Skip to content
TrustedSkillsbeta
Back to all skills

Claude Code Dispatch

Listed
win4r·v1.0.0·agents·MIT

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.

Repository

Install on your platform

Showing OpenClaw.

  1. 1

    Run this in your terminal

    terminal
    $ openclaw skills install claude-code-dispatch

What we know about this skill

Publisher

win4r

Taken from the source listing. We haven't verified who controls this account.

Install target

Pinned to c323fd71

Installs fetch a stored snapshot of that commit, so the code can't change after the fact.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill failed 1 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

  • No undeclared network calls: failed

    Contacts 1 host that is neither well-known infrastructure nor declared in the skill's frontmatter: code.claude.com.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

    Hosts contacted

    code.claude.comundeclared127.0.0.1local

    What it found (3 of 5)

    • scripts/claude_code_run.py:14contacts code.claude.com
      - Headless (Agent SDK): https://code.claude.com/docs/en/headless
    • scripts/claude_code_run.py:15contacts code.claude.com
      - Agent Teams: https://code.claude.com/docs/en/agent-teams
    • scripts/claude_code_run.py:16contacts code.claude.com
      - Subagents: https://code.claude.com/docs/en/sub-agents

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned win4r/claude-code-dispatch at c323fd714b.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
c323fd714b
Manifest
SKILL.md
Scanned
8 files, 2,159 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

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.py with a budget of $2."
  • "Run code review on the feature-branch worktree 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

Required binaries

bash

Tags

claudedispatchautomationmulti-agentgitworktree