prjct-cli 0.5.1 → 0.6.0

package/templates/commands/stuck.md

@@ -10,39 +10,27 @@ description: "Get unstuck"
 /p:stuck <issue>
 ```
 
-## Execution
-
-1. Detect issue type (bug/design/perf/feature)
-2. Check context:
-   - `~/.prjct-cli/projects/{id}/analysis/repo-summary.md`
-   - `~/.prjct-cli/projects/{id}/memory/context.jsonl`
-3. Log to `memory/context.jsonl`:
-   ```json
-   {"action":"stuck","issue":"[desc]","category":"[type]","approach":"[steps]","status":"in_progress"}
-   ```
-
-4. Response by type:
-
-   **Bug**: `🔍 1. Check logs 2. Isolate problem 3. Search error`
-
-   **Design**: `🎨 1. Define requirements 2. Start simple 3. Ship MVP`
-
-   **Performance**: `⚡ 1. Profile first 2. Fix slowest 3. Cache operations`
-
-   **Default**: `💡 1. Break into tasks 2. Start smallest 3. Ship it`
-
-5. Suggest breakdown + next actions:
-   ```
-   💡 [Type-specific guidance above]
+## Flow
+1. Detect: issue type (bug/design/perf/feature)
+2. Check: context from analysis + memory
+3. Provide: type-specific guidance
+4. Suggest: breakdown + next actions
+5. Log: `memory/context.jsonl`
+
+## Guidance by Type
+- **Bug**: 🔍 Check logs → Isolate → Search error
+- **Design**: 🎨 Define requirements → Start simple → Ship MVP
+- **Performance**: ⚡ Profile first → Fix slowest → Cache ops
+- **Default**: 💡 Break into tasks → Start smallest → Ship it
+
+## Response
+```
+💡 {type_guidance}
 
-   Let's break it down:
-   1. [subtask 1] (~15min)
-   2. [subtask 2] (~30min)
+Let's break it down:
+1. {subtask} (~{time})
+2. {subtask} (~{time})
 
-   Ready to start?
-   • "start the first part" → Begin small
-   • "add these as tasks" → Queue them
-   • "think more" → Capture ideas
+/p:now "{first}" | /p:task
+```
 
-   Or: /p:now "[first subtask]" | /p:task | /p:idea
-   ```

package/templates/commands/sync.md

@@ -1,220 +1,30 @@
 ---
-allowed-tools: [Read, Write, Bash, Glob, Grep, TodoWrite]
-description: "Sync project state and update AI agents based on latest analysis"
+allowed-tools: [Read, Bash, TodoWrite]
+description: "Sync project state and agents"
 ---
 
-# /p:sync - Sync Project State
+# /p:sync
 
-## Purpose
-Re-analyze the project and update all AI agents with current project state, stack changes, and new requirements.
+## Flow
+1. Run: `/p:analyze` → get current state
+2. Compare: with previous analysis
+3. Update: all existing agents with new context
+4. Add: newly required agents
+5. Remove: obsolete agents (with confirmation)
+6. Log: changes to `memory/context.jsonl`
 
-## Global Architecture
-This command uses the global prjct architecture:
-- Data stored in: `~/.prjct-cli/projects/{id}/`
-- Config stored in: `{project}/.prjct/prjct.config.json`
-- Agents updated in: `~/.claude/agents/`
-
-## Usage
-```
-/p:sync
-```
-
-## When to Run
-- After major dependency changes
-- When adding new frameworks or tools
-- After significant architecture changes
-- When project type changes (e.g., adding mobile support)
-- Periodically to keep agents up-to-date
-
-## Execution Flow
-
-### 1. Re-run Project Analysis
-
-Execute `/p:analyze` to get current project state:
-```javascript
-// This will:
-// 1. Scan all files and directories
-// 2. Detect current stack and frameworks
-// 3. Check git status
-// 4. Compare with previous analysis
-// 5. Identify what changed
-```
-
-### 2. Detect Changes
-
-Compare new analysis with previous:
-```javascript
-const previousAnalysis = await readFile('.prjct/analysis/repo-summary.md')
-const currentAnalysis = await runAnalyze()
-
-const changes = {
-  newDependencies: [],
-  removedDependencies: [],
-  newFrameworks: [],
-  stackChanges: [],
-  structureChanges: []
-}
-
-// Detect what changed
-if (currentAnalysis.frameworks !== previousAnalysis.frameworks) {
-  changes.newFrameworks = difference(current, previous)
-}
-```
-
-### 3. Update Existing Agents
-
-Regenerate all current agents with new context:
-```javascript
-const agentGenerator = require('../core/agent-generator')
-
-// Update all existing agents
-const updated = await agentGenerator.updateExistingAgents(currentAnalysis)
-
-console.log(`↻ Updated ${updated.length} agents with new context`)
-```
-
-### 4. Add New Agents
-
-Generate any newly required agents:
-```javascript
-// Detect newly required agents
-const existingAgents = await listAgentFiles()
-const requiredAgents = detectRequiredAgents(currentAnalysis)
-const newAgents = requiredAgents.filter(a => !existingAgents.includes(a))
-
-if (newAgents.length > 0) {
-  for (const agentType of newAgents) {
-    await agentGenerator.generateAgent(agentType, currentAnalysis)
-    console.log(`✅ Added ${agentType} agent`)
-  }
-}
+## Response
 ```
+🔄 Sync complete!
 
