Initial commit

commands/plan.md

@@ -0,0 +1,192 @@
+---
+tags: ["workflow", "planning", "implementation"]
+description: "Create PLAN.md file with phase-based breakdown for tasks, bugs, and spikes"
+argument-hint: "### | PROJ-###"
+allowed-tools: ["Read", "Write", "Edit", "Grep", "Glob", "TodoWrite", "Task", "mcp__plugin_ai-toolkit_sequential-thinking__sequentialthinking", "mcp__plugin_ai-toolkit_context7__resolve-library-id", "mcp__plugin_ai-toolkit_context7__get-library-docs", "WebSearch", "WebFetch"]
+model: claude-sonnet-4-5
+references_guidelines:
+  - docs/development/workflows/pm-workflows.md    # Plan methodology, phase structure, complexity scoring
+  - docs/development/workflows/task-workflow.md   # Task TDD phases
+  - docs/development/workflows/bug-workflow.md    # Bug reproduction-first phases
+  - docs/development/workflows/spike-workflow.md  # Spike exploration planning
+  - docs/development/templates/plan-template.md   # Plan file structure
+---
+
+# /plan Command
+
+**WHAT**: Create PLAN.md with phase-based breakdown through analysis and research.
+
+**HOW**: Detects issue type from file (TASK.md/BUG.md/SPIKE.md) and generates appropriate plan structure.
+
+## Usage
+
+```bash
+/plan 001         # Detects type from file, creates appropriate PLAN.md
+/plan 003         # If SPIKE.md exists → creates PLAN-1.md, PLAN-2.md
+/plan PROJ-123    # Jira: Fetches issue, creates PLAN.md locally
+```
+
+## Issue Type Detection
+
+**Reads issue file to determine type (not ID prefix):**
+
+```bash
+# In pm/issues/###-name/ directory:
+if [ -f "TASK.md" ]; then type="task"    # TDD phases
+elif [ -f "BUG.md" ]; then type="bug"    # Reproduction-first
+elif [ -f "SPIKE.md" ]; then type="spike" # Exploration plans
+fi
+```
+
+| Issue Type | Plan Structure | File Created |
+|------------|---------------|--------------|
+| Task (TASK.md) | TDD phases (RED/GREEN/REFACTOR) | PLAN.md |
+| Bug (BUG.md) | Reproduction-first phases | PLAN.md |
+| Spike (SPIKE.md) | Exploration phases per approach | PLAN-1.md, PLAN-2.md, ... |
+
+## Process
+
+### For Task/Bug
+
+1. **Load**: Read TASK.md/BUG.md, parent SPEC (if exists), similar WORKLOGs
+2. **Analyze**: Sequential thinking, research via Context7/web search
+3. **Generate**: Phase breakdown per workflow guidelines
+   - **Task**: TDD phases (X.RED/X.GREEN/X.REFACTOR) per task-workflow.md
+   - **Bug**: Reproduction → Fix → Harden phases per bug-workflow.md
+4. **Review**: code-architect (always), security-auditor (if security-relevant)
+5. **Present**: Phases, scenario coverage, complexity score, research summary
+
+### For Spike (Exploration)
+
+1. **Load**: Read SPIKE.md (questions, success criteria)
+2. **Ask**: "How many approaches do you want to explore?" → N
+3. **Gather**: For each approach:
+   - "Describe approach N?" → User describes
+   - "What aspects to evaluate?" → Performance, complexity, etc.
+4. **Generate**: Create PLAN-N.md for each approach
+   - Exploration phases (not TDD)
+   - Focus on answering questions
+   - Include spike reminder banner and branch reference
+5. **Present**: Summary of all exploration plans
+
+## Task Plan Example
+
+```markdown
+# Implementation Plan: 001 User Login Flow
+
+## Phase 1 - User can log in
+
+### 1.RED - Write Failing Tests
+- [ ] 1.1 Write login tests (valid credentials, invalid, locked account)
+- [ ] 1.2 [CHECKPOINT] Tests FAIL
+
+### 1.GREEN - Implement
+- [ ] 1.3 Implement login endpoint
+- [ ] 1.4 [CHECKPOINT] Tests PASS
+
+### 1.REFACTOR - Clean Up
+- [ ] 1.5 Refactor, review >= 90
+- [ ] 1.6 Commit phase
+
+## Scenario Coverage
+✓ SPEC-001 Scenario 1: "User logs in" → Phase 1
+
+Complexity: 8 points (Medium)
+```
+
+## Bug Plan Example
+
+```markdown
+# Implementation Plan: 002 Login Safari Crash
+
+## Phase 1 - Reproduce Failure
+
+### 1.RED - Write Reproduction Test
+- [ ] 1.1 Create Safari-specific test
+- [ ] 1.2 [CHECKPOINT] Test FAILS (proves bug exists)
+
+## Phase 2 - Implement Fix
+
+### 2.GREEN - Fix the Bug
+- [ ] 2.1 Investigate root cause
+- [ ] 2.2 Implement fix
+- [ ] 2.3 [CHECKPOINT] Reproduction test PASSES
+- [ ] 2.4 [CHECKPOINT] No regressions
+
+### 2.REFACTOR - Clean Up
+- [ ] 2.5 Refactor, review >= 90
+- [ ] 2.6 Commit fix
+```
+
+## Spike Plan Example
+
+Creates multiple files with branch references:
+
+**PLAN-1.md:**
+```markdown
+# 003 Exploration Plan 1: GraphQL
+
+> **⚠️ SPIKE EXPLORATION**
+> Code will be committed to spike branch, not merged to main.
+> Track discoveries in WORKLOG-1.md.
+> Branch: spike/003/plan-1
+
+## Exploration Goal
+Evaluate GraphQL for our API needs.
+
+## Phase 1: Setup (1 hour)
+- [ ] Install dependencies
+- [ ] Create basic schema
+
+## Phase 2: Performance Testing (2 hours)
+- [ ] Run benchmarks
+- [ ] Document in WORKLOG-1.md
+```
+
+## Spike Interaction Example
+
+```
+User: /plan 003
+
+AI: Issue 003 (spike): "GraphQL vs REST for our API?"
+
+    How many approaches do you want to explore?
+
+User: 2
+
+AI: Describe approach 1:
+
+User: GraphQL with Apollo Server - evaluate schema design,
+     query flexibility, and caching
+
+AI: Describe approach 2:
+
+User: REST with Express - compare setup simplicity,
+     HTTP caching, and team familiarity
+
+AI: Creating exploration plans...
+
+    ✓ PLAN-1.md: GraphQL with Apollo Server
+      Branch: spike/003/plan-1
+      - Phase 1: Setup (1h)
+      - Phase 2: Query implementation (2h)
+      - Phase 3: Performance testing (1h)
+
+    ✓ PLAN-2.md: REST with Express
+      Branch: spike/003/plan-2
+      - Phase 1: Setup (30min)
+      - Phase 2: Endpoint implementation (2h)
+      - Phase 3: Performance testing (1h)
+
+    Next: /implement 003 (will ask which plan)
+```
+
+## Integration
+
+```
+/issue → /plan {ID} → /implement {ID} → /complete {ID}
+```
+
+**Creates:**
+- Task/Bug: `pm/issues/###-*/PLAN.md`
+- Spike: `pm/issues/###-*/PLAN-1.md`, `PLAN-2.md`, etc.