universal-agent-memory 0.3.0 → 0.3.1

package/README.md

@@ -1,215 +1,309 @@
-# Universal Agent Memory
+# Universal Agent Memory (UAM)
 
-Universal AI agent memory system for Claude Code, Factory.AI, VSCode, OpenCode, and web-based LLMs.
+[![npm version](https://img.shields.io/npm/v/universal-agent-memory.svg)](https://www.npmjs.com/package/universal-agent-memory)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 
-Provides:
-- **CLAUDE.md template system** with automatic project analysis and generation
-- **Memory system** with flexible backends:
-  - **Desktop**: SQLite short-term + local Qdrant or cloud backends
-  - **Web**: IndexedDB short-term + GitHub/Qdrant Cloud long-term
-- **Git worktree workflow** automation for isolated development
-- **Cross-platform compatibility** for all major AI coding assistants (desktop and web)
+A complete autonomous agent operating system for AI coding assistants. Provides memory, task management, agent coordination, and workflow automation for Claude Code, Factory.AI, VSCode, OpenCode, and web-based LLMs.
+
+## What It Does
+
+UAM transforms AI coding assistants into autonomous agents with:
+
+- **4-Layer Memory System** - Working, session, semantic, and knowledge graph memory
+- **Task Management** - Git-backed issue tracking with dependency DAG (superior to Beads)
+- **Agent Coordination** - Multi-agent overlap detection and merge conflict prevention
+- **Deploy Batching** - Batch commits/pushes to save CI minutes
+- **Git Worktree Automation** - Isolated development branches with PR workflows
+- **CLAUDE.md Generation** - Auto-generated project context files
 
 ## Installation
 
-### Desktop (CLI)
+### Quick Install (Recommended)
 
 ```bash
-# Automatic installer with Docker detection
-bash <(curl -fsSL https://raw.githubusercontent.com/DammianMiller/universal-agent-memory/main/scripts/install-desktop.sh)
-
-# Or manually with npm
+# Install globally
 npm install -g universal-agent-memory
 
-# Or use npx
-npx universal-agent-memory init --desktop
+# Initialize in your project
+cd your-project
+uam init --interactive
 ```
 
-### Web Browsers (claude.ai, factory.ai)
+### One-Line Installers
 
 ```bash
-# Quick web setup
-bash <(curl -fsSL https://raw.githubusercontent.com/DammianMiller/universal-agent-memory/main/scripts/install-web.sh)
+# Desktop (with Docker for Qdrant)
+bash <(curl -fsSL https://raw.githubusercontent.com/DammianMiller/universal-agent-memory/main/scripts/install-desktop.sh)
 
-# Or manually
-npx universal-agent-memory init --web
+# Web browsers (claude.ai, factory.ai)
+bash <(curl -fsSL https://raw.githubusercontent.com/DammianMiller/universal-agent-memory/main/scripts/install-web.sh)
 ```
 
-Web installations use:
-- **IndexedDB** for short-term memory (replaces SQLite)
-- **GitHub** or **Qdrant Cloud** for long-term memory (opt-in via env vars)
+### Using npx (No Install)
+
+```bash
+npx universal-agent-memory init --interactive
+```
 
 ## Quick Start
 
 ```bash
-# Desktop initialization (default)
-uam init --desktop
+# 1. Initialize project
+uam init --with-memory --with-worktrees
+
+# 2. Start memory services (requires Docker)
+uam memory start
 
-# Web initialization (for claude.ai, factory.ai)
-uam init --web
+# 3. Generate CLAUDE.md
+uam generate
 
-# Interactive mode (asks questions)
-uam init --interactive
+# 4. Create your first task
+uam task create --title "My first task" --type task
 
-# Or with specific options
-uam init --platform factory --with-memory --with-worktrees
+# 5. Start working
+uam task claim <task-id>
+uam worktree create my-feature
 ```
 
-This will:
-1. Analyze your project structure
-2. Generate a customized `CLAUDE.md`
-3. Set up platform-specific directories (`.factory/`, `.claude/`, etc.)
-4. Optionally configure memory system and worktree workflow
+## Core Features
 
