prjct-cli 0.6.0 → 0.7.0

package/templates/commands/bug.md

@@ -0,0 +1,79 @@
+---
+allowed-tools: [Read, Write]
+description: 'Report and track bugs with auto-prioritization'
+---
+
+# /p:bug
+
+## Usage
+
+```
+/p:bug "<description>"
+```
+
+## What It Does
+
+1. **Severity detection**: Analyzes bug description for severity indicators
+2. **Priority placement**: Adds to `core/next.md` based on severity
+3. **Memory tracking**: Logs bug report to `memory/context.jsonl`
+4. **Quick resolution**: Suggests immediate actions
+
+## Severity Detection
+
+Auto-detects severity from keywords:
+
+- **Critical**: crash, down, broken, not working, production, urgent
+- **High**: error, fail, issue, problem, major
+- **Medium**: bug, incorrect, wrong, should
+- **Low**: minor, small, cosmetic, typo
+
+## Flow
+
+1. Detect severity from description
+2. Read `core/next.md`
+3. Format bug entry: `🐛 [SEVERITY] description`
+4. Insert at top if critical/high, bottom if medium/low
+5. Write to `core/next.md`
+6. Log to `memory/context.jsonl`
+
+## Response Format
+
+```
+🐛 Bug reported: {severity}
+
+{description}
+
+Priority: {critical/high/medium/low}
+Added to: core/next.md (position {top/bottom})
+
+Quick actions:
+• "start fixing" → /p:now "{description}"
+• "show queue" → /p:next
+
+/p:now | /p:next
+```
+
+## Example
+
+```
+User: p. bug "login button crashes on mobile"
+
+Claude detects:
+- Keywords: "crashes" → CRITICAL severity
+- Action: Add to top of next.md
+- Format: 🐛 [CRITICAL] login button crashes on mobile
+
+Response:
+🐛 Bug reported: CRITICAL
+
+login button crashes on mobile
+
+Priority: critical
+Added to: core/next.md (top priority)
+
+Quick actions:
+• "start fixing" → /p:now "login button crashes on mobile"
+• "show queue" → /p:next
+
+/p:now | /p:next
+```

package/templates/commands/build.md

@@ -1,15 +1,17 @@
 ---
 allowed-tools: [Read, Write]
-description: "Start task with agent assignment"
+description: 'Start task with agent assignment'
 ---
 
 # /p:build
 
 ## Validation
+
 - Blocks if: `core/now.md` has active task
 - Error: "Complete current task first. Use /p:done"
 
 ## Flow
+
 1. Parse: task desc OR queue # (1-5)
 2. Detect: `TaskSchema.detectAgent(task)` + complexity
 3. Get: GitHub dev from `git config user.name` + remote
@@ -17,6 +19,7 @@ description: "Start task with agent assignment"
 5. Write: `core/now.md` with frontmatter
 
 ## Frontmatter
+
 ```yaml
 ---
 id: task-{timestamp}
@@ -30,6 +33,7 @@ started: {iso_timestamp}
 ```
 
 ## Response
+
 ```
 🎯 {task}
 {agent_icon} {agent_name}
@@ -38,4 +42,3 @@ Complexity: {level}
 
 /p:done when finished
 ```
-

package/templates/commands/cleanup.md

@@ -1,16 +1,18 @@
 ---
 allowed-tools: [Read, Edit, Bash]
-description: "Code cleanup and optimization"
+description: 'Code cleanup and optimization'
 ---
 
 # /p:cleanup
 
 ## Usage
+
 ```
 /p:cleanup [--type code|imports|files|deps|all] [--dry-run]
 ```
 
 ## Flow
+
 1. Parse: type + mode
 2. Backup: create if needed
 3. Execute: cleanup by type
@@ -18,6 +20,7 @@ description: "Code cleanup and optimization"
 5. Log: `memory/cleanup-log.jsonl`
 
 ## Types
+
 - **code**: Remove console.logs, commented code, dead code
 - **imports**: Remove unused, organize imports
 - **files**: Remove temp files, empty files
@@ -25,6 +28,7 @@ description: "Code cleanup and optimization"
 - **all**: All cleanup types
 
 ## Response
+
 ```
 🧹 Cleanup complete!
 
@@ -36,4 +40,3 @@ description: "Code cleanup and optimization"
 
 /p:test | /p:ship
 ```
-

package/templates/commands/design.md

@@ -1,22 +1,25 @@
 ---
 allowed-tools: [Read, Write]
-description: "Design architecture and APIs"
+description: 'Design architecture and APIs'
 ---
 
 # /p:design
 
 ## Usage
+
 ```
 /p:design [target] [--type architecture|api|component|database|flow]
 ```
 
 ## Flow
+
 1. Parse: target + type
 2. Generate: ASCII diagrams
 3. Create: specifications
 4. Save: `designs/{target}-{type}.md`
 
