A robust runner for non-blocking, interactive Claude Code tasks utilizing slash commands and completion callbacks.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install miniade-dispatchi
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install miniade-dispatchi using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is dispatchi?
dispatchi is a specialized utility designed to manage interactive Claude Code execution within the Openclaw Skills ecosystem. It facilitates the launching of background tasks that require interactive slash command support, specifically catering to plugins like ralph-loop. By leveraging tmux sessions, it ensures that long-running tasks do not block the primary agent interface while providing reliable callback routing once completion triggers are met.
This skill is essential for developers who need to run complex, iterative coding agent tasks without stalling their active workspace. By providing a bridge between slash-only plugins and background execution, it enhances the utility of Openclaw Skills for sophisticated multi-step automation workflows.
dispatchi Use Cases
- Executing slash-only Claude Code plugins in a non-blocking background environment.
- Automating multi-step interactive coding tasks that require iterative feedback without manual oversight.
- Integrating completion callbacks into complex agentic workflows for automated status reporting.
- Managing concurrent Claude sessions across multiple projects within an Openclaw Skills environment.
How dispatchi Works
- The user triggers the command using the syntax
/dispatchi <project> <task-name> <prompt...>. - The system validates the provided arguments and initializes a local tmux session to isolate the process.
- A Claude process is launched within the tmux session using the bundled
claude_code_run.pyscript. - The skill continuously monitors the output for a predefined completion promise, which defaults to the word COMPLETE on its own line.
- Upon detecting the completion string, the wrapper automatically issues an
/exitcommand and terminates the tmux session.
dispatchi Setup
To set up dispatchi within your Openclaw Skills environment, ensure the runner script is executable and optionally configure your environment variables.
# Ensure the dispatchi script has execution permissions
chmod +x scripts/run_dispatchi.sh
# Optional: Configure environment variables in the local env file
echo "ENABLE_CALLBACK=1" >> skills/dispatch.env.local
You can also inject configurations via the standard Openclaw Skills entry configuration under skills.entries.dispatchi.env.
dispatchi Data Schema & Taxonomy
The skill organizes its operations based on the following data structure and environment mappings:
| Parameter | Description |
|---|---|
| Project | The target subdirectory located within your REPOS_ROOT path. |
| Task Name | A unique identifier used to track the specific background execution. |
| Max Iterations | Controls the loop depth; defaults to 20 iterations. |
| Completion Promise | The specific string (default: COMPLETE) that triggers task finalization. |
| REPOS_ROOT | The base directory for projects, defaulting to /home/miniade/repos. |
| Workdir | Resolved dynamically as ${REPOS_ROOT}/<project>. |
dispatchi Advanced Features
- Interactive slash-only plugin compatibility for advanced Openclaw Skills usage scenarios.
- Process isolation and persistence through automated tmux session management.
- Secure environment variable handling using a key-value allowlist to prevent arbitrary code execution.
- Asynchronous task control allowing users to stop running loops via the
/cancel <run-id>command. - Optional network callback support for integrating task results with external webhooks or APIs.
SKILL.md
Loading
Related Openclaw Skills
Cancel Dispatch Run
A vital utility for stopping active AI dispatch tasks and ralph-loop sessions through a simple slash command.
Explain Code
A visualization and teaching tool that breaks down complex code into relatable analogies, ASCII diagrams, and step-by-step walkthroughs.
The Prompting Company (TPC) Brand Visibility Skill
The Prompting Company skill provides comprehensive brand analytics and Share of Voice tracking across major AI engines like ChatGPT, Claude, and Gemini.
Lokuli Service Booking
An MCP-driven skill that enables AI agents to search, check availability, and book over 75 categories of local professional services.
Sigil Security
Sigil Security provides a robust 3-layer Guardian validation and co-signing framework for securing ERC-4337 smart wallets used by AI agents.
Sardis Balance
A secure, read-only analytics skill for monitoring Sardis agent wallet balances and transaction history.
Featured*