-## Commands
+### Task Management
 
-### Initialize Project
+A complete task tracking system integrated with memory and coordination.
 
 ```bash
-uam init [options]
-
-Options:
-  -p, --platform <platforms...>  Target platforms (claude, factory, vscode, opencode, claudeWeb, factoryWeb, all)
-  --desktop                      Desktop mode (SQLite + local Qdrant)
-  --web                          Web mode (IndexedDB + cloud backends)
-  --interactive                  Interactive setup with prompts
-  --with-memory                  Set up memory system
-  --with-worktrees               Set up git worktree workflow
-  --force                        Overwrite existing configuration
+# Create tasks
+uam task create --title "Fix auth bug" --type bug --priority 0
+uam task create --title "Add dark mode" --type feature --priority 2
+
+# View tasks
+uam task list                              # All open tasks
+uam task ready                             # Tasks with no blockers
+uam task blocked                           # Blocked tasks
+uam task stats                             # Statistics
+
+# Work on tasks
+uam task claim <id>                        # Claim task (announces to other agents)
+uam task show <id>                         # View details
+uam task release <id> --reason "Fixed"     # Complete task
+
+# Dependencies
+uam task dep --from <child> --to <parent>  # Add blocker
+uam task undep --from <child> --to <parent># Remove blocker
+
+# Git sync (version control your tasks)
+uam task sync                              # Export to JSONL
+uam task compact --days 90                 # Archive old tasks
 ```
 
-### Analyze Project
+**Task Types**: `task`, `bug`, `feature`, `chore`, `epic`, `story`
 
-```bash
-uam analyze [options]
+**Priority Levels**: P0 (critical) → P4 (backlog)
 
-Options:
-  -o, --output <format>  Output format (json, yaml, md)
-  --save                 Save analysis to file
-```
+### Memory System
 
-### Generate Files
+4-layer architecture for complete context retention.
 
 ```bash
-uam generate [options]
+# Start services
+uam memory start                           # Start Qdrant (Docker)
+uam memory status                          # Check status
+uam memory stop                            # Stop services
+
+# Query memories
+uam memory query "authentication JWT"      # Semantic search
 
-Options:
-  -f, --force         Overwrite without confirmation
-  -d, --dry-run       Preview without writing
-  -p, --platform      Generate for specific platform only
+# Store learnings
+uam memory store "lesson learned" --tags "auth,security" --importance 8
 ```
 
-**Smart Merging**: When a `CLAUDE.md` or `AGENT.md` file already exists, the CLI will offer to:
-- **Merge** (recommended): Updates standard sections while preserving your custom sections
-- **Overwrite**: Replace the entire file with newly generated content
-- **Cancel/Skip**: Leave the existing file unchanged
+**Layers:**
 
-The merge strategy:
-- Updates the preamble (project name, description) from new analysis
-- Replaces standard sections (Memory System, Browser Usage, Quick Reference, etc.) with updated versions
-- Preserves any custom sections you've added
-- Appends custom sections at the end of the file
+| Layer | Storage | Purpose | Speed |
+|-------|---------|---------|-------|
+| L1: Working | SQLite | Recent actions (last 50) | ~0.15ms |
+| L2: Session | SQLite | Session decisions | ~0.2ms |
+| L3: Semantic | Qdrant | Reusable learnings | ~1-2ms |
+| L4: Knowledge Graph | SQLite | Entity relationships | ~0.17ms |
 
-### Memory Management
+### Agent Coordination
+
+Multi-agent support with overlap detection and messaging.
 
 ```bash
-# Check status
-uam memory status
+# Register agent
+uam agent register --name "feature-agent" --capabilities "coding,review"
 
-# Start memory services (Qdrant)
-uam memory start
+# Announce work (enables overlap detection)
+uam agent announce --id <agent-id> --resource "src/auth/" --intent editing
 
-# Stop services
-uam memory stop
+# Check for conflicts
+uam agent overlaps --resource "src/auth/"
 
-# Query long-term memory
-uam memory query "search term" --limit 10
+# Complete work
+uam agent complete --id <agent-id> --resource "src/auth/"
 
-# Store a memory
-uam memory store "lesson learned" --tags "tag1,tag2" --importance 8
+# Status
+uam agent status                           # View all agents
+uam coord status                           # Coordination overview
 ```
 
-### Git Worktrees
+**Conflict Risk Levels**: `none`, `low`, `medium`, `high`, `critical`
 
-```bash
-# Create new worktree
-uam worktree create my-feature
+### Deploy Batching
 
-# List worktrees
-uam worktree list
+Batch multiple commits/pushes to reduce CI runs.
+
+```bash
+# Queue commits
+uam deploy queue --agent-id <id> --action-type commit \
+  --message "feat: add feature" --files "src/feature.ts"
 
-# Create PR from worktree
-uam worktree pr 001
+# View queue
+uam deploy status
 
-# Cleanup after merge
-uam worktree cleanup 001
+# Execute batched deploys
+uam deploy flush                           # Squashes commits, single push
 ```
 
-### Droids/Agents
+### Git Worktrees
+
+Isolated development branches with automated PR workflow.
 
