gkt-node 3.3.0

package/assets/.agent/skills/deployment-procedures/SKILL.md

@@ -0,0 +1,241 @@
+---
+name: deployment-procedures
+description: Production deployment principles and decision-making. Safe deployment workflows, rollback strategies, and verification. Teaches thinking, not scripts.
+allowed-tools: Read, Glob, Grep, Bash
+---
+
+# Deployment Procedures
+
+> Deployment principles and decision-making for safe production releases.
+> **Learn to THINK, not memorize scripts.**
+
+---
+
+## ⚠️ How to Use This Skill
+
+This skill teaches **deployment principles**, not bash scripts to copy.
+
+- Every deployment is unique
+- Understand the WHY behind each step
+- Adapt procedures to your platform
+
+---
+
+## 1. Platform Selection
+
+### Decision Tree
+
+```
+What are you deploying?
+│
+├── Static site / JAMstack
+│   └── Vercel, Netlify, Cloudflare Pages
+│
+├── Simple web app
+│   ├── Managed → Railway, Render, Fly.io
+│   └── Control → VPS + PM2/Docker
+│
+├── Microservices
+│   └── Container orchestration
+│
+└── Serverless
+    └── Edge functions, Lambda
+```
+
+### Each Platform Has Different Procedures
+
+| Platform | Deployment Method |
+|----------|------------------|
+| **Vercel/Netlify** | Git push, auto-deploy |
+| **Railway/Render** | Git push or CLI |
+| **VPS + PM2** | SSH + manual steps |
+| **Docker** | Image push + orchestration |
+| **Kubernetes** | kubectl apply |
+
+---
+
+## 2. Pre-Deployment Principles
+
+### The 4 Verification Categories
+
+| Category | What to Check |
+|----------|--------------|
+| **Code Quality** | Tests passing, linting clean, reviewed |
+| **Build** | Production build works, no warnings |
+| **Environment** | Env vars set, secrets current |
+| **Safety** | Backup done, rollback plan ready |
+
+### Pre-Deployment Checklist
+
+- [ ] All tests passing
+- [ ] Code reviewed and approved
+- [ ] Production build successful
+- [ ] Environment variables verified
+- [ ] Database migrations ready (if any)
+- [ ] Rollback plan documented
+- [ ] Team notified
+- [ ] Monitoring ready
+
+---
+
+## 3. Deployment Workflow Principles
+
+### The 5-Phase Process
+
+```
+1. PREPARE
+   └── Verify code, build, env vars
+
+2. BACKUP
+   └── Save current state before changing
+
+3. DEPLOY
+   └── Execute with monitoring open
+
+4. VERIFY
+   └── Health check, logs, key flows
+
+5. CONFIRM or ROLLBACK
+   └── All good? Confirm. Issues? Rollback.
