omniwire
Infrastructure layer for AI agent swarms — 88 MCP tools for mesh control, A2A protocol, OmniMesh VPN, CyberSync, web scraping, firewall management, browser automation, and more. ~80ms execution.
What this skill does
# OmniWire v3.5.0 — Mesh Control for AI Agent Swarms
> **88 MCP tools. 12 categories. Every machine, one agent, zero friction.**
OmniWire is the infrastructure layer for AI agent swarms. It connects your entire mesh (VPS, laptops, Raspberry Pis, Docker hosts) into a single controllable surface with 88 tools spanning execution, A2A protocol, OmniMesh VPN, CyberSync, web scraping, firewall management, CDP browser automation, and more.
```
You: check disk and container status on all servers
Agent: [omniwire_broadcast + omniwire_docker — parallel across all nodes]
contabo | 10.0.0.1 | ONLINE | 78ms | disk=16% | containers: 12 running
kali | 10.0.0.2 | ONLINE | 91ms | disk=34% | containers: 4 running
rpi | 10.0.0.3 | ONLINE | 112ms | disk=20% | containers: 2 running
```
---
## What It Does
| Category | Tools | What your agent can do |
|----------|-------|----------------------|
| **Execution** | 6 | Run commands, scripts, pipelines, background jobs on any node |
| **Agentic / A2A** | 13 | Agent tasks, messaging, blackboard, workflows, semaphores, registries |
| **Files** | 6 | Read, write, list, find, transfer, deploy files across nodes |
| **Monitoring** | 4 | Mesh health, live metrics, benchmarks, node info |
| **System / DevOps** | 14 | Processes, disks, packages, services, Docker, kernel, cron, git, logs |
| **Network / VPN** | 7 | VPN switching, port forwarding, browser, shell, streams, proxy, scraping |
| **Security** | 6 | Firewall, certs, audit, 2FA/TOTP, cookies, user management |
| **CyberSync** | 9 | Bi-directional config sync for 6 AI tools + knowledge/memory |
| **Knowledge** | 2 | Store and search unified knowledge base (pgvector) |
| **OmniMesh** | 3 | WireGuard mesh manager, expose services, gateway routing |
| **Events** | 1 | Webhook + WebSocket + SSE event bus |
| **CDP Browser** | 1 | 18 browser actions via persistent Docker Chrome |
| **Utilities** | 10+ | Alerts, aliases, backups, snippets, DNS, diagnostics, scheduling |
---
## Setup — 3 Steps
### Step 1: Install OmniWire
> **AGENT: Run this via exec. User just clicks Approve.**
```bash
npm install -g omniwire@latest
```
Works on: Linux (x64, ARM64, ARMv7), macOS (Intel + Apple Silicon), Windows (x64).
### Step 2: Configure Your Mesh
Create the mesh config. Ask the user for their server details:
> **AGENT: Ask the user:**
> "What servers do you want to control? For each one I need:
> - A name (e.g., `contabo`, `kali`, `rpi`)
> - IP address or hostname
> - SSH user (usually `root`)
> - SSH key filename in ~/.ssh/ (e.g., `id_ed25519`)
> - Role: `storage`, `compute`, `gpu+browser`, or leave blank"
Then create the config:
```bash
mkdir -p ~/.omniwire
cat > ~/.omniwire/mesh.json << 'EOF'
{
"nodes": [
{
"id": "contabo",
"host": "10.0.0.1",
"user": "root",
"identityFile": "id_ed25519",
"role": "storage",
"tags": ["vps", "docker"]
},
{
"id": "kali",
"host": "10.0.0.2",
"user": "root",
"identityFile": "id_ed25519",
"role": "compute",
"tags": ["kali", "pentest"]
}
],
"cyberbase": {
"host": "10.10.0.1",
"port": 5432,
"database": "cyberbase",
"user": "cyberbase"
}
}
EOF
```
### Step 3: Verify
```bash
echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"test","version":"1"}}}' \
| omniwire --stdio --no-sync 2>/dev/null | head -1
```
Should respond with `omniwire v3.5.0`. Done.
