prjct-cli 0.10.13 → 0.11.0

package/templates/checklists/infrastructure.md

@@ -0,0 +1,33 @@
+# Infrastructure Checklist
+
+> Applies to: Cloud, On-prem, Hybrid, Edge
+
+## Deployment
+- [ ] Infrastructure as Code (Terraform, Pulumi, CloudFormation, etc.)
+- [ ] Reproducible environments
+- [ ] Rollback strategy defined
+- [ ] Blue-green or canary deployment option
+
+## Observability
+- [ ] Logging strategy defined
+- [ ] Metrics collection configured
+- [ ] Alerting thresholds set
+- [ ] Distributed tracing (if applicable)
+
+## Security
+- [ ] Secrets management (not in code)
+- [ ] Network segmentation
+- [ ] Least privilege access
+- [ ] Encryption at rest and in transit
+
+## Reliability
+- [ ] Backup strategy defined
+- [ ] Disaster recovery plan
+- [ ] Health checks configured
+- [ ] Auto-scaling rules (if applicable)
+
+## Cost Management
+- [ ] Resource sizing appropriate
+- [ ] Unused resources identified
+- [ ] Cost monitoring in place
+- [ ] Budget alerts configured

package/templates/checklists/performance.md

@@ -0,0 +1,33 @@
+# Performance Checklist
+
+> Applies to: Backend, Frontend, Mobile, Database
+
+## Analysis
+- [ ] Bottlenecks identified with profiling
+- [ ] Baseline metrics established
+- [ ] Performance budgets defined
+- [ ] Benchmarks before/after changes
+
+## Optimization Strategies
+- [ ] Algorithmic complexity reviewed (O(n) vs O(n²))
+- [ ] Appropriate data structures used
+- [ ] Caching implemented where beneficial
+- [ ] Lazy loading for expensive operations
+
+## Resource Management
+- [ ] Memory usage optimized
+- [ ] Connection pooling used
+- [ ] Batch operations where applicable
+- [ ] Async/parallel processing considered
+
+## Frontend Specific
+- [ ] Bundle size optimized
+- [ ] Images optimized
+- [ ] Critical rendering path optimized
+- [ ] Network requests minimized
+
+## Backend Specific
+- [ ] Database queries optimized
+- [ ] Response compression enabled
+- [ ] Proper indexing in place
+- [ ] Connection limits configured

package/templates/checklists/security.md

@@ -0,0 +1,33 @@
+# Security Checklist
+
+> ALWAYS ON - Applies to ALL applications
+
+## Input/Output
+- [ ] All user input validated and sanitized
+- [ ] Output encoded appropriately (prevent injection)
+- [ ] File uploads restricted and scanned
+- [ ] No sensitive data in logs or error messages
+
+## Authentication & Authorization
+- [ ] Strong authentication mechanism
+- [ ] Proper session management
+- [ ] Authorization checked at every access point
+- [ ] Principle of least privilege applied
+
+## Data Protection
+- [ ] Sensitive data encrypted at rest
+- [ ] Secure transmission (TLS/HTTPS)
+- [ ] PII handled according to regulations
+- [ ] Data retention policies followed
+
+## Dependencies
+- [ ] Dependencies from trusted sources
+- [ ] Known vulnerabilities checked
+- [ ] Minimal dependency surface
+- [ ] Regular security updates planned
+
+## API Security
+- [ ] Rate limiting implemented
+- [ ] Authentication required for sensitive endpoints
+- [ ] CORS properly configured
+- [ ] API keys/tokens secured

package/templates/checklists/testing.md

@@ -0,0 +1,33 @@
+# Testing Checklist
+
+> Applies to: Unit, Integration, E2E, Performance testing
+
+## Coverage Strategy
+- [ ] Critical paths have high coverage
+- [ ] Happy path tested
+- [ ] Error paths tested
+- [ ] Edge cases covered
+
+## Test Quality
+- [ ] Tests are deterministic (no flaky tests)
+- [ ] Tests are independent (no order dependency)
+- [ ] Tests are fast (optimize slow tests)
+- [ ] Tests are readable (clear intent)
+
+## Test Types
+- [ ] Unit tests for business logic
+- [ ] Integration tests for boundaries
+- [ ] E2E tests for critical flows
+- [ ] Performance tests for bottlenecks
+
+## Mocking Strategy
+- [ ] External services mocked
+- [ ] Database isolated or mocked
+- [ ] Time-dependent code controlled
+- [ ] Random values seeded
+
+## Test Maintenance
+- [ ] Tests updated with code changes
+- [ ] Dead tests removed
+- [ ] Test data managed properly
+- [ ] CI/CD integration working

