@ngxtm/devkit 2.0.2 → 3.0.0

package/commands/fix/fast.md

@@ -1,84 +0,0 @@
----
-description: ⚡ Quick Fix — Rapid issue resolution
-version: "1.0"
-category: debugging
-execution-mode: execute
----
-
-# /fix:fast — Rapid Issue Fix
-
-> **MISSION**: Quickly diagnose and fix simple issues with minimal overhead.
-
-<issue>$ARGUMENTS</issue>
-
----
-
-## 🛑 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) |
-
----
-
-## ⚠️ ESCALATION
-
-| If | Route To |
-|----|----------|
-| Complex issue | `/fix:hard` |
-| Research needed | `/fix:hard` |
-
----
-
-## ⛔ 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: DIAGNOSIS
-
-| Agent | `debugger` |
-|-------|------------|
-| Goal | Identify root cause |
-| Exit | Root cause identified, complexity assessed |
-
----
-
-## 🎭 Phase 2: FIX IMPLEMENTATION
-
-| Agent | Route by domain |
-|-------|-----------------|
-| Route | UI → `frontend-engineer`, API → `backend-engineer` |
-| Goal | Implement fix |
-| Exit | Fix implemented, minimal changes, code compiles |
-
----
-
-## 🎭 Phase 3: VALIDATION
-
-| Agent | `tester` |
-|-------|----------|
-| Goal | Verify fix |
-| Exit | Issue resolved, no regression |
-
----
-
-## COMPLETION
-
-Present fix with:
-
-1. ✅ **Fixed** — Issue resolved
-2. 🧪 **Test more** → `/test`

package/commands/fix/hard.md

@@ -1,116 +0,0 @@
----
-description: ⚡⚡⚡ Full Fix — Complete issue resolution with research
-version: "1.0"
-category: debugging
-execution-mode: execute
----
-
-# /fix:hard — Complete Issue Resolution
-
-> **MISSION**: Full resolution workflow with research, planning, and validation.
-
-<issue>$ARGUMENTS</issue>
-
----
-
-## 🛑 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) |
-
-**❌ Anti-Lazy**: Never use TIER 2 when TIER 1 tool available.
-
----
-
-## 📁 DELIVERABLE FILES
-
-| Agent | Output |
-|-------|--------|
-| debugger | `./reports/debugs/DEBUG-{issue}.md` |
-| researcher | `./reports/researchers/RESEARCH-{issue}.md` |
-
-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). Format: rules/EXECUTION-PROTOCOL.md § Phase output structure.
-
----
-
-## 🎭 Phase 1: DEEP ANALYSIS
-
-| Agent | `debugger` |
-|-------|------------|
-| Goal | Full root cause analysis |
-| Exit | Root cause identified, impact assessed, failure chain documented |
-
----
-
-## 🎭 Phase 2: RESEARCH
-
-| Agent | `researcher` |
-|-------|--------------|
-| Goal | Research solution patterns |
-| Exit | Solutions researched, best approach identified |
-
----
-
-## 🎭 Phase 3: FIX PLANNING
-
-| Agent | `planner` |
-|-------|-----------|
-| Goal | Create fix strategy with rollback |
-| Exit | Plan created, rollback included |
-
----
-
-## 🎭 Phase 4: IMPLEMENTATION
-
-| Agent | `tech-lead` → specialists |
-|-------|---------------------------|
-| Goal | Execute fix plan |
-| Exit | Fix implemented, changes documented |
-
----
-
-## 🎭 Phase 5: VALIDATION
-
-| Agent | `tester` |
-|-------|----------|
-| Goal | Comprehensive validation |
-| Exit | Issue resolved, tests pass, no regression |
-
----
-
-## 🎭 Phase 5.5: ROLLBACK VERIFICATION (IF CRITICAL)
-
-| Agent | `devops-engineer` |
-|-------|-------------------|
-| Trigger | Fix affects production or is critical |
-| Goal | Verify rollback plan |
-| Exit | Rollback documented, tested, recovery time estimated |
-
----
-
-## COMPLETION
-
-Present fix report with:
-
-1. ✅ **Fixed** — Issue resolved
-2. 🧪 **Test** → `/test`
-3. 📝 **Docs** → `/docs:core`

package/commands/fix.md

@@ -1,64 +0,0 @@
----
-description: 🔧 Fix Router — Route to issue resolution workflows
-version: "1.0"
-category: debugging
-execution-mode: router
----
-
-# /fix — Issue Resolution Router
-
-> **ROUTER DIRECTIVE**: Analyze issue complexity and route to appropriate fix workflow.
-
-<issue>$ARGUMENTS</issue>
-
----
-
-## 🛑 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
-
-```
-IF issue is simple (clear cause, quick fix):
-  → Route to /fix:fast
-
-IF issue is complex (research needed, multi-file):
-  → Route to /fix:hard
-
-IF unsure:
-  → Default to /fix:fast (escalate if needed)
-```
-
----
-
-## AVAILABLE ROUTES
-
-| Route       | When to Use                     |
-| ----------- | ------------------------------- |
-| `/fix:fast` | Quick fixes, clear issues       |
-| `/fix:hard` | Complex issues, research needed |
-
----
-
-## PRESENT OPTIONS
-
-```markdown
-## 🔧 Fix Mode Selection
-
-**Issue**: [parsed issue]
-
-**Choose workflow:**
-
-1. ⚡ **Fast** → `/fix:fast` — Quick fix
-2. ⚡⚡⚡ **Hard** → `/fix:hard` — Full resolution
-
-⏳ Awaiting selection...
-```

