 +54,7 @@ All documentation is written to a new `C4-Documentation/` directory in the repos
 
 For each directory, starting from the deepest:
 
-- Use Task tool with subagent_type="c4-architecture::c4-code"
+- Use Task tool with subagent_type="general-purpose"
 - Prompt: |
   Analyze the code in directory: [directory_path]
 
@@ -110,7 +110,7 @@ For each directory, starting from the deepest:
 
 For each identified component:
 
-- Use Task tool with subagent_type="c4-architecture::c4-component"
+- Use Task tool with subagent_type="general-purpose"
 - Prompt: |
   Synthesize the following C4 Code-level documentation files into a logical component:
 
@@ -153,7 +153,7 @@ For each identified component:
 
 ### 2.3 Create Master Component Index
 
-- Use Task tool with subagent_type="c4-architecture::c4-component"
+- Use Task tool with subagent_type="general-purpose"
 - Prompt: |
   Create a master component index that lists all components in the system.
 
@@ -188,7 +188,7 @@ For each identified component:
 
 ### 3.2 Map Components to Containers
 
-- Use Task tool with subagent_type="c4-architecture::c4-container"
+- Use Task tool with subagent_type="general-purpose"
 - Prompt: |
   Synthesize components into containers based on deployment definitions.
 
@@ -261,7 +261,7 @@ For each identified component:
 
 ### 4.2 Create Context Documentation
 
-- Use Task tool with subagent_type="c4-architecture::c4-context"
+- Use Task tool with subagent_type="general-purpose"
 - Prompt: |
   Create comprehensive C4 Context-level documentation for the system.
 

package/merged-commands/code/auto.md

@@ -3,7 +3,7 @@ description: ⚡⚡⚡ [AUTO] Start coding & testing an existing plan ("trust me
 argument-hint: [plan] [all-phases-yes-or-no] (default: yes)
 ---
 
-**MUST READ** `CLAUDE.md` then **THINK HARDER** to start working on the following plan follow the Orchestration Protocol, Core Responsibilities, Subagents Team and Development Rules:
+**MUST READ** `CLAUDE.md` then **THINK HARDER** to start working on the following plan follow the Orchestration Protocol, Core Responsibilities, Task Agents Team and Development Rules:
 <plan>$ARGUMENTS</plan>
 
 ## Arguments
@@ -17,7 +17,7 @@ argument-hint: [plan] [all-phases-yes-or-no] (default: yes)
 - Validate the plan's assumptions, surface blockers, and confirm priorities with the user prior to execution.
 - Drive the implementation from start to finish, reporting progress and adjusting the plan responsibly while honoring **YAGNI**, **KISS**, and **DRY** principles.
 
-**IMPORTANT:** Remind these rules with subagents communication:
+**IMPORTANT:** Remind these rules with Task agents communication:
 - Sacrifice grammar for the sake of concision when writing reports.
 - In reports, list any unresolved questions at the end, if any.
 - Ensure token efficiency while maintaining high quality.
@@ -36,9 +36,9 @@ argument-hint: [plan] [all-phases-yes-or-no] (default: yes)
 
 **Output:** `✓ Step 0: [Plan Name] - [Phase Name]`
 
-**Subagent Pattern (use throughout):**
+**Task Agent Pattern (use throughout):**
 ```
-Task(subagent_type="[type]", prompt="[task description]", description="[brief]")
+Task(subagent_type="general-purpose", prompt="[task description]", description="[brief]")
 ```
 
 ---
@@ -50,10 +50,10 @@ Task(subagent_type="[type]", prompt="[task description]", description="[brief]")
 ---
 
 ## Step 1: Analysis & Task Extraction
-Use `project-manager` agent to read plan file completely. Map dependencies between tasks. List ambiguities or blockers. Identify required skills/tools and activate from catalog. Parse phase file and extract actionable tasks.
+Use a Task agent for project management to read plan file completely. Map dependencies between tasks. List ambiguities or blockers. Identify required skills/tools and activate from catalog. Parse phase file and extract actionable tasks.
 
 **TodoWrite Initialization & Task Extraction:**
-`project-manager` agent must respond back with:
+Task agent for project management must respond back with:
 - Initialize `TodoWrite` with `Step 0: [Plan Name] - [Phase Name]` and all command steps (Step 1 through Step 5)
 - Read phase file (e.g., phase-01-preparation.md)
 - Look for tasks/steps/phases/sections/numbered/bulleted lists
@@ -72,7 +72,7 @@ Mark Step 1 complete in `TodoWrite`, mark Step 2 in_progress.
 