package/templates/checklists/ux-ui.md

@@ -0,0 +1,37 @@
+# UX/UI Checklist
+
+> Applies to: Web, Mobile, CLI, Desktop, API DX
+
+## User Experience
+- [ ] Clear user journey/flow
+- [ ] Feedback for every action
+- [ ] Loading states shown
+- [ ] Error states handled gracefully
+- [ ] Success confirmation provided
+
+## Interface Design
+- [ ] Consistent visual language
+- [ ] Intuitive navigation
+- [ ] Responsive/adaptive layout (if applicable)
+- [ ] Touch targets adequate (mobile)
+- [ ] Keyboard navigation (web/desktop)
+
+## CLI Specific
+- [ ] Help text for all commands
+- [ ] Clear error messages with suggestions
+- [ ] Progress indicators for long operations
+- [ ] Consistent flag naming conventions
+- [ ] Exit codes meaningful
+
+## API DX (Developer Experience)
+- [ ] Intuitive endpoint/function naming
+- [ ] Consistent response format
+- [ ] Helpful error messages with codes
+- [ ] Good documentation with examples
+- [ ] Predictable behavior
+
+## Information Architecture
+- [ ] Content hierarchy clear
+- [ ] Important actions prominent
+- [ ] Related items grouped
+- [ ] Search/filter for large datasets

package/templates/commands/bug.md

@@ -1,10 +1,36 @@
 ---
-allowed-tools: [Read, Write]
+allowed-tools: [Read, Write, Task, Glob]
 description: 'Report bug with auto-priority'
 ---
 
 # /p:bug
 
+## Agent Delegation (REQUIRED)
+
+Before fixing a bug, delegate to specialist agent:
+
+1. **List agents**: `Glob("~/.prjct-cli/projects/{projectId}/agents/*.md")`
+2. **Analyze bug domain**: frontend, backend, database, etc.
+3. **Delegate via Task tool**:
+
+```
+Task(
+  subagent_type: 'general-purpose',
+  prompt: '
+    ## Agent
+    Read: ~/.prjct-cli/projects/{projectId}/agents/{agent}.md
+
+    ## Bug
+    {bug description}
+
+    ## Flow
+    1. Read agent file
+    2. Apply expertise to fix bug
+    3. Return fix
+  '
+)
+```
+
 ## Severity Keywords
 - **Critical**: crash, down, broken, production
 - **High**: error, fail, issue

package/templates/commands/done.md

@@ -1,15 +1,17 @@
 ---
-allowed-tools: [Read, Write]
-description: 'Complete current task'
+allowed-tools: [Read, Write, Bash]
+description: 'Complete current task with session metrics'
 timestamp-rule: 'GetTimestamp() for all timestamps'
 ---
 
-# /p:done - Complete Current Task
+# /p:done - Complete Current Task with Session Metrics
 
 ## Context Variables
 - `{projectId}`: From `.prjct/prjct.config.json`
 - `{globalPath}`: `~/.prjct-cli/projects/{projectId}`
 - `{nowPath}`: `{globalPath}/core/now.md`
+- `{sessionPath}`: `{globalPath}/sessions/current.json`
+- `{archiveDir}`: `{globalPath}/sessions/archive`
 - `{memoryPath}`: `{globalPath}/memory/context.jsonl`
 - `{metricsPath}`: `{globalPath}/progress/metrics.md`
 
@@ -22,116 +24,236 @@ IF file not found:
   OUTPUT: "No prjct project. Run /p:init first."
   STOP
 
-## Step 2: Validate Active Task
+## Step 2: Check Session State
 
+### Try structured session first
+READ: `{sessionPath}`
+
+IF file exists:
+  PARSE as JSON
+  EXTRACT: {session} object
+  GOTO Step 3 (Session Completion)
+
+### Fallback to legacy now.md
 READ: `{nowPath}`
 
 IF empty OR contains "No current task":
   OUTPUT: "⚠️ No active task to complete. Use /p:now to start one."
   STOP
 
-## Step 3: Extract Task Data
+## Step 3: Session Completion
 
-From NOW file content, extract:
+### Calculate Final Duration
+SET: {now} = GetTimestamp()
 
-1. **Task name**: Text between `**` markers
-   - Pattern: `**(.+?)**`
-   - Example: `**implement auth**` → "implement auth"
+For each event in {session.timeline}:
+  Track start/resume/pause/complete times
+  Calculate total active time
 
-2. **Start time**: Text after "Started:"
-   - Pattern: `Started: (.+)`
-   - Example: `Started: 11/28/2025, 2:30:00 PM`
+SET: {duration} = total active seconds
+SET: {durationFormatted} = format as "Xh Ym" or "Xm"
 