+```
+
+### Phase Principles
+
+| Phase | Principle |
+|-------|-----------|
+| **Prepare** | Never deploy untested code |
+| **Backup** | Can't rollback without backup |
+| **Deploy** | Watch it happen, don't walk away |
+| **Verify** | Trust but verify |
+| **Confirm** | Have rollback trigger ready |
+
+---
+
+## 4. Post-Deployment Verification
+
+### What to Verify
+
+| Check | Why |
+|-------|-----|
+| **Health endpoint** | Service is running |
+| **Error logs** | No new errors |
+| **Key user flows** | Critical features work |
+| **Performance** | Response times acceptable |
+
+### Verification Window
+
+- **First 5 minutes**: Active monitoring
+- **15 minutes**: Confirm stable
+- **1 hour**: Final verification
+- **Next day**: Review metrics
+
+---
+
+## 5. Rollback Principles
+
+### When to Rollback
+
+| Symptom | Action |
+|---------|--------|
+| Service down | Rollback immediately |
+| Critical errors | Rollback |
+| Performance >50% degraded | Consider rollback |
+| Minor issues | Fix forward if quick |
+
+### Rollback Strategy by Platform
+
+| Platform | Rollback Method |
+|----------|----------------|
+| **Vercel/Netlify** | Redeploy previous commit |
+| **Railway/Render** | Rollback in dashboard |
+| **VPS + PM2** | Restore backup, restart |
+| **Docker** | Previous image tag |
+| **K8s** | kubectl rollout undo |
+
+### Rollback Principles
+
+1. **Speed over perfection**: Rollback first, debug later
+2. **Don't compound errors**: One rollback, not multiple changes
+3. **Communicate**: Tell team what happened
+4. **Post-mortem**: Understand why after stable
+
+---
+
+## 6. Zero-Downtime Deployment
+
+### Strategies
+
+| Strategy | How It Works |
+|----------|--------------|
+| **Rolling** | Replace instances one by one |
+| **Blue-Green** | Switch traffic between environments |
+| **Canary** | Gradual traffic shift |
+
+### Selection Principles
+
+| Scenario | Strategy |
+|----------|----------|
+| Standard release | Rolling |
+| High-risk change | Blue-green (easy rollback) |
+| Need validation | Canary (test with real traffic) |
+
+---
+
+## 7. Emergency Procedures
+
+### Service Down Priority
+
+1. **Assess**: What's the symptom?
+2. **Quick fix**: Restart if unclear
+3. **Rollback**: If restart doesn't help
+4. **Investigate**: After stable
+
+### Investigation Order
+
+| Check | Common Issues |
+|-------|--------------|
+| **Logs** | Errors, exceptions |
+| **Resources** | Disk full, memory |
+| **Network** | DNS, firewall |
+| **Dependencies** | Database, APIs |
+
+---
+
+## 8. Anti-Patterns
+
+| ❌ Don't | ✅ Do |
+|----------|-------|
+| Deploy on Friday | Deploy early in week |
+| Rush deployment | Follow the process |
+| Skip staging | Always test first |
+| Deploy without backup | Backup before deploy |
+| Walk away after deploy | Monitor for 15+ min |
+| Multiple changes at once | One change at a time |
+
+---
+
+## 9. Decision Checklist
+
+Before deploying:
+
+- [ ] **Platform-appropriate procedure?**
+- [ ] **Backup strategy ready?**
+- [ ] **Rollback plan documented?**
+- [ ] **Monitoring configured?**
+- [ ] **Team notified?**
+- [ ] **Time to monitor after?**
+
+---
+
+## 10. Best Practices
+
+1. **Small, frequent deploys** over big releases
+2. **Feature flags** for risky changes
+3. **Automate** repetitive steps
+4. **Document** every deployment
+5. **Review** what went wrong after issues
+6. **Test rollback** before you need it
+
+---
+
+> **Remember:** Every deployment is a risk. Minimize risk through preparation, not speed.

package/assets/.agent/skills/diff-applier/SKILL.md

@@ -0,0 +1,34 @@
+---
+name: diff-applier
+description: Smart Patcher — Apply Diff, Lint, and Auto-Index.
+---
+
+# Diff Applier
+
+## Purpose
+Apply code changes ("patches") safely, saving tokens by not rewriting the whole file. Automatically checks for lint errors and updates the codebase index.
+
+## Usage
+
+### 1. Create a Patch File
+The patch file must use `SEARCH/REPLACE` blocks:
+```text
+<<<<<<< SEARCH
+def old_function():
+    return True
+=======
+def new_function():
+    return False
+>>>>>>> REPLACE
+```
+
+### 2. Apply Patch
+```bash
+python .agent/skills/diff-applier/scripts/apply_patch.py src/main.py my_patch.txt
+```
+
+## Workflow
+1.  **Backup**: Creates `src/main.py.bak`.
+2.  **Apply**: Replaces exact text matches.
+3.  **Lint**: Runs `flake8` (Python) or `eslint` (JS) if available.
