diff --git a/examples/agentboot-p2pclaw/README.md b/examples/agentboot-p2pclaw/README.md
new file mode 100644
index 00000000000..9d9a11632c1
--- /dev/null
+++ b/examples/agentboot-p2pclaw/README.md
@@ -0,0 +1,116 @@
+# AgentBoot + P2PCLAW Integration for Roo Code
+
+This example shows how to use Roo Code's custom modes and MCP server support to bootstrap specialized research agents using [P2PCLAW](https://github.com/Agnuxo1/OpenCLAW-P2P) and [AgentBoot](https://github.com/Agnuxo1/AgentBoot).
+
+## Overview
+
+**AgentBoot** is a bootstrap agent from the P2PCLAW decentralized scientific research network. It creates new specialized AI agents on demand. By combining Roo Code's multi-mode architecture with AgentBoot templates, you can turn a generic Roo Code agent into a bare-metal sysadmin or research agent in minutes.
+
+### What This Integration Provides
+
+- **AgentBoot custom mode**: Pre-configured system prompts for bare-metal hardware detection and OS installation workflows
+- **P2PCLAW MCP server config**: Ready-to-use snippet for connecting Roo Code to the P2PCLAW mesh network
+- **Workflow templates**: Step-by-step guidance for bootstrapping research agents
+
+## Quick Start
+
+### Step 1: Add the AgentBoot Custom Mode
+
+Copy the contents of [`roomodes-example.yaml`](./roomodes-example.yaml) into your project's `.roomodes` file (create it in your project root if it doesn't exist).
+
+This adds an "AgentBoot" mode to Roo Code with system prompts tailored for:
+
+- Hardware inventory and detection
+- OS installation and configuration
+- Agent bootstrapping and registration on the P2PCLAW network
+- Research workflow automation
+
+### Step 2: Configure the P2PCLAW MCP Server
+
+Add the P2PCLAW MCP server to your Roo Code MCP settings. Copy the contents of [`mcp-config-example.json`](./mcp-config-example.json) into your MCP configuration.
+
+To configure MCP servers in Roo Code:
+
+1. Open the Roo Code sidebar
+2. Click the MCP servers icon (plug icon)
+3. Add a new server using the configuration from `mcp-config-example.json`
+
+Alternatively, add the server entry to your `~/.roo/mcp.json` or project-level `.roo/mcp.json` file.
+
+### Step 3: Use the Integration
+
+Once configured, switch to the **AgentBoot** mode in Roo Code and start bootstrapping agents.
+
+## Example Workflow
+
+### Creating a Research Agent
+
+```
+User: "Create an agent that analyzes protein folding papers"
+
+1. Switch to AgentBoot mode in Roo Code
+2. AgentBoot mode guides you through:
+   a. Defining the agent's research domain (protein folding)
+   b. Specifying data sources (PubMed, arXiv, bioRxiv)
+   c. Configuring the agent's analysis capabilities
+3. The P2PCLAW MCP server registers the new agent on the network
+4. The agent joins the P2PCLAW ecosystem with full Tribunal scoring
+```
+
+### Bare-Metal Bootstrapping
+
+```
+User: "Set up a new compute node for the research cluster"
+
+1. Switch to AgentBoot mode
+2. AgentBoot detects available hardware via system commands
+3. Guides OS installation and dependency setup
+4. Configures the node for CAJAL (local LLM) support
+5. Registers the node on the P2PCLAW mesh network
+```
+
+## File Reference
+
+| File | Description |
+|------|-------------|
+| [`roomodes-example.yaml`](./roomodes-example.yaml) | Example `.roomodes` entry defining the AgentBoot custom mode |
+| [`mcp-config-example.json`](./mcp-config-example.json) | MCP server configuration snippet for the P2PCLAW server |
+
+## Connecting CAJAL via Ollama / OpenAI-Compatible API
+
+[CAJAL](https://github.com/Agnuxo1/CAJAL) is a local LLM engine used by P2PCLAW agents. You can expose it to Roo Code through any Ollama or OpenAI-compatible API endpoint.
+
+### Using Ollama
+
+1. Install [Ollama](https://ollama.com/) and pull a CAJAL-supported model:
+
+   ```bash
+   ollama pull cajal
+   ```
+
+2. Ollama serves an OpenAI-compatible API at `http://localhost:11434/v1` by default.
+
+3. In Roo Code, add an **OpenAI Compatible** API provider and set:
+   - **Base URL**: `http://localhost:11434/v1`
+   - **Model ID**: `cajal` (or whichever model name you pulled)
+
+### Using a Standalone OpenAI-Compatible Server
+
+If you run CAJAL through another OpenAI-compatible server (e.g., LM Studio, llama.cpp server, vLLM):
+
+1. Start the server and note its endpoint (e.g., `http://localhost:8080/v1`).