-3. **Calculate duration**:
-   - Current: GetTimestamp()
-   - Duration: current - started
-   - Format: "Xh Ym" (e.g., "2h 15m")
-   - If < 1 hour: "Xm"
-   - If < 1 minute: "< 1m"
+### Calculate Git Metrics
+BASH: `git rev-list --count --since="{session.startedAt}" HEAD 2>/dev/null || echo "0"`
+CAPTURE as {commits}
 
-## Step 4: Clear Task File
+BASH: `git diff --stat HEAD~{commits} 2>/dev/null || git diff --stat`
+PARSE output for:
+  - {filesChanged}: number of files
+  - {linesAdded}: insertions
+  - {linesRemoved}: deletions
 
-WRITE: `{nowPath}`
+### Update Session Object
+```json
+{
+  "id": "{session.id}",
+  "projectId": "{projectId}",
+  "task": "{session.task}",
+  "status": "completed",
+  "startedAt": "{session.startedAt}",
+  "pausedAt": null,
+  "completedAt": "{now}",
+  "duration": {duration},
+  "metrics": {
+    "filesChanged": {filesChanged},
+    "linesAdded": {linesAdded},
+    "linesRemoved": {linesRemoved},
+    "commits": {commits},
+    "snapshots": {session.metrics.snapshots}
+  },
+  "timeline": [
+    ...{session.timeline},
+    {"type": "complete", "at": "{now}"}
+  ]
+}
+```
+
+## Step 4: Archive Session
+
+### Create Archive Directory
+GET: {yearMonth} = YYYY-MM from {now}
+ENSURE: `{archiveDir}/{yearMonth}` exists
+
+BASH: `mkdir -p {archiveDir}/{yearMonth}`
+
+### Write Archived Session
+WRITE: `{archiveDir}/{yearMonth}/{session.id}.json`
+Content: Updated session object from Step 3
+
+## Step 5: Clear Current Session
+
+DELETE: `{sessionPath}`
 
-Content (exact):
+OR WRITE empty state:
+WRITE: `{sessionPath}`
+Content:
+```json
+{}
+```
+
+## Step 6: Update Legacy now.md
+
+WRITE: `{nowPath}`
+Content:
 ```markdown
 # NOW
 
 No current task. Use `/p:now` to set focus.
 ```
 
-## Step 5: Log to Memory
+## Step 7: Log to Memory
 
 APPEND to: `{memoryPath}`
 
 Single line (JSONL format):
 ```json
-{"timestamp":"{GetTimestamp()}","action":"task_completed","task":"{task}","duration":"{duration}"}
+{"timestamp":"{now}","action":"session_completed","sessionId":"{session.id}","task":"{session.task}","duration":{duration},"metrics":{"files":{filesChanged},"added":{linesAdded},"removed":{linesRemoved},"commits":{commits}}}
 ```
 
-## Step 6: Update Metrics (Optional)
+## Step 8: Update Metrics Summary
+
+READ: `{metricsPath}` (create if not exists)
 
-IF `{metricsPath}` exists:
-  READ current content
-  APPEND new entry with task and duration
+### Append Daily Entry
+GET: {date} = YYYY-MM-DD from {now}
+
+INSERT or UPDATE entry for {date}:
+```markdown
+### {date}
+- **{session.task}** ({durationFormatted})
+  - Files: {filesChanged} | +{linesAdded}/-{linesRemoved} | Commits: {commits}
+```
 
 ## Output
 
 SUCCESS:
 ```
-✅ {task} ({duration})
+✅ {session.task} ({durationFormatted})
+
+Session: {session.id}
+Files: {filesChanged} | +{linesAdded}/-{linesRemoved}
+Commits: {commits}
 
 Next:
 • /p:now - Start next task
 • /p:ship - Ship completed work
-• /p:next - See priority queue
+• /p:progress - View metrics
 ```
 
 ## Error Handling
 
-| Error | Response |
-|-------|----------|
-| Config not found | "No prjct project. Run /p:init first." |
-| Now.md empty | "⚠️ No active task. Use /p:now to start." |
-| Parse fails | Use task = "task", duration = "unknown", continue |
-| Write fails | Log warning, continue (non-critical) |
+| Error | Response | Action |
+|-------|----------|--------|
+| Config not found | "No prjct project" | STOP |
+| No session/task | "No active task" | STOP |
+| Git fails | Use zeros for metrics | CONTINUE |
+| Archive fails | Log warning | CONTINUE |
+| Write fails | Log warning | CONTINUE |
 