 ## Types
+
 - **architecture**: System design, components, data flow
 - **api**: Endpoint specs, schemas, auth
 - **component**: Interfaces, props, state
@@ -24,6 +27,7 @@ description: "Design architecture and APIs"
 - **flow**: User journeys, workflows
 
 ## Response
+
 ```
 🎨 Design complete!
 
@@ -32,4 +36,3 @@ description: "Design architecture and APIs"
 
 /p:now "Implement {target}"
 ```
-

package/templates/commands/done.md

@@ -1,22 +1,25 @@
 ---
 allowed-tools: [Read, Write]
-description: "Complete task, clear focus"
+description: 'Complete task, clear focus'
 ---
 
 # /p:done
 
 ## Validation
+
 - Requires: `.prjct/prjct.config.json` exists
 - Requires: `core/now.md` has content
 - Else: "Not working on anything. Use /p:now or /p:next"
 
 ## Flow
+
 1. Read: `core/now.md` → calculate duration
 2. Clear: `core/now.md`
 3. Update: `progress/metrics.md`, `core/context.md`
 4. Log: `memory/context.jsonl`
 
 ## Response
+
 ```
 ✅ {task} ({duration})
 
@@ -25,4 +28,3 @@ Next?
 • "ship {feature}" → celebrate
 • /p:now | /p:ship
 ```
-

package/templates/commands/feature.md

@@ -0,0 +1,113 @@
+---
+allowed-tools: [Read, Write, Bash]
+description: 'Value analysis + roadmap + task breakdown + auto-start'
+---
+
+# /p:feature
+
+## Usage
+
+```
+/p:feature "<description>"
+```
+
+## What It Does
+
+1. **Value analysis**: Impact/effort/timing analysis
+2. **Roadmap**: Positioning in project roadmap
+3. **Task breakdown**: Smart breakdown into logical tasks
+4. **Auto-start**: First task starts automatically
+
+## Flow
+
+1. Analyze value (impact/effort/timing)
+2. Position in roadmap
+3. Break down into logical tasks (as many as needed)
+4. **Write to session**: Append to `planning/sessions/{YYYY-MM}/{YYYY-MM-DD}.jsonl`
+5. **Update index**: Add to `planning/roadmap.md` (lightweight, last 30 days only)
+6. **Queue tasks**: Write to `core/next.md`
+7. Auto-start first task
+
+## Session Log Format
+
+Append to `planning/sessions/{YYYY-MM}/{YYYY-MM-DD}.jsonl`:
+
+```jsonl
+{"ts":"2025-10-04T14:30:00Z","type":"feature_add","name":"{feature}","tasks":{N},"impact":"{high/med/low}","effort":"{Xh}","status":"queued"}
+```
+
+## Index Update
+
+Append to `planning/roadmap.md` (keep only last 30 days):
+
+```markdown
+## Queued
+- [ ] {feature_name} ({N} tasks, {Xh} estimated) - Added 2025-10-04
+```
+
+If roadmap.md > 30 days old entries, archive them to `planning/archive/roadmap-{YYYY-MM}.md`
+
+## Value Analysis
+
+```
+Feature: {description}
+
+Value Analysis:
+• Impact: {high/medium/low}
+• Effort: {hours estimation}
+• Timing: {now/later/blocked_by}
+• Recommendation: {do_now/defer/needs_X_first}
+```
+
+## Task Breakdown
+
+```
+Roadmap: {feature_name}
+
+Tasks:
+1. [ ] {task_1}
+2. [ ] {task_2}
+3. [ ] {task_3}
+... (as many as needed)
+
+Estimated: {total_hours}h
+```
+
+## Response
+
+```
+✅ Feature roadmap created!
+
+{feature_name}
+📊 Value: {impact} | Effort: {hours}h
+⏰ Recommendation: {timing_advice}
+
+Tasks:
+1. {task_1}
+2. {task_2}
+...
+
+¿Empezamos con tarea 1?
+
+/p:done (when task complete) | /p:ship (when feature complete)
+```
+
+## Example
+
+```
+User: p. feature "agregar unit testing"
+
+Claude analyzes:
+- Impact: HIGH (quality improvement)
+- Effort: 8h
+- Timing: NOW (before shipping more features)
+
+Tasks created:
+1. Setup Jest/Vitest configuration
+2. Write tests for core utilities
+3. Write tests for components
+4. Add CI/CD test runner
+5. Update docs with testing guide
+
+"¿Empezamos con tarea 1: Setup Jest/Vitest?"
+```

package/templates/commands/fix.md

@@ -1,48 +1,79 @@
 ---
 allowed-tools: [Read, Bash, Edit]
-description: "Quick troubleshooting and fixes"
+description: 'Troubleshooting, guidance, and fixes'
 ---
 