+4.  **Index**: Calls `codebase-navigator` to update the project index.

package/assets/.agent/skills/diff-applier/scripts/apply_patch.py

@@ -0,0 +1,137 @@
+#!/usr/bin/env python3
+"""
+Diff Applier — Apply SEARCH/REPLACE blocks safely.
+
+Usage:
+    python apply_patch.py <target_file> <patch_file>
+"""
+
+import argparse
+import sys
+import shutil
+import subprocess
+from pathlib import Path
+
+def apply_patch(target_file, patch_file):
+    target = Path(target_file)
+    patch = Path(patch_file)
+    
+    if not target.exists():
+        print(f"❌ Target file not found: {target}")
+        sys.exit(1)
+        
+    if not patch.exists():
+        print(f"❌ Patch file not found: {patch}")
+        sys.exit(1)
+        
+    print(f"🔧 Applying patch to {target.name}...")
+    
+    with open(target, 'r', encoding='utf-8') as f:
+        content = f.read()
+        
+    with open(patch, 'r', encoding='utf-8') as f:
+        patch_content = f.read()
+        
+    # Parse blocks
+    blocks = patch_content.split('<<<<<<< SEARCH')
+    if len(blocks) < 2:
+        print("❌ No SEARCH blocks found in patch.")
+        sys.exit(1)
+        
+    new_content = content
+    changes_count = 0
+    
+    for block in blocks[1:]: # Skip preamble
+        if '=======' not in block or '>>>>>>> REPLACE' not in block:
+            print("❌ Malformed block (missing separator or end tag)")
+            continue
+            
+        search_part, rest = block.split('=======', 1)
+        replace_part, _ = rest.split('>>>>>>> REPLACE', 1)
+        
+        search_text = search_part.strip()
+        replace_text = replace_part.strip()
+        
+        # Try to find exact match (ignoring leading/trailing whitespace of the block itself, but keeping internal structure)
+        # Actually, simpler: search for the exact lines
+        
+        if search_text not in new_content:
+             # Try stricter normalization if exact match fails?
+             # For now, strict.
+             print(f"❌ Could not find SEARCH block:\n{search_text[:50]}...")
+             continue
+             
+        # Check uniqueness
+        if new_content.count(search_text) > 1:
+            print(f"❌ SEARCH block matches multiple locations. Aborting block:\n{search_text[:50]}...")
+            continue
+            
+        new_content = new_content.replace(search_text, replace_text)
+        changes_count += 1
+        
+    if changes_count == 0:
+        print("⚠️ No changes applied.")
+        sys.exit(1)
+        
+    # Backup
+    backup = target.with_suffix('.bak')
+    shutil.copy2(target, backup)
+    print(f"📦 Backup created: {backup.name}")
+    
+    # Write
+    with open(target, 'w', encoding='utf-8') as f:
+        f.write(new_content)
+        
+    print(f"✅ Applied {changes_count} changes.")
+    
+    # Auto-Lint
+    run_linter(target)
+    
+    # Auto-Index
+    run_indexer(target)
+
+def run_linter(target):
+    print("\n🔍 Running Linter...")
+    # Simple heuristic
+    if target.suffix == '.py':
+        # Try flake8 or pylint
+        try:
+            subprocess.run(["flake8", str(target)], check=False)
+        except FileNotFoundError:
+            print("   (flake8 not found, skipping)")
+    elif target.suffix in ['.js', '.ts', '.jsx', '.tsx']:
+        # Try eslint
+        try:
+            subprocess.run(["npx", "eslint", str(target)], check=False, shell=True)
+        except Exception:
+            print("   (eslint failed, skipping)")
+            
+def run_indexer(target):
+    print("\n📚 Updating Codebase Index...")
+    # Assume navigator is at .agent/skills/codebase-navigator/scripts/navigator.py
+    # We are running from project root usually?