package/commands/plan/fast.md

@@ -1,78 +0,0 @@
----
-description: ⚡ Quick Plan — Fast planning without deep research
-version: "1.0"
-category: planning
-execution-mode: execute
----
-
-# /plan:fast — Quick Planning
-
-> **MISSION**: Create quick implementation plan for clear tasks.
-
-<task>$ARGUMENTS</task>
-
----
-
-## 🛑 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) |
-
-**Deliverables:** 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). Format: rules/EXECUTION-PROTOCOL.md § Phase output structure.
-
----
-
-## 🎭 Phase 1: CONTEXT SCAN
-
-| Agent | `scouter`                                              |
-| ----- | ------------------------------------------------------ |
-| Goal  | Quick context gathering                                |
-| Exit  | Relevant patterns found, integration points identified |
-
----
-
-## 🎭 Phase 2: PLAN CREATION
-
-| Agent  | `planner`                          |
-| ------ | ---------------------------------- |
-| Goal   | Create focused implementation plan |
-| Output | `./reports/plans/PLAN-{task}.md`   |
-| Exit   | Steps defined, approach clear      |
-
----
-
-## ESCALATION
-
-| If                   | Route To     |
-| -------------------- | ------------ |
-| Complex architecture | `/plan:hard` |
-| Research needed      | `/plan:hard` |
-
----
-
-## COMPLETION
-
-Present plan with:
-
-1. ✅ **Plan Ready** — `./reports/plans/PLAN-{task}.md`
-2. 🍳 **Implement** → `/cook:fast`

package/commands/plan/hard.md

@@ -1,131 +0,0 @@
----
-description: ⚡⚡⚡ Full Plan — Research-backed comprehensive planning
-version: "1.0"
-category: planning
-execution-mode: execute
----
-
-# /plan:hard — Comprehensive Planning
-
-> **MISSION**: Create thorough implementation plan with research and architecture analysis.
-
-<task>$ARGUMENTS</task>
-
----
-
-## 🛑 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) |
-
----
-
-## 📁 DELIVERABLE FILES
-
-| Agent      | Output                                                                                                                                                                   |
-| ---------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| researcher | `./reports/researchers/RESEARCH-{task}.md`                                                                                                                               |
-| scouter    | `./reports/scouts/SCOUT-{task}.md`                                                                                                                                       |
-| planner    | **One** `./reports/plans/PLAN-{task}.md` **OR** multiple `./reports/plans/PLAN-{task}-phase1.md`, `PLAN-{task}-phase2.md`, … (see **Complexity & plan splitting** below) |
-
-**Plans are source of truth for implementation.** All files in `./reports/` → English only.
-
----
-
-## 📐 COMPLEXITY & PLAN SPLITTING (MANDATORY FOR PLANNER)
-
-When the logical plan would have **> 3 phases** or **estimated effort > 3 days**, the planner **MUST** produce **multiple plan files** (one per executable phase or per milestone group), **not** one monolithic file.
-
-| Condition                  | Planner output                                                   |
-| -------------------------- | ---------------------------------------------------------------- |
-| ≤ 3 phases, ≤ 3 days       | **One** `PLAN-{task}.md`                                         |
-| > 3 phases **or** > 3 days | **Multiple** `PLAN-{task}-phase1.md`, `PLAN-{task}-phase2.md`, … |
-
-**Multi-plan rules:**
-
-- Naming: `PLAN-{task}-phase1.md`, `PLAN-{task}-phase2.md`, …
-- Order: Execute in numeric order; phase N starts only after phase N−1 is complete.
-- Each file: scope **only** that phase; Prerequisites state “Phase N−1 complete” (or prior deliverables); clear handoff to next file.
-- Index (optional): planner may add `PLAN-{task}-INDEX.md` listing phases and file names for navigation.
-
----
-
-## ⛔ 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). Format: rules/EXECUTION-PROTOCOL.md § Phase output structure.
-
----
-
-## 🎭 Phase 1: RESEARCH
-
-| Agent  | `researcher`                                  |
-| ------ | --------------------------------------------- |
-| Goal   | Research best practices and patterns          |
-| Output | `./reports/researchers/RESEARCH-{task}.md`    |
-| Exit   | Best practices identified, sources documented |
-
----
-
-## 🎭 Phase 2: CODEBASE ANALYSIS
-
-| Agent  | `scouter`                                    |
-| ------ | -------------------------------------------- |
-| Goal   | Full architecture mapping                    |
-| Output | `./reports/scouts/SCOUT-{task}.md`           |
-| Exit   | Architecture understood, dependencies mapped |
-
----
-
-## 🎭 Phase 3: DESIGN (IF UI NEEDED)
-
-| Agent   | `designer`                                        |
-| ------- | ------------------------------------------------- |
-| Trigger | Task involves UI/UX                               |
-| Goal    | Design approach input                             |
-| Exit    | Design approach defined, accessibility considered |
-
----
-
-## 🎭 Phase 4: PLAN CREATION
-
-| Agent        | `planner`                                                                                                                   |
-| ------------ | --------------------------------------------------------------------------------------------------------------------------- |
-| Prerequisite | **READ** RESEARCH + SCOUT files (and DESIGN if Phase 3 ran)                                                                 |
-| Goal         | Create detailed implementation plan as **one file** or **multiple phase files** (see **Complexity & plan splitting** above) |
-| Output       | One `./reports/plans/PLAN-{task}.md` **or** multiple `./reports/plans/PLAN-{task}-phase1.md`, `PLAN-{task}-phase2.md`, …    |
-
-**Directive to planner:** If the task decomposes into **> 3 phases** or **> 3 days** effort, produce **multiple plan files** (one per phase/milestone), each executable in sequence. Otherwise produce a single `PLAN-{task}.md`.
-
-**CONSTRAINT INHERITANCE:**
-
-```
-Plan(s) MUST reference prior phases:
-- "Based on research finding R1..."
-- "Following pattern from Scout..."
-- "Per design decision D1..."
-```
-
-| Exit | One plan file **or** multiple phase plan files created; each has scope, prerequisites, tasks, exit criteria, risks, rollback; order and handoffs clear |
-
----
-
-## COMPLETION
-
-Present plan with:
-
-1. ✅ **Plan Ready** — `./reports/plans/PLAN-{task}.md` (single) **or** `PLAN-{task}-phase1.md`, `PLAN-{task}-phase2.md`, … (multi-phase, execute in order)
-2. 🍳 **Implement** → `/cook:hard` (run phase-by-phase when multiple plan files exist)