 # /p:fix
 
 ## Usage
+
 ```
-/p:fix              # Diagnose current issue
+/p:fix              # Diagnose current issue or get unstuck
 /p:fix [error]      # Fix specific error
+/p:stuck [issue]    # Alias for fix (guidance mode)
 ```
 
 ## Flow
-1. Read: `core/now.md` → get context
-2. Parse: error message OR diagnose current state
-3. Detect: common patterns (deps, config, syntax, tests)
-4. Apply: automatic fix OR suggest solution
-5. Verify: test fix works
+
+1. Read: `core/now.md` + `analysis/` → get context
+2. Parse: error message OR issue description
+3. Detect: issue type (error/bug/design/perf/feature/blocked)
+4. Apply: automatic fix OR provide guidance
+5. Verify: test fix works (if auto-fix)
 6. Log: `memory/context.jsonl`
 
-## Common Fixes
+## Auto-Fix (Technical Errors)
+
 - **Dependencies**: `npm install` missing packages
 - **Config**: Fix malformed JSON/YAML
 - **Syntax**: ESLint/Prettier auto-fix
 - **Tests**: Update snapshots, fix imports
 - **Git**: Resolve merge conflicts
 
+## Guidance (When Stuck)
+
+- **Bug**: 🔍 Check logs → Isolate → Search error → Test fix
+- **Design**: 🎨 Define requirements → Start simple → Ship MVP → Iterate
+- **Performance**: ⚡ Profile first → Fix slowest → Cache ops → Measure
+- **Blocked**: 💡 Break into tasks → Start smallest → Ship incrementally
+- **Default**: Break down → Prioritize → Start → Ship
+
 ## Response (auto-fixed)
+
 ```
 ✅ Fixed: {error_type}
 
 {fix_details}
 
 Verify: {command_to_test}
+
+/p:test | /p:done
+```
+
+## Response (guidance)
+
+```
+💡 {type_guidance}
+
+Let's break it down:
+1. {subtask} (~{time})
+2. {subtask} (~{time})
+3. {subtask} (~{time})
+
+Start with: /p:now "{first_subtask}"
+
+/p:now | /p:task
 ```
 
-## Response (manual)
+## Response (manual diagnosis)
+
 ```
 🔍 Diagnosed: {issue}
 
 Suggested fixes:
 1. {fix_option_1}
 2. {fix_option_2}
+3. {fix_option_3}
 
 /p:done after fixing
 ```
-

package/templates/commands/git.md

@@ -1,11 +1,12 @@
 ---
 allowed-tools: [Bash, Read, Write]
-description: "Smart git operations with context"
+description: 'Smart git operations with context'
 ---
 
 # /p:git
 
 ## Usage
+
 ```
 /p:git commit       # Smart commit with metadata
 /p:git push         # Push with verification
@@ -14,6 +15,7 @@ description: "Smart git operations with context"
 ```
 
 ## Flow: commit
+
 1. Read: `core/now.md` → get task context
 2. Git: `add .` → stage changes
 3. Create: commit message with prjct metadata
@@ -21,16 +23,19 @@ description: "Smart git operations with context"
 5. Log: `memory/context.jsonl`
 
 ## Flow: push
+
 1. Git: `status` → verify clean
 2. Git: `push` with branch tracking
 3. Handle: errors (upstream, conflicts)
 
 ## Flow: sync
+
 1. Git: `pull --rebase`
 2. Resolve: conflicts if any
 3. Git: `push`
 
 ## Commit Message Format
+
 ```
 {type}: {description}
 
@@ -42,6 +47,7 @@ Co-Authored-By: @{github_dev}
 ```
 
 ## Response
+
 ```
 ✅ Git {operation}
 
@@ -49,4 +55,3 @@ Co-Authored-By: @{github_dev}
 
 /p:ship | /p:status
 ```
-

package/templates/commands/help.md

@@ -1,11 +1,12 @@
 ---
 allowed-tools: []
-description: "Interactive guide"
+description: 'Interactive guide'
 ---
 
 # /p:help
 
 ## Response
+
 ```
 🎯 What do you want to do?
 
@@ -35,4 +36,3 @@ description: "Interactive guide"
 
 💬 Talk naturally - I understand both!
 ```
-

package/templates/commands/idea.md

@@ -1,25 +1,34 @@
 ---
 allowed-tools: [Write]
-description: "Quick idea capture"
+description: 'Quick idea capture'
 ---
 
