home / skills / jeremylongshore / claude-code-plugins-plus-skills / gastown

This skill orchestrates multi-agent workflows with Gastown to run parallel tasks, track work, and automate code merging across projects.

npx playbooks add skill jeremylongshore/claude-code-plugins-plus-skills --skill gastown

Review the files below or copy the command above to add this skill to your agents.

Files (8)
SKILL.md
2.2 KB
---
name: gastown
description: |
  Manage multi-agent orchestrator for Claude Code. Use when user mentions gastown, gas town,
  gt commands, bd commands, convoys, polecats, crew, rigs, slinging work, multi-agent
  coordination, beads, hooks, molecules, workflows, the witness, the mayor, the refinery,
  the deacon, dogs, escalation, or wants to run multiple AI agents on projects simultaneously.
  Handles installation, workspace setup, work tracking, agent lifecycle, crash recovery,
  and all gt/bd CLI operations. Trigger with phrases like "gas town", "gt sling", "fire up the engine".
allowed-tools: Read, Write, Edit, Bash(cmd:*), Grep, Glob, WebFetch
version: 1.0.0
license: Apache-2.0
author: Numman Ali <[email protected]>
---

# Gastown

## Overview

Gas Town is a multi-agent orchestration system for Claude Code that enables parallel AI workers to execute tasks simultaneously. It provides work tracking through beads, agent lifecycle management via polecats and crew, and automated code merging through the Refinery.

## Prerequisites

- Go 1.21+ installed for CLI tools (`gt` and `bd`)
- Git configured with SSH or HTTPS access
- Terminal access for running commands
- Sufficient disk space for workspace (~100MB for ~/gt)
- GitHub account for repository integration (optional)

## Instructions

1. Install Gas Town CLI tools (gt and bd) using Go
2. Create your workshop directory at ~/gt
3. Run diagnostics with gt doctor and bd doctor
4. Add a project as a rig using gt rig add
5. Create work items as beads using bd create
6. Sling work to agents using gt sling
7. Monitor progress with gt status and gt peek
8. Let the Refinery merge completed work

The Cognition Engine. Track work with convoys; sling to agents.

## Output

- Executed gt and bd commands with results reported to user
- Engine status reports showing system health and worker states
- Work tracking updates (beads created, assigned, completed)
- Polecat and crew lifecycle events (spawn, completion, termination)
- Diagnostic results from gt doctor and bd doctor
- Merge pipeline status from Refinery operations

## Error Handling

See `{baseDir}/references/errors.md` for comprehensive error handling.

## Examples

See `{baseDir}/references/examples.md` for detailed examples.

## Resources


Overview

This skill manages a multi-agent orchestrator for Claude Code called Gastown. It installs CLI tools, sets up and monitors a workspace, and runs coordinated AI workers to execute parallel tasks. Use it to create, assign, and track work items while automating agent lifecycle and recovery.

How this skill works

The skill wraps the gt and bd command-line tools to install binaries, initialize a ~/gt workspace, and run diagnostics. It creates and tracks work as beads and convoys, slings tasks to agents (polecats and crew), and reports status and progress. It also monitors the Refinery merge pipeline and handles crash recovery and agent restarts.

When to use it

  • You need to run multiple AI agents on a single project simultaneously
  • You mention gastown, gas town, gt sling, bd commands, convoys, or crew
  • You want automated work tracking and merge automation via the Refinery
  • You need crash recovery and agent lifecycle management
  • You want CLI-driven setup and diagnostics for an agent workspace

Best practices

  • Install Go 1.21+ and ensure gt and bd binaries are on PATH before use
  • Create a dedicated ~/gt workspace with sufficient disk space (~100MB minimum)
  • Run gt doctor and bd doctor after setup and before launching large convoys
  • Organize work into small beads for parallel processing and easier merges
  • Monitor gt status and gt peek regularly and let the Refinery handle merges

Example use cases

  • Onboard a new project by installing gt/bd, adding a rig, and creating initial beads
  • Split a large coding task into beads and sling them to multiple polecats for parallel implementation
  • Recover from an agent crash by using built-in restart and crash-recovery commands
  • Run continuous integration of plugin changes while the Refinery automates merges and reports merge status
  • Track progress across many workers with gt status and export diagnostics for troubleshooting

FAQ

What prerequisites are required?

Install Go 1.21+, configure Git (SSH or HTTPS), and ensure terminal access with enough disk space for the ~/gt workspace.

How do I recover from an agent failure?

Use the integrated crash-recovery tools; run diagnostics (gt doctor / bd doctor), restart affected polecats or crew, and the system will reassign incomplete beads.