package/commands/plan.md

@@ -1,64 +0,0 @@
----
-description: 📋 Plan Router — Route to planning workflows
-version: "1.0"
-category: planning
-execution-mode: router
----
-
-# /plan — Planning Router
-
-> **ROUTER DIRECTIVE**: Analyze planning need and route to appropriate workflow.
-
-<task>$ARGUMENTS</task>
-
----
-
-## 🛑 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. plan/hard.md), and execute it.
-
----
-
-## ROUTING LOGIC
-
-```
-IF task is clear (known approach, codebase-only):
-  → Route to /plan:fast
-
-IF task is complex (research needed, architectural):
-  → Route to /plan:hard
-
-IF unsure:
-  → Default to /plan:fast
-```
-
----
-
-## AVAILABLE ROUTES
-
-| Route        | When to Use                     |
-| ------------ | ------------------------------- |
-| `/plan:fast` | Quick planning without research |
-| `/plan:hard` | Full planning with research     |
-
----
-
-## PRESENT OPTIONS
-
-```markdown
-## 📋 Planning Mode Selection
-
-**Task**: [parsed task]
-
-**Choose workflow:**
-
-1. ⚡ **Fast** → `/plan:fast` — Quick plan
-2. ⚡⚡⚡ **Hard** → `/plan:hard` — Full research-backed plan
-
-⏳ Awaiting selection...
-```

package/commands/test.md

@@ -1,64 +0,0 @@
----
-description: 🧪 Test Router — Route to testing workflows
-version: "1.0"
-category: validation
-execution-mode: router
----
-
-# /test — Testing Router
-
-> **ROUTER DIRECTIVE**: Analyze testing need and route to appropriate workflow.
-
-<scope>$ARGUMENTS</scope>
-
----
-
-## 🛑 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
-
-```
-IF scope is limited (unit tests, quick check):
-  → Route to /test:fast
-
-IF scope is comprehensive (full suite, E2E):
-  → Route to /test:hard
-
-IF unsure:
-  → Default to /test:fast
-```
-
----
-
-## AVAILABLE ROUTES
-
-| Route        | When to Use             |
-| ------------ | ----------------------- |
-| `/test:fast` | Quick tests, unit tests |
-| `/test:hard` | Full test suite, E2E    |
-
----
-
-## PRESENT OPTIONS
-
-```markdown
-## 🧪 Test Mode Selection
-
-**Scope**: [parsed scope]
-
-**Choose workflow:**
-
-1. ⚡ **Fast** → `/test:fast` — Quick tests
-2. ⚡⚡⚡ **Hard** → `/test:hard` — Comprehensive testing
-
-⏳ Awaiting selection...
-```