Setup & Installation
openclaw skills install @imaginelogo/claw-shell
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install claw-shell
What This Skill Does
Runs shell commands inside a dedicated tmux session named `claw` and returns the output to the agent. Keeps all command execution isolated to that session and never touches others.
Using a named tmux session means commands persist across agent turns and the agent can always read back the latest output reliably.
When to use it
- Running build scripts without leaving the agent context
- Checking git status during a code review session
- Listing directory contents to verify file operations
- Executing test commands and reading back results
- Running long-lived processes inside a persistent tmux session
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: run the test suite and show me the results
AGENT
- 1Attach to tmux session `claw`, creating it if it does not exist
- 2Send `npm test` to the session
- 3Wait for the command to complete
- 4Capture the pane output
- 5Return the test results to the user
OUTPUT
Full terminal output from the test run, including pass/fail summary