 ## Step 2: Implementation
 
-Implement selected plan phase step-by-step following extracted tasks (Step 2.1, Step 2.2, etc.). Mark tasks complete as done. For UI work, call `ui-ux-designer` subagent: "Implement [feature] UI per ./docs/design-guidelines.md". Use `ai-multimodal` skill for image assets, imagemagick in `media-processing` skill for editing. Run type checking and compile to verify no syntax errors.
+Implement selected plan phase step-by-step following extracted tasks (Step 2.1, Step 2.2, etc.). Mark tasks complete as done. For UI work, use a Task agent for UI/UX design: Task(subagent_type="general-purpose", prompt="You are a ui-ux-designer. Implement [feature] UI per ./docs/design-guidelines.md", description="Implement UI"). Use `ai-multimodal` skill for image assets, imagemagick in `media-processing` skill for editing. Run type checking and compile to verify no syntax errors.
 
 **Output:** `✓ Step 2: Implemented [N] files - [X/Y] tasks complete, compilation passed`
 
@@ -82,7 +82,7 @@ Mark Step 2 complete in `TodoWrite`, mark Step 3 in_progress.
 
 ## Step 3: Testing
 
-Write tests covering happy path, edge cases, and error cases. Call `tester` subagent: "Run test suite for plan phase [phase-name]". If ANY tests fail: STOP, call `debugger` subagent: "Analyze failures: [details]", fix all issues, re-run `tester`. Repeat until 100% pass.
+Write tests covering happy path, edge cases, and error cases. Use a Task agent for testing: Task(subagent_type="general-purpose", prompt="You are a tester. Run test suite for plan phase [phase-name]", description="Run tests"). If ANY tests fail: STOP, use a Task agent for debugging: Task(subagent_type="general-purpose", prompt="You are a debugger. Analyze failures: [details]", description="Debug test failures"), fix all issues, re-run tester. Repeat until 100% pass.
 
 **Testing standards:** Unit tests may use mocks for external dependencies (APIs, DB). Integration tests use test environment. E2E tests use real but isolated data. Forbidden: commenting out tests, changing assertions to pass, TODO/FIXME to defer fixes.
 
@@ -96,7 +96,7 @@ Mark Step 3 complete in `TodoWrite`, mark Step 4 in_progress.
 
 ## Step 4: Code Review (Smart Auto-Handling)
 
-Call `code-reviewer` subagent: "Review code changes in **Step 2** of plan phase [phase-name]. Check security, performance, architecture, YAGNI/KISS/DRY. Return score (X/10), critical issues list, warnings list, suggestions list."
+Use a Task agent for code review: Task(subagent_type="general-purpose", prompt="You are a code-reviewer. Review code changes in **Step 2** of plan phase [phase-name]. Check security, performance, architecture, YAGNI/KISS/DRY. Return score (X/10), critical issues list, warnings list, suggestions list.", description="Code review")
 
 **Auto-Handling Logic (max 3 cycles):**
 
@@ -141,14 +141,14 @@ Mark Step 4 complete in TodoWrite, mark Step 5 in_progress.
 ## Step 5: Finalize
 
 1. **STATUS UPDATE - BOTH MANDATORY - PARALLEL EXECUTION:**
-- **Call** `project-manager` sub-agent: "Update plan status in [plan-path]. Mark plan phase [phase-name] as DONE with timestamp. Update roadmap."
-- **Call** `docs-manager` sub-agent: "Update docs for plan phase [phase-name]. Changed files: [list]."
+- **Use** Task agent for project management: Task(subagent_type="general-purpose", prompt="You are a project-manager. Update plan status in [plan-path]. Mark plan phase [phase-name] as DONE with timestamp. Update roadmap.", description="Update plan status")
+- **Use** Task agent for documentation: Task(subagent_type="general-purpose", prompt="You are a docs-manager. Update docs for plan phase [phase-name]. Changed files: [list].", description="Update docs")
 
 2. **ONBOARDING CHECK:** Detect onboarding requirements (API keys, env vars, config) + generate summary report with next steps.
 - If this is the last phase: use `AskUserQuestion` tool to ask if user wants to set up onboarding requirements.
 
 3. **AUTO-COMMIT (after steps 1 and 2 completes):**
-- **Call** `git-manager` subagent to handle git operation.
+- **Use** Task agent for git operations: Task(subagent_type="general-purpose", prompt="You are a git-manager. Handle git operation.", description="Git commit")
 - Run only if: Steps 1 and 2 successful + Tests passed
 - Auto-stage, commit with conventional commit message based on actual changes
 
@@ -185,10 +185,10 @@ Use `AskUserQuestion` tool to ask these questions:
 
 **TodoWrite tracking required:** Initialize at Step 0, mark each step complete before next.
 
-**Mandatory subagent calls:**
-- Step 3: `tester`
-- Step 4: `code-reviewer`
-- Step 5: `project-manager` AND `docs-manager` AND `git-manager`
+**Mandatory Task agent calls:**
+- Step 3: Task agent for testing
+- Step 4: Task agent for code review
+- Step 5: Task agent for project management AND Task agent for documentation AND Task agent for git operations
 