-### 5. Remove Obsolete Agents (Optional)
-
-Ask user if agents should be removed:
-```javascript
-const obsoleteAgents = existingAgents.filter(a => !requiredAgents.includes(a))
-
-if (obsoleteAgents.length > 0) {
-  console.log(`\n⚠️  The following agents may no longer be needed:`)
-  obsoleteAgents.forEach(a => console.log(`   - ${a}`))
-
-  const shouldRemove = await confirmWithUser('\nRemove these agents? (y/n): ')
-
-  if (shouldRemove) {
-    await agentGenerator.cleanupObsoleteAgents(requiredAgents)
-  }
-}
-```
-
-### 6. Update Analysis File
-
-Save new analysis:
-```bash
-# Backup previous analysis
-cp .prjct/analysis/repo-summary.md .prjct/analysis/repo-summary.backup.md
-
-# Save new analysis
-# (already saved by /p:analyze)
-```
+📊 Changes:
+• {N} agents updated
+• {N} agents added
+• {N} agents removed
 
-### 7. Update Memory Log
+Stack changes:
+• {changes_list}
 
-Log sync action:
-```jsonl
-{"timestamp":"2025-10-02T14:30:00Z","action":"sync","author":"Name","changes":{"addedAgents":["mobile"],"updatedAgents":["fe","be"],"removedAgents":[],"stackChanges":["added react-native"]}}
+/p:status | /p:context
 ```
 
-## Output Examples
-
-### No Changes
-```
-🔄 Syncing project state...
-
-📊 Analysis Complete
-   No significant changes detected
-
-🤖 Agents Status
-   ✓ All 7 agents are up-to-date
-
-✅ Sync complete! Everything is current.
-```
-
-### With Changes
-```
-🔄 Syncing project state...
-
-📊 Changes Detected
-   ✅ New dependency: @tanstack/react-query
-   ✅ New framework: Expo (React Native)
-   ℹ️  Architecture: Still feature-based
-
-🤖 Agent Updates
-   ↻ FE agent - Added React Query patterns
-   ↻ BE agent - Updated API integration context
-   ✅ Mobile agent - ADDED (React Native detected)
-   ✓ Other agents - No changes needed
-
-⚠️  Obsolete Agents
-   - devops (Docker removed from project)
-
-   Remove obsolete agents? (y/n): _
-
-✅ Sync complete!
-   - 2 agents updated
-   - 1 agent added
-   - 1 agent removed
-```
-
-### Stack Migration
-```
-🔄 Syncing project state...
-
-📊 Major Changes Detected
-   ⚠️  Framework changed: Vue → React
-   ⚠️  Build tool changed: Webpack → Vite
-   ✅ New: TypeScript added
-
-🤖 Full Agent Regeneration
-   ↻ PM - Updated with React patterns
-   ↻ UX - Updated component guidelines
-   ↻ FE - COMPLETELY REGENERATED for React + TS
-   ↻ BE - Updated API patterns
-   ↻ QA - Updated test framework context
-   ↻ Scribe - Updated documentation style
-
-✅ Sync complete! All agents updated for new stack.
-
-💡 Tip: Review agent descriptions to see new capabilities.
-```
-
-## Error Handling
-
-- **No .prjct/**: Error - Project not initialized, run `/p:init` first
-- **No analysis file**: Warning - Running first-time analysis
-- **Agent generation fails**: Warn but continue with others