 ```bash
-# List available droids
-uam droids list
+# Create worktree
+uam worktree create my-feature             # Creates feature/NNN-my-feature
+
+# List worktrees
+uam worktree list
 
-# Add a new droid
-uam droids add my-droid --template code-reviewer
+# Create PR
+uam worktree pr <id>                       # Push + create PR
 
-# Import from another platform
-uam droids import ~/.claude/agents/
+# Cleanup
+uam worktree cleanup <id>                  # Remove worktree + delete branch
 ```
 
-### Platform Sync
+### CLAUDE.md Generation
+
+Auto-generate context files for AI assistants.
 
 ```bash
-# Sync between platforms
-uam sync --from claude --to factory
+# Analyze project
+uam analyze --output json
+
+# Generate CLAUDE.md
+uam generate                               # Interactive merge with existing
+uam generate --force                       # Overwrite
+uam generate --dry-run                     # Preview only
 ```
 
+## Command Reference
+
+### Core Commands
+
+| Command | Description |
+|---------|-------------|
+| `uam init` | Initialize UAM in a project |
+| `uam analyze` | Analyze project structure |
+| `uam generate` | Generate CLAUDE.md |
+| `uam sync` | Sync between platforms |
+
+### Task Commands
+
+| Command | Description |
+|---------|-------------|
+| `uam task create` | Create a new task |
+| `uam task list` | List tasks (with filters) |
+| `uam task show <id>` | Show task details |
+| `uam task claim <id>` | Claim task for work |
+| `uam task release <id>` | Complete and release task |
+| `uam task ready` | Show unblocked tasks |
+| `uam task blocked` | Show blocked tasks |
+| `uam task dep` | Add dependency |
+| `uam task stats` | Show statistics |
+| `uam task sync` | Sync with JSONL |
+
+### Memory Commands
+
+| Command | Description |
+|---------|-------------|
+| `uam memory start` | Start Qdrant (Docker) |
+| `uam memory stop` | Stop memory services |
+| `uam memory status` | Check service status |
+| `uam memory query` | Semantic search |
+| `uam memory store` | Store a learning |
+
+### Agent Commands
+
+| Command | Description |
+|---------|-------------|
+| `uam agent register` | Register new agent |
+| `uam agent announce` | Announce work on resource |
+| `uam agent overlaps` | Check for conflicts |
+| `uam agent complete` | Mark work complete |
+| `uam agent status` | Show agent status |
+| `uam agent broadcast` | Send to all agents |
+| `uam agent send` | Direct message |
+| `uam agent receive` | Get pending messages |
+
+### Coordination Commands
+
+| Command | Description |
+|---------|-------------|
+| `uam coord status` | Overview of coordination |
+| `uam coord flush` | Execute pending deploys |
+| `uam coord cleanup` | Clean stale data |
+
+### Deploy Commands
+
+| Command | Description |
+|---------|-------------|
+| `uam deploy queue` | Queue a deploy action |
+| `uam deploy status` | View deploy queue |
+| `uam deploy batch` | Create batch from queue |
+| `uam deploy execute` | Execute a batch |
+| `uam deploy flush` | Batch and execute all |
+
+### Worktree Commands
+
+| Command | Description |
+|---------|-------------|
+| `uam worktree create` | Create feature worktree |
+| `uam worktree list` | List all worktrees |
+| `uam worktree pr` | Create PR from worktree |
+| `uam worktree cleanup` | Remove worktree |
+
+### Droids Commands
+
+| Command | Description |
+|---------|-------------|
+| `uam droids list` | List available droids |
+| `uam droids add` | Add a new droid |
+| `uam droids import` | Import from path |
+
 ## Configuration
 
 Configuration is stored in `.uam.json`:
 