 # /p:idea
 
 ## Usage
+
 ```
 /p:idea <text>
 ```
 
 ## Flow
-1. Append: `planning/ideas.md` with timestamp
-2. If actionable → add to `core/next.md`
-3. Log: `memory/context.jsonl`
+
+1. **Append to session**: `planning/sessions/{YYYY-MM}/{YYYY-MM-DD}.jsonl`
+2. **Update index**: Append to `planning/ideas.md` (keep only last 30 days)
+3. If actionable → add to `core/next.md`
+4. **Archive old**: If ideas.md > 30 days, move to `planning/archive/ideas-{YYYY-MM}.md`
+
+## Session Log Format
+
+```jsonl
+{"ts":"2025-10-04T16:00:00Z","type":"idea_add","idea":"{text}","actionable":{true/false},"priority":"{high/med/low}"}
+```
 
 ## Response
+
 ```
 💡 {idea}
 {✅ Added to queue | 📝 Saved to backlog}
 
 /p:now "{idea}" | /p:next
 ```
-

package/templates/commands/init.md

@@ -1,28 +1,52 @@
 ---
 allowed-tools: [Read, Write, Bash]
-description: "Initialize prjct project"
+description: 'Initialize prjct project (with architect mode for blank projects)'
 ---
 
 # /p:init
 
-## Flow
+## Usage
+
+```
+/p:init                    # Existing project
+/p:init "[idea]"          # New blank project (architect mode)
+```
+
+## Flow: Existing Project
+
 1. Generate: project ID from path hash
-2. Create: `~/.prjct-cli/projects/{id}/` structure
+2. Create: `~/.prjct-cli/projects/{id}/` structure (including `agents/`)
 3. Write: `.prjct/prjct.config.json`
-4. Init: all markdown files with templates
-5. Log: `memory/context.jsonl`
+4. Run: `/p:analyze` to understand stack
+5. Generate: agents based on stack
+6. Log: `memory/context.jsonl`
+
+## Flow: Blank Project (Architect Mode)
+
+1. Generate: project ID
+2. Activate: ARCHITECT role
+3. Analyze: idea/requirements
+4. Recommend: tech stack options (Next.js, React, Vue, etc.)
+5. User confirms: choice
+6. Create: directory structure + base files
+7. Generate: initial roadmap
+8. Generate: agents
+9. Ask: "¿Empezamos con la primera feature?"
 
 ## Directory Structure
+
 ```
 ~/.prjct-cli/projects/{id}/
 ├── core/          # now.md, next.md, context.md
 ├── progress/      # shipped.md, metrics.md
 ├── planning/      # ideas.md, roadmap.md
 ├── analysis/      # repo-summary.md
+├── agents/        # AI agent definitions
 └── memory/        # context.jsonl
 ```
 
 ## Config Format
+
 ```json
 {
   "version": "0.6.0",
@@ -36,13 +60,44 @@ description: "Initialize prjct project"
 }
 ```
 
-## Response
+## Response: Existing Project
+
 ```
 ✅ prjct initialized!
 
 📁 Data: ~/.prjct-cli/projects/{id}
 📝 Config: .prjct/prjct.config.json
+📊 Analysis: {stack_summary}
+🤖 Agents: {N} agents generated
+
+Listo para trabajar! ¿Qué feature agregamos?
 
-/p:now | /p:idea | /p:status
+/p:feature | /p:analyze
 ```
 
+## Response: Blank Project
+
+```
+✅ prjct initialized!
+
+📐 ARCHITECT MODE
+
+Your idea: "{idea}"
+
+Recommended stack:
+  Option 1: Next.js + TypeScript + Tailwind (⭐ Recommended)
+  Option 2: React + Vite + shadcn/ui
+  Option 3: Vue 3 + Nuxt
+
+Which option? (or describe your preference)
+
+[After user confirms:]
+
+✅ Structure created!
+📋 Initial roadmap: {N} features
+🤖 Agents: generated
+
+¿Empezamos con la primera feature?
+
+/p:feature | /p:ship
+```

package/templates/commands/next.md

@@ -1,16 +1,18 @@
 ---
 allowed-tools: [Read]
-description: "Show priority queue (top 5 non-blocking)"
+description: 'Show priority queue (top 5 non-blocking)'
 ---
 
 # /p:next
 
 ## Flow
+
 1. Check: `core/now.md` → if active task, show warning
 2. Read: `core/next.md` → filter blocked tasks
 3. Return: top 5 actionable
 
 ## Response (active task)
+
 ```
 ⚠️  Active: {current_task}
 Started: {time_ago}
@@ -22,6 +24,7 @@ Complete first: /p:done
 ```
 
 ## Response (no active)
+
 ```
 📋 Priority Queue
 
@@ -29,4 +32,3 @@ Complete first: /p:done
 
 /p:build {1-5} | /p:build "{task}"
 ```
-