-- **Permission issues**: Suggest checking `~/.claude/agents/` permissions
-
-## Notes
-
-- Sync is safe to run anytime
-- Existing agents are updated, not deleted (unless confirmed)
-- Git status is refreshed during sync
-- Analysis diff helps track project evolution
-- Agents get project-specific context from analysis
-
-## Related Commands
-
-- `/p:analyze` - Just analyze without updating agents
-- `/p:init` - Initialize project (first-time setup)
-- `/p:context` - View current project context
-
-## Implementation Notes
-
-The sync command should:
-1. Be idempotent (safe to run multiple times)
-2. Preserve manual agent customizations (warn if detected)
-3. Create backups before major changes
-4. Provide clear diff of what changed
-5. Allow granular control (which agents to update)

package/templates/commands/task.md

@@ -1,97 +1,35 @@
 ---
-allowed-tools: [Read, Write, Edit, TodoWrite, Bash, Glob]
-description: "Break down and execute complex tasks systematically"
+allowed-tools: [Read, Write, TodoWrite]
+description: "Break down complex tasks"
 ---
 
-## Global Architecture
-This command uses the global prjct architecture:
-- Data stored in: `~/.prjct-cli/projects/{id}/`
-- Config stored in: `{project}/.prjct/prjct.config.json`
-- Commands synchronized across all editors
-
-
-
-# /p:task - Complex Task Execution
-
-## Purpose
-Handle complex features by breaking them down, executing systematically, and tracking progress. No overwhelm.
+# /p:task
 
 ## Usage
 ```
 /p:task <description>
 ```
 
-## Execution
-1. Analyze task complexity
-2. Break into 3-7 subtasks automatically
-3. Create execution plan in `.prjct/planning/tasks/`
-4. Execute each subtask with validation
-5. Track progress and update metrics
-
-## Implementation
+## Flow
+1. Analyze: task complexity
+2. Break down: into 3-7 subtasks
+3. Create: execution plan
+4. Execute: each subtask with validation
+5. Track: progress in `planning/tasks/`
 
-**Task breakdown**:
-- Identify main components needed
-- Order by dependencies
-- Estimate time for each
-- Create actionable subtasks
-
-**Example breakdown**:
+## Response
 ```
-/p:task "implement user authentication"
-
-📋 Task Plan Created:
-
-1. Database schema (15 min)
-   - User table with email/password
-   - Sessions table
-
-2. Auth middleware (30 min)
-   - JWT token generation
-   - Route protection
+📋 Task Plan: {description}
 
-3. API endpoints (45 min)
-   - POST /auth/signup
-   - POST /auth/login
-   - POST /auth/logout
+Breakdown:
+1. {subtask} (~{time})
+2. {subtask} (~{time})
+3. {subtask} (~{time})
 
-4. Frontend forms (30 min)
-   - Login component
-   - Signup component
-
-5. Testing (20 min)
-   - Auth flow tests
-   - Security tests
+Est total: {total_time}
 