 ```json
 {
-  "$schema": "https://raw.githubusercontent.com/DammianMiller/universal-agent-memory/main/schema.json",
   "version": "1.0.0",
   "project": {
     "name": "my-project",
-    "description": "Project description",
     "defaultBranch": "main"
   },
-  "platform": "claudeCode",
-  "platforms": {
-    "claudeCode": { "enabled": true },
-    "claudeWeb": { "enabled": false },
-    "factory": { "enabled": true },
-    "factoryWeb": { "enabled": false },
-    "vscode": { "enabled": false },
-    "opencode": { "enabled": false }
-  },
   "memory": {
     "shortTerm": {
       "enabled": true,
       "path": "./agents/data/memory/short_term.db",
-      "maxEntries": 50,
-      "webDatabase": "agentContext",
-      "forceDesktop": false
+      "maxEntries": 50
     },
     "longTerm": {
       "enabled": true,
       "provider": "qdrant",
       "endpoint": "localhost:6333",
-      "collection": "agent_memory",
-      "github": {
-        "enabled": false,
-        "repo": "owner/repo",
-        "path": ".uam/memory"
-      },
-      "qdrantCloud": {
-        "enabled": false,
-        "url": "https://xxxxx.aws.cloud.qdrant.io:6333",
-        "collection": "agent_memory"
-      }
+      "collection": "agent_memory"
     }
   },
   "worktrees": {
@@ -222,100 +316,91 @@ Configuration is stored in `.uam.json`:
 
 ## Platform Support
 
-| Platform | Environment | Context File | Agents | Commands |
-|----------|-------------|--------------|--------|----------|
-| Claude Code | Desktop | `CLAUDE.md` | `.claude/agents/` | `.claude/commands/` |
-| claude.ai | Web | `CLAUDE.md` | Project context | N/A |
-| Factory.AI | Desktop | `CLAUDE.md` | `.factory/droids/` | `.factory/commands/` |
-| factory.ai | Web | `CLAUDE.md` | Project context | N/A |
-| VSCode | Desktop | `CLAUDE.md` | Extension-based | Tasks |
-| OpenCode | Desktop | `opencode.json` | `.opencode/agent/` | `.opencode/command/` |
-
-## Built-in Droid Templates
-
-- `code-reviewer` - Reviews diffs for correctness and risks
-- `security-reviewer` - Finds security issues in code
-- `performance-reviewer` - Identifies performance bottlenecks
-- `test-writer` - Generates unit tests
-
-## Memory System
-
-### Desktop Environments
+| Platform | Environment | Context File | Agents/Droids |
+|----------|-------------|--------------|---------------|
+| Claude Code | Desktop | `CLAUDE.md` | `.claude/agents/` |
+| claude.ai | Web | `CLAUDE.md` | Project context |
+| Factory.AI | Desktop | `CLAUDE.md` | `.factory/droids/` |
+| factory.ai | Web | `CLAUDE.md` | Project context |
+| VSCode | Desktop | `CLAUDE.md` | Extension-based |
+| OpenCode | Desktop | `opencode.json` | `.opencode/agent/` |
 
-#### Short-term Memory (SQLite)
+## Workflow Engine
 
-Stores the last 50 actions/observations for immediate context. Automatically pruned.
+UAM enforces a 5-phase workflow for every agent action:
 
-Location: `./agents/data/memory/short_term.db`
-
-#### Long-term Memory
-
-**Local Qdrant** (requires Docker):
-```bash
-uam memory start
-```
-
-**GitHub Backend** (opt-in):
-```bash
-export GITHUB_TOKEN=your_token
-# Stores memories as JSON files in git repository
 ```
-
-**Qdrant Cloud** (opt-in, 1GB free tier):
-```bash
-export QDRANT_API_KEY=your_key
-export QDRANT_URL=https://xxxxx.aws.cloud.qdrant.io:6333
+START → TASK → CONTEXT → WORK → COMPLETE
 ```
 
-### Web Environments (claude.ai, factory.ai)
+1. **START**: Check existing tasks, read memory
+2. **TASK**: Create/claim task before any work
+3. **CONTEXT**: Query memory, check skills
+4. **WORK**: Create worktree, make changes, test, PR
+5. **COMPLETE**: Update memory, release task
 
-#### Short-term Memory (IndexedDB)
+Each phase has **gates** that must pass before proceeding.
 