+    # Script location: .agent/skills/diff-applier/scripts/apply_patch.py
+    # Navigator: ../../codebase-navigator/scripts/navigator.py
+    
+    base_dir = Path(__file__).resolve().parent.parent.parent
+    navigator_script = base_dir / "codebase-navigator" / "scripts" / "navigator.py"
+    
+    if navigator_script.exists():
+        try:
+            subprocess.run(["python", str(navigator_script), "--incremental"], check=True)
+            print("✅ Index updated.")
+        except Exception as e:
+            print(f"⚠️ Index update failed: {e}")
+    else:
+        print(f"⚠️ Navigator script not found at {navigator_script}")
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("target_file")
+    parser.add_argument("patch_file")
+    args = parser.parse_args()
+    
+    apply_patch(args.target_file, args.patch_file)
+
+if __name__ == "__main__":
+    main()

package/assets/.agent/skills/discord-automation/SKILL.md

@@ -0,0 +1,187 @@
+---
+name: discord-automation
+description: "Automate Discord tasks via Rube MCP (Composio): messages, channels, roles, webhooks, reactions. Always search tools first for current schemas."
+requires:
+  mcp: [rube]
+---
+
+# Discord Automation via Rube MCP
+
+Automate Discord operations through Composio's Discord/Discordbot toolkits via Rube MCP.
+
+## Prerequisites
+
+- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
+- Active Discord connection via `RUBE_MANAGE_CONNECTIONS` with toolkits `discord` and `discordbot`
+- Always call `RUBE_SEARCH_TOOLS` first to get current tool schemas
+
+## Setup
+
+**Get Rube MCP**: Add `https://rube.app/mcp` as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.
+
+
+1. Verify Rube MCP is available by confirming `RUBE_SEARCH_TOOLS` responds
+2. Call `RUBE_MANAGE_CONNECTIONS` with toolkit `discordbot` (bot operations) or `discord` (user operations)
+3. If connection is not ACTIVE, follow the returned auth link to complete Discord auth
+4. Confirm connection status shows ACTIVE before running any workflows
+
+## Core Workflows
+
+### 1. Send Messages
+
+**When to use**: User wants to send messages to channels or DMs
+
+**Tool sequence**:
+1. `DISCORD_LIST_MY_GUILDS` - List guilds the bot belongs to [Prerequisite]
+2. `DISCORDBOT_LIST_GUILD_CHANNELS` - List channels in a guild [Prerequisite]
+3. `DISCORDBOT_CREATE_MESSAGE` - Send a message [Required]
+4. `DISCORDBOT_UPDATE_MESSAGE` - Edit a sent message [Optional]
+
+**Key parameters**:
+- `channel_id`: Channel snowflake ID
+- `content`: Message text (max 2000 characters)
+- `embeds`: Array of embed objects for rich content
+- `guild_id`: Guild ID for channel listing
+
+**Pitfalls**:
+- Bot must have SEND_MESSAGES permission in the channel
+- High-frequency sends can hit per-route rate limits; respect Retry-After headers
+- Only messages sent by the same bot can be edited
+
+### 2. Send Direct Messages
+
+**When to use**: User wants to DM a Discord user
+
+**Tool sequence**:
+1. `DISCORDBOT_CREATE_DM` - Create or get DM channel [Required]
+2. `DISCORDBOT_CREATE_MESSAGE` - Send message to DM channel [Required]
+
+**Key parameters**:
+- `recipient_id`: User snowflake ID for DM
+- `channel_id`: DM channel ID from CREATE_DM
+
+**Pitfalls**:
+- Cannot DM users who have DMs disabled or have blocked the bot
+- CREATE_DM returns existing channel if one already exists
+
+### 3. Manage Roles
+