 **Blocking gates:**
 - Step 3: Tests must be 100% passing

package/merged-commands/code/fast.md

@@ -1,5 +1,5 @@
 ---
-description: ⚡ Quick Implementation — Direct coding without planning phase
+description: Quick Implementation — Direct coding without planning phase
 version: "1.0"
 category: engineering
 execution-mode: execute
@@ -13,36 +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 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: PHASE CONTINUITY RULES
+## CRITICAL: PHASE CONTINUITY RULES
 
 ```yaml
 phase_continuity:
@@ -60,90 +31,66 @@ All files in `./reports/` → English only.
 
 ---
 
-## ⛔ INCREMENTAL EXECUTION (MANDATORY)
+## Execution
 
-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).
+One phase at a time, sequential. Each phase must complete before next begins.
 
 ---
 
-## 🎭 Phase 1: CONTEXT SCAN
+## Phase 1: CONTEXT SCAN
 
 | Attribute | Value                                       |
 | --------- | ------------------------------------------- |
-| **Agent** | `scouter`                                   |
+| **Role**  | `scouter`                                   |
 | **Goal**  | Find relevant code patterns and conventions |
 
-### ⚡ 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. Find relevant code patterns and conventions for the task. Exit when: relevant files identified, patterns understood, conventions noted.", description="scouter: Find relevant code patterns and conventions")
 
 **Exit Criteria:**
 
 - [ ] Relevant files identified
 - [ ] Patterns understood
 - [ ] Conventions noted
-- [ ] **METHODOLOGY CHECK**: Output aligns with `scouter` Thinking Protocol
 
 ---
 
-## 🎭 Phase 2: IMPLEMENTATION
+## Phase 2: IMPLEMENTATION
 
 | Attribute | Value                                                      |
 | --------- | ---------------------------------------------------------- |
-| **Agent** | Route by domain: `frontend-engineer` \| `backend-engineer` |
+| **Role**  | Route by domain: `frontend-engineer` \| `backend-engineer` |
 | **Goal**  | Implement the feature/fix                                  |
 
-### ⚡ TIERED EXECUTION
-
-**TIER 1 (MANDATORY when tool exists):**
+### Delegation
 
-> Invoke runSubagent for appropriate domain engineer. Context: ISOLATED.
-
-**TIER 2 (FALLBACK on system error only):**
-
-> Load `{AGENTS_PATH}/[domain]-engineer.md`
-> EMBODY [domain-engineer] — Requires logged system error justification.
+> Task(subagent_type="general-purpose", prompt="You are a domain engineer (frontend or backend as appropriate). Implement the feature/fix following existing patterns. Exit when: code implemented, follows existing patterns, compiles without errors.", description="engineer: Implement the feature/fix")
 
 **Exit Criteria:**
 
 - [ ] Code implemented
 - [ ] Follows existing patterns
 - [ ] Compiles without errors
-- [ ] **METHODOLOGY CHECK**: Output aligns with the engineer agent's Thinking Protocol
 
 ---
 
-## 🎭 Phase 3: QUICK VALIDATION
+## Phase 3: QUICK VALIDATION
 
 | Attribute | Value                              |
 | --------- | ---------------------------------- |
-| **Agent** | `tester`                           |
+| **Role**  | `tester`                           |
 | **Goal**  | Basic validation of implementation |
 
-### ⚡ TIERED EXECUTION
-
-**TIER 1 (MANDATORY when tool exists):**
-
-> Invoke runSubagent for `tester`. Context: ISOLATED.
-
-**TIER 2 (FALLBACK on system error only):**
+### Delegation
 
-> Load `{AGENTS_PATH}/tester.md`
-> EMBODY [tester] — Requires logged system error justification.
+> Task(subagent_type="general-purpose", prompt="You are a tester. Perform basic validation of the implementation. Exit when: basic functionality verified, no obvious errors, ready for review.", description="tester: Basic validation of implementation")
 
 **Exit Criteria:**
 
 - [ ] Basic functionality verified
 - [ ] No obvious errors
 - [ ] Ready for review
-- [ ] **METHODOLOGY CHECK**: Output aligns with `tester` Thinking Protocol
 
 ---
 
@@ -161,6 +108,6 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 
 Present implementation with:
 
-1. ✅ **Done** — Implementation complete
-2. 🧪 **Test** → `/test:fast`
-3. 🔍 **Review** → `/review:fast`
+1. **Done** — Implementation complete
+2. **Test** → `/test:fast`
+3. **Review** → `/review:fast`