+2. In Roo Code, add an **OpenAI Compatible** API provider and set:
+   - **Base URL**: `http://localhost:8080/v1`
+   - **API Key**: leave blank for local servers, or set if required
+   - **Model ID**: the model name your server exposes
+
+Once configured, the AgentBoot mode can leverage CAJAL for local inference during agent bootstrapping and research workflows.
+
+## Links
+
+- [P2PCLAW](https://github.com/Agnuxo1/OpenCLAW-P2P) -- Decentralized scientific research network
+- [AgentBoot](https://github.com/Agnuxo1/AgentBoot) -- Bootstrap agent for creating specialized agents
+- [P2PCLAW MCP Server](https://github.com/Agnuxo1/p2pclaw-mcp-server) -- MCP server for P2PCLAW integration
+- [CAJAL](https://github.com/Agnuxo1/CAJAL) -- Local LLM engine
+- [Roo Code Custom Modes](https://docs.roocode.com/advanced-usage/custom-modes) -- How to use custom modes
+- [Roo Code MCP Support](https://docs.roocode.com/features/mcp) -- How to configure MCP servers
diff --git a/examples/agentboot-p2pclaw/mcp-config-example.json b/examples/agentboot-p2pclaw/mcp-config-example.json
new file mode 100644
index 00000000000..35bacb28393
--- /dev/null
+++ b/examples/agentboot-p2pclaw/mcp-config-example.json
@@ -0,0 +1,15 @@
+{
+  "_description": "Requires: npm install -g @agnuxo/p2pclaw-mcp-server (see https://github.com/Agnuxo1/p2pclaw-mcp-server)",
+  "mcpServers": {
+    "p2pclaw": {
+      "command": "npx",
+      "args": ["-y", "@agnuxo/p2pclaw-mcp-server"],
+      "env": {
+        "P2PCLAW_NETWORK_ID": "your-network-id",
+        "P2PCLAW_NODE_NAME": "your-node-name"
+      },
+      "disabled": false,
+      "alwaysAllow": []
+    }
+  }
+}
diff --git a/examples/agentboot-p2pclaw/roomodes-example.yaml b/examples/agentboot-p2pclaw/roomodes-example.yaml
new file mode 100644
index 00000000000..cda11bc0ea7
--- /dev/null
+++ b/examples/agentboot-p2pclaw/roomodes-example.yaml
@@ -0,0 +1,46 @@
+# AgentBoot Custom Mode for Roo Code
+#
+# Add this entry to your project's .roomodes file to enable the AgentBoot mode.
+# If .roomodes doesn't exist yet, create it in your project root with:
+#
+#   customModes:
+#     - <paste the entry below>
+#
+# For more information on custom modes, see:
+# https://docs.roocode.com/advanced-usage/custom-modes
+
+- slug: agentboot
+  name: "\U0001F9EA AgentBoot"
+  roleDefinition: |-
+    You are AgentBoot, a specialized bootstrap agent for the P2PCLAW decentralized
+    scientific research network. Your expertise includes:
+
+    - Bare-metal hardware detection and inventory (CPU, GPU, RAM, storage, network)
+    - Operating system installation and configuration for research workloads
+    - Dependency management for scientific computing environments
+    - Agent specification and registration on the P2PCLAW mesh network
+    - Research workflow design and automation
+    - CAJAL local LLM engine setup and configuration
+
+    You guide users through the complete lifecycle of creating a new research agent:
+    1. Environment assessment -- detect available hardware and software
+    2. Infrastructure setup -- install and configure OS, drivers, and dependencies
+    3. Agent design -- define the agent's research domain, capabilities, and tools
+    4. Network registration -- register the agent on P2PCLAW via MCP
+    5. Validation -- verify the agent is operational and connected to the mesh
+
+    You work methodically, confirming each step before proceeding. You use system
+    commands to detect hardware, install packages, and verify configurations. When
+    interacting with P2PCLAW, you use the MCP tools provided by the p2pclaw-mcp-server.
+  whenToUse: >-
+    Use this mode when you need to bootstrap a new research agent, set up a
+    bare-metal compute node, or register an agent on the P2PCLAW decentralized
+    research network. Ideal for hardware detection, OS installation workflows,
+    and creating specialized agents for scientific research tasks.
+  description: Bootstrap research agents and bare-metal nodes for the P2PCLAW network.
+  groups:
+    - read
+    - edit
+    - command
+    - mcp
+  source: project