-Browser-native storage for recent context. Per-project isolation with automatic pruning.
+## Memory Backends
 
-Database: `agentContext/memories`
+### Desktop
 
-#### Long-term Memory (Cloud Backends)
+- **Short-term**: SQLite (local file)
+- **Long-term**: Qdrant (Docker) or Qdrant Cloud
 
-Requires environment variables for opt-in:
+### Web (claude.ai, factory.ai)
 
-**GitHub**:
-```bash
-export GITHUB_TOKEN=your_token
-```
+- **Short-term**: IndexedDB (browser)
+- **Long-term**: GitHub or Qdrant Cloud
 
-**Qdrant Cloud** (1GB free tier):
 ```bash
+# Cloud backends (optional)
 export QDRANT_API_KEY=your_key
-export QDRANT_URL=https://xxxxx.aws.cloud.qdrant.io:6333
+export QDRANT_URL=https://xxx.aws.cloud.qdrant.io:6333
+export GITHUB_TOKEN=your_token
 ```
 
-### What Memory Stores
+## Built-in Droids
 
-Vector database for semantic search of past learnings:
-- Discoveries about environment/capabilities
-- Successful strategies
-- Failed approaches to avoid
-- Important facts learned
+| Droid | Purpose |
+|-------|---------|
+| `code-quality-guardian` | Code review, complexity, SOLID |
+| `security-auditor` | OWASP, secrets, injection |
+| `performance-optimizer` | Algorithms, memory, caching |
+| `documentation-expert` | JSDoc, README, accuracy |
 
 ## Development
 
 ```bash
-# Clone and install
+# Clone
 git clone https://github.com/DammianMiller/universal-agent-memory.git
 cd universal-agent-memory
+
+# Install
 npm install
 
 # Build
 npm run build
 
-# Run locally
-npm start -- init
-
-# Run tests
+# Test
 npm test
+
+# Run locally
+npm start -- init --interactive
 ```
 
+## Requirements
+
+- Node.js 18+
+- Docker (for local Qdrant)
+- Git
+
 ## License
 
 MIT
+
+## Links
+
+- [GitHub Repository](https://github.com/DammianMiller/universal-agent-memory)
+- [npm Package](https://www.npmjs.com/package/universal-agent-memory)
+- [Issue Tracker](https://github.com/DammianMiller/universal-agent-memory/issues)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "universal-agent-memory",
-  "version": "0.3.0",
+  "version": "0.3.1",
   "description": "Universal AI agent memory system - CLAUDE.md templates, memory, worktrees for Claude Code, Factory.AI, VSCode, OpenCode",
   "type": "module",
   "main": "dist/index.js",

package/templates/CLAUDE.template.md

@@ -1,15 +1,34 @@
 <!--
-  CLAUDE.md Universal Template - Optimized v3.0
+  CLAUDE.md Universal Template - v3.1
   
   Single-source-of-truth workflow engine with zero duplication.
   All variables populated by UAM generator from project analysis.
   
-  Template Variables: {{PROJECT_NAME}}, {{PROJECT_PATH}}, {{DEFAULT_BRANCH}},
-  {{MEMORY_DB_PATH}}, {{MEMORY_QUERY_CMD}}, {{MEMORY_STORE_CMD}}, {{MEMORY_START_CMD}},
-  {{LONG_TERM_BACKEND}}, {{LONG_TERM_ENDPOINT}}, {{LONG_TERM_COLLECTION}}, {{SHORT_TERM_LIMIT}},
-  {{WORKTREE_CREATE_CMD}}, {{WORKTREE_PR_CMD}}, {{WORKTREE_CLEANUP_CMD}}, {{WORKTREE_DIR}},
-  {{BRANCH_PREFIX}}, {{SKILLS_PATH}}, {{DROIDS_PATH}}, {{COMMANDS_PATH}}, {{DOCS_PATH}},
-  {{SCREENSHOTS_PATH}}, {{TEST_COMMAND}}, {{STRUCTURE_DATE}}
+  Core Variables:
+    {{PROJECT_NAME}}, {{PROJECT_PATH}}, {{DEFAULT_BRANCH}}, {{STRUCTURE_DATE}}
+  
+  Memory System:
+    {{MEMORY_DB_PATH}}, {{MEMORY_QUERY_CMD}}, {{MEMORY_STORE_CMD}}, {{MEMORY_START_CMD}},
+    {{MEMORY_STATUS_CMD}}, {{MEMORY_STOP_CMD}}, {{LONG_TERM_BACKEND}}, {{LONG_TERM_ENDPOINT}},
+    {{LONG_TERM_COLLECTION}}, {{SHORT_TERM_LIMIT}}
+  
+  Worktree:
+    {{WORKTREE_CREATE_CMD}}, {{WORKTREE_PR_CMD}}, {{WORKTREE_CLEANUP_CMD}},
+    {{WORKTREE_DIR}}, {{BRANCH_PREFIX}}
+  
+  Paths:
+    {{SKILLS_PATH}}, {{DROIDS_PATH}}, {{COMMANDS_PATH}}, {{DOCS_PATH}}, {{SCREENSHOTS_PATH}}
+  
+  Commands:
+    {{TEST_COMMAND}}, {{BUILD_COMMAND}}, {{LINT_COMMAND}}
+  
+  Conditional Sections (auto-populated from analysis):
+    REPOSITORY_STRUCTURE, ARCHITECTURE_OVERVIEW, DATABASE_ARCHITECTURE,
+    CORE_COMPONENTS, CLUSTER_CONTEXTS, PROJECT_URLS, KEY_WORKFLOWS,
+    ESSENTIAL_COMMANDS, INFRA_WORKFLOW, HEALTH_CHECKS, ROLLBACK_PROCEDURES,
+    INCIDENT_RESPONSE, TROUBLESHOOTING, KEY_CONFIG_FILES, DISCOVERED_SKILLS,
+    LANGUAGE_DROIDS, PREPOPULATED_KNOWLEDGE, FILE_TYPE_ROUTING, SKILL_TRIGGERS,
+    RECENT_ACTIVITY, LEARNED_LESSONS, KNOWN_GOTCHAS, HOT_SPOTS
 -->
 