 🚀 Starting execution...
-[1/5] Creating database schema... ✅
-[2/5] Building auth middleware... 🔄
-```
-
-**Progress tracking**:
-- Real-time status updates
-- Save progress between sessions
-- Resume interrupted tasks
-- Log to `.prjct/memory/context.jsonl`
-
-**Response format**:
-```
-✅ Task completed: User authentication
-
-📊 Execution Summary:
-• Time: 2h 15min (estimated 2h 20min)
-• Subtasks: 5/5 completed
-• Tests: All passing
-• Files: 12 created/modified
-
-📝 Logged to: .prjct/planning/tasks/auth_system.md
-
-💡 Next: /p:ship "user authentication"
+[1/{N}] {subtask}... ✅
+[2/{N}] {subtask}... 🔄
 ```
 
-## Features
-- Automatic task decomposition
-- Progress persistence
-- Time tracking
-- Dependency management
-- Smart validation gates

package/templates/commands/test.md

@@ -1,94 +1,45 @@
 ---
-allowed-tools: [Bash, Read, Edit, Glob]
-description: "Run tests and auto-fix simple failures"
+allowed-tools: [Bash, Read, Edit]
+description: "Run tests with auto-fix"
 ---
 
-## Global Architecture
-This command uses the global prjct architecture:
-- Data stored in: `~/.prjct-cli/projects/{id}/`
-- Config stored in: `{project}/.prjct/prjct.config.json`
-- Commands synchronized across all editors
-
-
-
-# /p:test - Smart Test Execution
-
-## Purpose
-Run tests, show failures clearly, and auto-fix obvious issues. Ship with confidence.
+# /p:test
 
 ## Usage
 ```
-/p:test [all|unit|e2e|failed]
-```
-
-Default: all
-
-## Execution
-1. Detect test runner (jest/vitest/mocha/pytest)
-2. Run tests with appropriate command
-3. Parse and display results with clarity
-4. Auto-fix simple test failures
-5. Update `.prjct/progress/metrics.md` with coverage
-
-## Implementation
-
-**Test detection**:
-```bash
-# Auto-detect test command from package.json or config
-- npm test / npm run test
-- pytest / python -m pytest
-- go test ./...
-- cargo test
+/p:test [all|unit|e2e|failed|fix]  # Default: all
 ```
 
-**Auto-fixable issues**:
-- Snapshot updates → Update automatically
-- Timeout errors → Increase timeout
-- Import errors → Fix imports
-- Expected vs received → Show diff clearly
+## Flow
+1. Detect: test runner (jest/vitest/pytest/etc)
+2. Run: tests with appropriate command
+3. Parse: results
+4. Auto-fix: simple failures (snapshots, timeouts, imports)
+5. Update: coverage in `progress/metrics.md`
 
-**Response format for success**:
+## Response (success)
 ```
 ✅ All tests passing!
 
-📊 Test Results:
-• Unit: 45/45 passed
-• Integration: 12/12 passed
-• E2E: 8/8 passed
+📊 Results:
+• Unit: {N}/{N}
+• Integration: {N}/{N}
+• E2E: {N}/{N}
 
-🎯 Coverage: 87% (+2%)
-⚡ Time: 4.2s
+🎯 Coverage: {X}%
+⚡ Time: {X}s
 
-🚀 Ready to ship!
+/p:ship
 ```
 
-**Response format for failures**:
+## Response (failures)
 ```
-❌ 3 tests failing
+❌ {N} tests failing
 
-1️⃣ UserService.test.js:
-   Expected: "John Doe"
-   Received: "John"
+{failure_details}
 
-   💡 Auto-fix available: /p:test fix
+💡 Auto-fix: /p:test fix
 
-2️⃣ auth.e2e.js:
-   Timeout after 5000ms
-
-   💡 Increasing timeout to 10000ms...
-
-📊 Summary: 62/65 passed (95%)
+📊 Summary: {passed}/{total} ({X}%)
 ```
 
-**Quick commands**:
-- `/p:test` - Run all tests
-- `/p:test failed` - Re-run only failed tests
-- `/p:test watch` - Run in watch mode
-- `/p:test fix` - Apply available auto-fixes
-
-## Features
-- Smart failure detection
-- Clear error messages
-- Auto-fix common issues
-- Coverage tracking
-- Performance monitoring