dispatchi
Launch non-blocking interactive Claude Code tasks for slash-only plugins like ralph-loop. Use when a task needs interactive slash commands and completion callback routing.
Why use this skill?
Use the dispatchi OpenClaw skill to run non-blocking, interactive Claude Code tasks in tmux. Ideal for complex automation and loop workflows.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/edxi/miniade-dispatchiWhat This Skill Does
The dispatchi skill is a specialized automation tool designed for OpenClaw agents to trigger non-blocking, interactive tasks powered by Claude Code. It acts as a wrapper around local script execution, specifically optimized for slash-only plugins like ralph-loop. Unlike standard command execution, dispatchi manages the lifecycle of a task by spinning up a dedicated tmux session in the background. This allows the AI agent to initiate complex, multi-step operations—such as iterative coding tasks or refactoring workflows—without blocking the main conversation thread. The skill includes built-in auto-exit logic that monitors for a 'completion-promise' (defaulting to "COMPLETE"), at which point it automatically terminates the tmux session and cleans up resources.
Installation
To integrate this skill into your OpenClaw environment, execute the following installation command in your terminal:
clawhub install openclaw/skills/skills/edxi/miniade-dispatchi
Ensure that your environment variables, specifically REPOS_ROOT, are correctly configured to point to your development directory, as the skill relies on accurate working directory mapping.
Use Cases
Use dispatchi when you need to run tasks that require persistent interactive sessions. Ideal scenarios include:
- Long-running refactoring tasks where the agent needs to invoke multiple slash commands sequentially.
- Automated loop-based operations like
ralph-loopthat require a background process to handle state. - Orchestrating tasks that produce extensive logs that would otherwise clutter your primary chat interface.
Example Prompts
- "/dispatchi web-portal feature-auth-update implement OAuth2 login flow using ralph-loop settings."
- "/dispatchi backend-service data-migration run the database schema migration scripts and wait for completion."
- "/dispatchi core-engine optimize-render-loop trigger the performance optimization routine and exit upon full completion promise."
Tips & Limitations
- Security: The skill strictly parses
dispatch.env.localfiles for key-value pairs without executing them, preventing shell injection. Network callbacks are disabled by default; you must explicitly setENABLE_CALLBACK=1to allow external reporting. - Lifecycle Management: Use
/cancel <run-id>if you need to abort a loop prematurely. Avoid launching multiple conflicting instances on the same project path. - Monitoring: Because it operates in a background tmux session, check the logs in your
REPOS_ROOTconfigured output paths if a task hangs or fails unexpectedly.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-edxi-miniade-dispatchi": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read, file-write, code-execution
Related Skills
dispatch
Launch non-blocking Claude Code headless tasks from slash command dispatch. Use when user requests async coding jobs and does not require slash-only Claude plugins.
cancel
Cancel an active interactive dispatch run by run-id from slash command cancel. Use when user wants to stop a dispatchi or ralph-loop task immediately.