Claude Code Dispatch
Dispatch development tasks to Claude Code with automatic callback on completion. Supports Agent Teams for parallel dev+test, cost controls, model fallback, and MCP integration.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add claude-code-dispatch npx -- -y @trustedskills/claude-code-dispatch
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"claude-code-dispatch": {
"command": "npx",
"args": [
"-y",
"@trustedskills/claude-code-dispatch"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
Claude Code Dispatch allows you to send development tasks to Claude Code and receive notifications upon completion, all without needing to actively monitor the process. It leverages OpenClaw for task management and Telegram for notifications, enabling a "fire-and-forget" workflow with features like cost controls and isolated worktrees. This skill significantly reduces token usage compared to interactive sessions.
When to use it
- Automated Code Generation: Dispatch code generation tasks (e.g., creating unit tests or refactoring) and receive the results without constant monitoring.
- Parallel Development: Utilize agent teams with dedicated testing agents for concurrent development efforts across multiple isolated Git worktrees.
- Cost-Constrained Tasks: Set budget limits (
--max-budget-usd) and turn limits (--max-turns) to control costs when using Claude Code. - CI/CD Integration: Automate code review or analysis steps within your CI/CD pipelines, receiving notifications upon task completion.
Key capabilities
- Fire & Forget task dispatch with automatic callbacks
- Agent Teams for parallel development and specialized subagents
- Cost Controls: Budget and turn limits
- Git Worktree Isolation for concurrent tasks
- Custom Subagent definition via JSON configuration
- Rich Telegram notifications including status, duration, and test results
Example prompts
- "Dispatch a task to generate unit tests for
src/main.pywith a budget of $2." - "Run code review on the
feature-branchworktree using my custom security reviewer agent." - "Generate documentation for the API, limiting it to 10 turns."
Tips & gotchas
- Ensure OpenClaw and Claude Code CLI are installed and configured correctly before use.
- Telegram bot configuration within OpenClaw is required for notifications to function.
Requirements
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Installing this skill downloads the exact code at commit c323fd71, not the current state of the repository. This prevents supply-chain attacks from unauthorized updates.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.
Install command fetches the verified snapshot, not the live repository.