 <coding_guidelines>
@@ -164,6 +183,43 @@ Task(subagent_type: "code-quality-guardian", prompt: "Review...")
 Task(subagent_type: "security-auditor", prompt: "Audit...")
 ```
 
+### Skill vs Droid: When to Use Which
+| Use a **Skill** when | Use a **Droid** when |
+|---------------------|---------------------|
+| Inline guidance needed | Autonomous agent work needed |
+| Human follows instructions | Agent executes independently |
+| Interactive decision-making | Batch processing of tasks |
+| Design/review work | Code generation/refactoring |
+| Expands into current context | Runs in parallel as subagent |
+
+---
+
+## TASK ROUTING
+
+### By Request Type
+| Keywords | Task Type | Workflow | Droids |
+|----------|-----------|----------|--------|
+| "fix", "bug", "error", "broken" | Bug | Reproduce → Test → Fix | `code-quality-guardian` |
+| "add", "implement", "build", "feature" | Feature | Design → Implement → Test | Language specialist |
+| "slow", "optimize", "performance" | Performance | Profile → Identify → Optimize | `performance-optimizer` |
+| "security", "vulnerability", "audit" | Security | Scan → Assess → Remediate | `security-auditor` |
+| "test", "coverage", "spec" | Testing | Write → Run → Report | `code-quality-guardian` |
+| "docs", "README", "document" | Docs | Check → Update → Verify | `documentation-expert` |
+| "refactor", "clean up" | Refactoring | Scope → Test → Refactor | `code-quality-guardian` |
+
+### By File Type
+| Extension | Language | Droid |
+|-----------|----------|-------|
+{{#if FILE_TYPE_ROUTING}}
+{{{FILE_TYPE_ROUTING}}}
+{{else}}
+| `.ts`, `.tsx`, `.js`, `.jsx` | TypeScript/JavaScript | `typescript-node-expert` |
+| `.py` | Python | Language specialist |
+| `.go` | Go | Language specialist |
+| `.rs` | Rust | Language specialist |
+| `.cpp`, `.h`, `.hpp` | C++ | Language specialist |
+{{/if}}
+
 ---
 
 ## AUTOMATIC TRIGGERS
@@ -355,6 +411,24 @@ After EVERY browser action:
 {{{INFRA_WORKFLOW}}}
 {{/if}}
 
+{{#if HEALTH_CHECKS}}
+## Health Checks
+
+{{{HEALTH_CHECKS}}}
+{{/if}}
+
+{{#if ROLLBACK_PROCEDURES}}
+## Emergency Rollback
+
+{{{ROLLBACK_PROCEDURES}}}
+{{/if}}
+
+{{#if INCIDENT_RESPONSE}}
+## Incident Response
+
+{{{INCIDENT_RESPONSE}}}
+{{/if}}
+
 {{#if TROUBLESHOOTING}}
 ## Troubleshooting