**Transport options:**
| Transport | Command | Port |
|-----------|---------|------|
| stdio (MCP default) | `omniwire --stdio` | — |
| SSE (HTTP streaming) | `omniwire --sse` | 3200 |
| REST (HTTP JSON) | `omniwire --rest` | 3201 |
| Events (WebSocket) | `omniwire --events` | 3202 |
---
## Usage Examples
### Execute commands anywhere
```
You: restart nginx on contabo
Agent: [omniwire_exec node=contabo command="systemctl restart nginx"]
OK — nginx restarted (0ms)
You: run uptime on every server
Agent: [omniwire_broadcast command="uptime"]
contabo | up 42 days, 3:21
kali | up 7 days, 11:04
rpi | up 2 days, 0:15
```
### Transfer files between nodes
```
You: copy the pentest report from kali to contabo
Agent: [omniwire_transfer_file src_node=kali dest_node=contabo src=/root/report.pdf dest=/var/reports/]
Transferred 2.4MB — LZ4 compressed — 83ms
```
Transfer modes (auto-selected):
- **SFTP** for files under 10MB
- **netcat + LZ4** for 10MB–1GB
- **aria2c** for files over 1GB (16 parallel connections)
### Docker management
```
You: what containers are running on contabo?
Agent: [omniwire_docker node=contabo action=ps]
12 running — neo4j, postgres, omnibus-hub, kali-htb, omniwire-events...
You: pull and start the latest omniwire-events image
Agent: [omniwire_container node=contabo action=pull image=omniwire-events:latest]
Pulled. Starting...
✓ omniwire-events running (healthy)
```
### Monitor mesh health
```
You: how are all my servers doing?
Agent: [omniwire_mesh_status]
contabo | 10.0.0.1 | ONLINE | 78ms | load=1.2 | mem=31% | disk=16%
kali | 10.0.0.2 | ONLINE | 91ms | load=0.4 | mem=19% | disk=34%
rpi | 10.0.0.3 | ONLINE | 112ms | load=0.7 | mem=22% | disk=20%
```
### VPN switching
```
You: switch to Mullvad on the kali node
Agent: [omniwire_vpn node=kali action=connect provider=mullvad country=nl]
Connected — Netherlands exit — mesh routes preserved
New IP: 185.65.134.x
```
Supported providers: Mullvad, OpenVPN, WireGuard, Tailscale. OmniMesh routes are protected during VPN switches.
### Web scraping with Cloudflare bypass
```
You: scrape the pricing table from example.com
Agent: [omniwire_scrape node=contabo url=https://example.com/pricing selector=".pricing-table"]
Scraped 4.2KB — Scrapling engine — Cloudflare bypassed
[returns structured data]
```
### A2A agent messaging
```
You: send a task to the pentest agent on kali
Agent: [omniwire_agent_task node=kali agent_id=pentest-agent task={type:"scan", target:"192.168.1.0/24"}]
Task queued — ID: task_abc123
Agent: [omniwire_blackboard action=watch key=task_abc123/result]
Result ready: {hosts: 12, open_ports: [...]}
```
### COC — Unified CyberBase + Obsidian + Canvas sync
```
You: COC save — OmniWire v3.5.0 deployed with 88 tools
Agent: [omniwire_coc action=save note="OmniWire v3.5.0 deployed with 88 tools"]
Saved to CyberBase (knowledge table)
Mirrored to Obsidian vault: CyberBase/omniwire-v350.md
Canvas node updated: CyberBase MindMap.canvas
✓ All 3 sync targets confirmed
```
---
## Full Tool Reference
<details>
<summary><strong>Execution (6 tools)</strong></summary>
| Tool | Description |
|------|-------------|
| `omniwire_exec` | Execute a command on a specific node. Args: `node`, `command`, `timeout`, `background` |
| `omniwire_run` | Run a named script or predefined task. Args: `node`, `script`, `args` |
| `omniwire_batch` | Execute multiple commands across multiple nodes in one call. Args: `commands[]` |
| `omniwire_broadcast` | Execute command on ALL nodes simultaneously. Args: `command`, `tags` (filter by tag) |
| `omniwire_pipeline` | Chain commands where output of one feeds into next. Args: `node`, `steps[]` |
| `omniwire_bg` | Background task manager — dispatch, poll, get result. Args: `action`, `task_id` |
</details>
<details>
<summary><strong>Agentic / A2A Protocol (13 tools)</strong></summary>
| Tool | Description |
|------|-------------|
| `omniwire_store` | Key-value store for agents. Actions: get, set, delete, list. Args: `key`, `value`, `ttl` |
| `omniwire_watch` | Watch a key for changes (long-poll). Args: `key`, `timeout` |
| `omniwire_healthcheck` | Check agent health status across nodes. Args: `agent_id`, `node` |
| `omniwire_agent_task` | Dispatch a structured task to a named agent. Args: `node`, `agent_id`, `task` |
| `omniwire_a2a_message` | Send an A2A protocol message between agents. Args: `to`, `from`, `messageRelated in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.