| name | acp-remote |
| description | Connect to remote ACP server and execute commands via imclaw-cli. |
| homepage | https://github.com/smallnest/imclaw |
| metadata | {"clawdbot":{"emoji":"🤖","requires":{"bins":["imclaw-cli","acpx"]}}} |
ACP Remote
Connect to a remote ACP (Agent Client Protocol) server and execute commands using imclaw-cli.
Prerequisites
Auto-install dependencies
Before using this skill, ensure both imclaw-cli and acpx are installed. Run these commands to install them automatically:
if ! command -v acpx &> /dev/null; then
npm install -g acpx@latest
fi
if ! command -v imclaw-cli &> /dev/null; then
curl -fsSL https://raw.githubusercontent.com/smallnest/imclaw/main/scripts/install.sh | bash
fi
Manual installation
Install acpx
npm install -g acpx@latest
Install imclaw-cli
From GitHub Releases:
OS=$(uname -s | tr '[:upper:]' '[:lower:]')
ARCH=$(uname -m)
[ "$ARCH" = "x86_64" ] && ARCH="amd64"
[ "$ARCH" = "aarch64" ] && ARCH="arm64"
LATEST=$(curl -s https://api.github.com/repos/smallnest/imclaw/releases/latest | grep '"tag_name"' | sed -E 's/.*"([^"]+)".*/\1/')
curl -sL "https://github.com/smallnest/imclaw/releases/download/${LATEST}/imclaw_${OS}_${ARCH}.tar.gz" | tar xz -C /tmp
mkdir -p ~/bin
mv /tmp/imclaw-cli ~/bin/
chmod +x ~/bin/imclaw-cli
echo 'export PATH="$HOME/bin:$PATH"' >> ~/.bashrc
Verify installation
imclaw-cli --help
acpx --version
Configuration
Set the remote server URL and optional auth token:
export IMCLAW_SERVER="ws://your-server:8080/ws"
export IMCLAW_TOKEN="your-secret-token"
Or pass directly via command line.
Server Configuration
IMClaw server uses command line flags (no config file needed):
imclaw
imclaw --port 9000 --token my-secret-token
imclaw --help
| Flag | Default | Description |
|---|
-H, --host | 0.0.0.0 | Server host address |
-p, --port | 8080 | Server port |
--timeout | 30 | Default timeout in seconds |
--token | "" | Authentication token (empty = no auth) |
Usage
One-shot mode (recommended)
imclaw-cli --server ws://your-server:8080/ws -p "Hello"
imclaw-cli --server ws://your-server:8080/ws --token your-token -p "Hello"
imclaw-cli --server ws://your-server:8080/ws --agent codex -p "Analyze this code"
imclaw-cli --server ws://your-server:8080/ws --format json -p "List files"
Continue a session
imclaw-cli --server ws://your-server:8080/ws -p "Read the README.md"
imclaw-cli --server ws://your-server:8080/ws --session <session-id> -p "Summarize it"
Parameters
| Parameter | Description |
|---|
--server | WebSocket URL of ACP server (default: ws://localhost:8080/ws) |
--token | Authentication token (if required) |
-p, --prompt | Prompt message (one-shot mode) |
--session | Session ID to continue |
--agent | Agent type: claude, codex, etc. (default: claude) |
--format | Output format: text, json, quiet (default: text) |
--approve-all | Auto-approve all permission requests |
--approve-reads | Auto-approve reads, prompt for writes (default) |
--deny-all | Deny all permission requests |
--allowed-tools | Comma-separated tool names (default: Bash,Read,Write) |
--cwd | Working directory |
--timeout | Max wait time in seconds |
--model | Agent model ID |
Examples
Execute shell commands on remote
imclaw-cli --server ws://remote-server:8080/ws \
--agent claude \
--approve-all \
-p "Run 'df -h' and show disk usage"
Analyze remote codebase
imclaw-cli --server ws://remote-server:8080/ws \
--cwd /path/to/project \
-p "Review the main.go file and suggest improvements"
Use with SSH tunnel
ssh -L 8080:localhost:8080 user@remote-server -N &
imclaw-cli --server ws://localhost:8080/ws -p "Hello from remote"
Secure connection with token
imclaw-cli \
--server wss://secure-server:8080/ws \
--token "your-secret-token" \
-p "Execute analysis task"
Environment Variables
For convenience, you can set these environment variables:
export IMCLAW_SERVER="ws://your-server:8080/ws"
export IMCLAW_TOKEN="your-token"
Then simply run:
imclaw-cli --server $IMCLAW_SERVER --token $IMCLAW_TOKEN -p "Hello"
Tips
- Session reuse: Save the session ID from first response to continue conversations
- Permission control: Use
--approve-all for non-interactive automation
- Output parsing: Use
--format json for programmatic consumption
- Tool restrictions: Use
--allowed-tools to limit what the agent can do
- Working directory: Always specify
--cwd for file operations