gastown

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".

1,868 stars

Best use case

gastown is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

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".

Teams using gastown should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/gastown/SKILL.md --create-dirs "https://raw.githubusercontent.com/jeremylongshore/claude-code-plugins-plus-skills/main/plugins/community/gastown/skills/gastown/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/gastown/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How gastown Compares

Feature / AgentgastownStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

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".

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# 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 `${CLAUDE_SKILL_DIR}/references/errors.md` for comprehensive error handling.

## Examples

See `${CLAUDE_SKILL_DIR}/references/examples.md` for detailed examples.

## Resources


- Official Gastown documentation
- Community best practices and patterns
- Related skills in this plugin pack

Related Skills

schema-optimization-orchestrator

1868
from jeremylongshore/claude-code-plugins-plus-skills

Multi-phase schema optimization workflow orchestrator. Creates session directories, spawns phase agents sequentially, validates outputs, aggregates results. Trigger: "run schema optimization", "optimize schema workflow", "execute schema phases"

test-skill

1868
from jeremylongshore/claude-code-plugins-plus-skills

Test skill for E2E validation. Trigger with "run test skill" or "execute test". Use this skill when testing skill activation and tool permissions.

example-skill

1868
from jeremylongshore/claude-code-plugins-plus-skills

Brief description of what this skill does and when the model should activate it. Use when [describe the user's intent or situation]. Trigger with "example phrase", "another trigger", "/example-skill".

testing-visual-regression

1868
from jeremylongshore/claude-code-plugins-plus-skills

Detect visual changes in UI components using screenshot comparison. Use when detecting unintended UI changes or pixel differences. Trigger with phrases like "test visual changes", "compare screenshots", or "detect UI regressions".

generating-unit-tests

1868
from jeremylongshore/claude-code-plugins-plus-skills

Test automatically generate comprehensive unit tests from source code covering happy paths, edge cases, and error conditions. Use when creating test coverage for functions, classes, or modules. Trigger with phrases like "generate unit tests", "create tests for", or "add test coverage".

generating-test-reports

1868
from jeremylongshore/claude-code-plugins-plus-skills

Generate comprehensive test reports with metrics, coverage, and visualizations. Use when performing specialized testing. Trigger with phrases like "generate test report", "create test documentation", or "show test metrics".

orchestrating-test-execution

1868
from jeremylongshore/claude-code-plugins-plus-skills

Test coordinate parallel test execution across multiple environments and frameworks. Use when performing specialized testing. Trigger with phrases like "orchestrate tests", "run parallel tests", or "coordinate test execution".

managing-test-environments

1868
from jeremylongshore/claude-code-plugins-plus-skills

Test provision and manage isolated test environments with configuration and data. Use when performing specialized testing. Trigger with phrases like "manage test environment", "provision test env", or "setup test infrastructure".

generating-test-doubles

1868
from jeremylongshore/claude-code-plugins-plus-skills

Generate mocks, stubs, spies, and fakes for dependency isolation. Use when creating mocks, stubs, or test isolation fixtures. Trigger with phrases like "generate mocks", "create test doubles", or "setup stubs".

generating-test-data

1868
from jeremylongshore/claude-code-plugins-plus-skills

Generate realistic test data including edge cases and boundary conditions. Use when creating realistic fixtures or edge case test data. Trigger with phrases like "generate test data", "create fixtures", or "setup test database".

analyzing-test-coverage

1868
from jeremylongshore/claude-code-plugins-plus-skills

Analyze code coverage metrics and identify untested code paths. Use when analyzing untested code or coverage gaps. Trigger with phrases like "analyze coverage", "check test coverage", or "find untested code".

managing-snapshot-tests

1868
from jeremylongshore/claude-code-plugins-plus-skills

Create and validate component snapshots for UI regression testing. Use when performing specialized testing. Trigger with phrases like "update snapshots", "test UI snapshots", or "validate component snapshots".