 ## Examples
 
-### Example 1: Success
-**now.md content:**
+### Example 1: Full Session Completion
+**Session:**
+```json
+{
+  "id": "sess_abc12345",
+  "task": "implement authentication",
+  "status": "active",
+  "startedAt": "2025-12-07T10:00:00.000Z",
+  "timeline": [
+    {"type": "start", "at": "2025-12-07T10:00:00.000Z"}
+  ]
+}
 ```
-# NOW
 
-**implement authentication**
+**Git activity:**
+- 3 commits
+- 5 files changed
+- +120/-30 lines
 
-Started: 11/28/2025, 12:15:00 PM
+**Output:**
 ```
+✅ implement authentication (2h 15m)
 
-**Current time:** 11/28/2025, 2:30:00 PM
-**Duration:** 2h 15m
-**Output:** `✅ implement authentication (2h 15m)`
+Session: sess_abc12345
+Files: 5 | +120/-30
+Commits: 3
 
-### Example 2: No Task
-**now.md content:**
+Next:
+• /p:now - Start next task
+• /p:ship - Ship completed work
+• /p:progress - View metrics
 ```
-# NOW
 
-No current task.
+### Example 2: Session with Pauses
+**Session with multiple pause/resume:**
+```json
+{
+  "id": "sess_xyz98765",
+  "task": "fix login bug",
+  "timeline": [
+    {"type": "start", "at": "2025-12-07T09:00:00.000Z"},
+    {"type": "pause", "at": "2025-12-07T10:00:00.000Z"},
+    {"type": "resume", "at": "2025-12-07T14:00:00.000Z"},
+    {"type": "pause", "at": "2025-12-07T15:30:00.000Z"},
+    {"type": "resume", "at": "2025-12-07T16:00:00.000Z"}
+  ]
+}
+```
+
+**Completion at 17:00:**
+- Active time: 1h + 1.5h + 1h = 3.5h
+- Duration: 3h 30m
+
+**Output:**
 ```
+✅ fix login bug (3h 30m)
 
-**Output:** `⚠️ No active task to complete. Use /p:now to start one.`
+Session: sess_xyz98765
+Files: 2 | +45/-12
+Commits: 1
 
-### Example 3: Quick Task
+Next:
+• /p:now - Start next task
+• /p:ship - Ship completed work
+• /p:progress - View metrics
+```
+
+### Example 3: Legacy Fallback (No Session)
 **now.md content:**
 ```
 # NOW
 
-**fix typo in readme**
+**quick fix**
 
-Started: 11/28/2025, 2:25:00 PM
+Started: 2025-12-07T16:45:00.000Z
 ```
 
-**Current time:** 11/28/2025, 2:30:00 PM
-**Duration:** 5m
-**Output:** `✅ fix typo in readme (5m)`
+**Output:**
+```
+✅ quick fix (15m)
+
+Next:
+• /p:now - Start next task
+• /p:ship - Ship completed work
+```

package/templates/commands/feature.md

@@ -1,11 +1,48 @@
 ---
-allowed-tools: [Read, Write, Bash]
+allowed-tools: [Read, Write, Bash, Task, Glob]
 description: 'Value analysis + roadmap + task breakdown + auto-start'
 timestamp-rule: 'GetTimestamp() and GetDate() for ALL timestamps'
 ---
 
 # /p:feature - Add Feature to Roadmap
 
+## Agent Delegation (REQUIRED)
+
+Before executing any code-related task, delegate to a specialist agent:
+
+### Step 0: Assign Agent
+
+1. **List agents**: `Glob("~/.prjct-cli/projects/{projectId}/agents/*.md")`
+2. **Read routing**: `Read("templates/agentic/agent-routing.md")`
+3. **Analyze task**: Determine domain (frontend, backend, testing, etc.)
+4. **Select agent**: Match task to best agent
+5. **Delegate via Task tool** (pass reference, NOT content):
+
+```
+Task(
+  subagent_type: 'general-purpose',
+  prompt: '
+    ## Agent Assignment
+    Read and apply: ~/.prjct-cli/projects/{projectId}/agents/{agent-name}.md
+
+    ## Task
+    {feature description}
+
+    ## Context
+    - Project: {projectPath}
+    - Feature: {feature}
+
+    ## Flow
+    1. Read agent file FIRST
+    2. Apply agent expertise
+    3. Execute task
+    4. Return results
+  '
+)
+```
+
+**CRITICAL:** Pass file PATH, not content. Subagent reads it (~200 bytes vs 3-5KB).
+
 ## Context Variables
 - `{projectId}`: From `.prjct/prjct.config.json`
 - `{globalPath}`: `~/.prjct-cli/projects/{projectId}`