+**When to use**: User wants to create, assign, or remove roles
+
+**Tool sequence**:
+1. `DISCORDBOT_CREATE_GUILD_ROLE` - Create a new role [Optional]
+2. `DISCORDBOT_ADD_GUILD_MEMBER_ROLE` - Assign role to member [Optional]
+3. `DISCORDBOT_DELETE_GUILD_ROLE` - Delete a role [Optional]
+4. `DISCORDBOT_GET_GUILD_MEMBER` - Get member details [Optional]
+5. `DISCORDBOT_UPDATE_GUILD_MEMBER` - Update member (roles, nick, etc.) [Optional]
+
+**Key parameters**:
+- `guild_id`: Guild snowflake ID
+- `user_id`: User snowflake ID
+- `role_id`: Role snowflake ID
+- `name`: Role name
+- `permissions`: Bitwise permission value
+- `color`: RGB color integer
+
+**Pitfalls**:
+- Role assignment requires MANAGE_ROLES permission
+- Target role must be lower in hierarchy than bot's highest role
+- DELETE permanently removes the role from all members
+
+### 4. Manage Webhooks
+
+**When to use**: User wants to create or use webhooks for external integrations
+
+**Tool sequence**:
+1. `DISCORDBOT_GET_GUILD_WEBHOOKS` / `DISCORDBOT_LIST_CHANNEL_WEBHOOKS` - List webhooks [Optional]
+2. `DISCORDBOT_CREATE_WEBHOOK` - Create a new webhook [Optional]
+3. `DISCORDBOT_EXECUTE_WEBHOOK` - Send message via webhook [Optional]
+4. `DISCORDBOT_UPDATE_WEBHOOK` - Update webhook settings [Optional]
+
+**Key parameters**:
+- `webhook_id`: Webhook ID
+- `webhook_token`: Webhook secret token
+- `channel_id`: Channel for webhook creation
+- `name`: Webhook name
+- `content`/`embeds`: Message content for execution
+
+**Pitfalls**:
+- Webhook tokens are secrets; handle securely
+- Webhooks can post with custom username and avatar per message
+- MANAGE_WEBHOOKS permission required for creation
+
+### 5. Manage Reactions
+
+**When to use**: User wants to view or manage message reactions
+
+**Tool sequence**:
+1. `DISCORDBOT_LIST_MESSAGE_REACTIONS_BY_EMOJI` - List users who reacted [Optional]
+2. `DISCORDBOT_DELETE_ALL_MESSAGE_REACTIONS` - Remove all reactions [Optional]
+3. `DISCORDBOT_DELETE_ALL_MESSAGE_REACTIONS_BY_EMOJI` - Remove specific emoji reactions [Optional]
+4. `DISCORDBOT_DELETE_USER_MESSAGE_REACTION` - Remove specific user's reaction [Optional]
+
+**Key parameters**:
+- `channel_id`: Channel ID
+- `message_id`: Message snowflake ID
+- `emoji_name`: URL-encoded emoji or `name:id` for custom emojis
+- `user_id`: User ID for specific reaction removal
+
+**Pitfalls**:
+- Unicode emojis must be URL-encoded (e.g., '%F0%9F%91%8D' for thumbs up)
+- Custom emojis use `name:id` format
+- DELETE_ALL requires MANAGE_MESSAGES permission
+
+## Common Patterns
+
+### Snowflake IDs
+
+Discord uses snowflake IDs (64-bit integers as strings) for all entities:
+- Guilds, channels, users, roles, messages, webhooks
+
+### Permission Bitfields
+
+Permissions are combined using bitwise OR:
+- SEND_MESSAGES = 0x800
+- MANAGE_ROLES = 0x10000000
+- MANAGE_MESSAGES = 0x2000
+- ADMINISTRATOR = 0x8
+
+### Pagination
+
+- Most list endpoints support `limit`, `before`, `after` parameters
+- Messages: max 100 per request
+- Reactions: max 100 per request, use `after` for pagination
+
+## Known Pitfalls
+
+**Bot vs User Tokens**:
+- `discordbot` toolkit uses bot tokens; `discord` uses user OAuth
+- Bot operations are preferred for automation
+
+**Rate Limits**:
+- Discord enforces per-route rate limits
+- Respect `Retry-After` headers on 429 responses
+
+## Quick Reference
+
+| Task | Tool Slug | Key Params |
+|------|-----------|------------|
+| List guilds | DISCORD_LIST_MY_GUILDS | (none) |
+| List channels | DISCORDBOT_LIST_GUILD_CHANNELS | guild_id |
+| Send message | DISCORDBOT_CREATE_MESSAGE | channel_id, content |
+| Edit message | DISCORDBOT_UPDATE_MESSAGE | channel_id, message_id |
+| Get messages | DISCORDBOT_LIST_MESSAGES | channel_id, limit |
+| Create DM | DISCORDBOT_CREATE_DM | recipient_id |
+| Create role | DISCORDBOT_CREATE_GUILD_ROLE | guild_id, name |
+| Assign role | DISCORDBOT_ADD_GUILD_MEMBER_ROLE | guild_id, user_id, role_id |
+| Delete role | DISCORDBOT_DELETE_GUILD_ROLE | guild_id, role_id |
+| Get member | DISCORDBOT_GET_GUILD_MEMBER | guild_id, user_id |
+| Update member | DISCORDBOT_UPDATE_GUILD_MEMBER | guild_id, user_id |
+| Get guild | DISCORDBOT_GET_GUILD | guild_id |
+| Create webhook | DISCORDBOT_CREATE_WEBHOOK | channel_id, name |
+| Execute webhook | DISCORDBOT_EXECUTE_WEBHOOK | webhook_id, webhook_token |
+| List webhooks | DISCORDBOT_GET_GUILD_WEBHOOKS | guild_id |
+| Get reactions | DISCORDBOT_LIST_MESSAGE_REACTIONS_BY_EMOJI | channel_id, message_id, emoji_name |
+| Clear reactions | DISCORDBOT_DELETE_ALL_MESSAGE_REACTIONS | channel_id, message_id |
+| Test auth | DISCORDBOT_TEST_AUTH | (none) |
+| Get channel | DISCORDBOT_GET_CHANNEL | channel_id |

package/assets/.agent/skills/distributed-debugging-debug-trace/SKILL.md

@@ -0,0 +1,44 @@
+---
+name: distributed-debugging-debug-trace
+description: "You are a debugging expert specializing in setting up comprehensive debugging environments, distributed tracing, and diagnostic tools. Configure debugging workflows, implement tracing solutions, and establish troubleshooting practices for development and production environments."
+---
+
+# Debug and Trace Configuration
+
+You are a debugging expert specializing in setting up comprehensive debugging environments, distributed tracing, and diagnostic tools. Configure debugging workflows, implement tracing solutions, and establish troubleshooting practices for development and production environments.
+
+## Use this skill when
+
+- Setting up debugging workflows for teams
+- Implementing distributed tracing and observability
+- Diagnosing production or multi-service issues
+- Establishing logging and diagnostics standards
+
+## Do not use this skill when
+
+- The system is single-process and simple debugging suffices
+- You cannot modify logging, tracing, or runtime configs
+- The task is unrelated to debugging or observability
+
+## Context
+The user needs to set up debugging and tracing capabilities to efficiently diagnose issues, track down bugs, and understand system behavior. Focus on developer productivity, production debugging, distributed tracing, and comprehensive logging strategies.
+
+## Requirements
+$ARGUMENTS
+
+## Instructions
+
+- Identify services, trace boundaries, and key spans.
+- Configure local debugging and production-safe tracing.
+- Standardize log/trace fields and correlation IDs.
+- Validate end-to-end trace coverage and sampling.
+- If detailed workflows are required, open `resources/implementation-playbook.md`.
+
+## Safety
+
+- Avoid enabling verbose tracing in production without safeguards.
+- Redact secrets and PII from logs and traces.
+
+## Resources
+
+- `resources/implementation-playbook.md` for detailed tooling and configuration patterns.