openclaw-skill-gastownMulti-agent coding orchestrator using Gas Town (gt) and Claude Code. Use for ANY non-trivial coding task — multi-file changes, new features, refactors, bug fixes, anything involving code that needs to compile/run/test. Delegates work to parallel Claude Code agents (polecats) with git-backed persistent state, work tracking (beads), and coordination. Use when a task involves more than a single file edit or quick script.
Install via ClawdBot CLI:
clawdbot install saesak/openclaw-skill-gastownGrade Good — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
rm -rf /Accesses system directories or attempts privilege escalation
sudo rmCalls external URL not in known-safe list
https://go.dev/doc/installUses known external API (expected, informational)
raw.githubusercontent.comGenerated Mar 20, 2026
A development team uses Gas Town to manage multiple AI agents working on different features simultaneously. Each agent is assigned specific coding tasks via beads, with work state persisted across agent restarts. The Witness and Refinery agents monitor progress and handle failures, ensuring continuous integration without manual intervention.
A media company employs Gas Town to orchestrate AI agents for generating articles, editing, and publishing. Work is broken into molecules (e.g., research, drafting, proofreading) and distributed across agents. The system's persistent hooks prevent context loss, allowing seamless handoffs between agents for high-volume content production.
A customer service department uses Gas Town to manage AI agents handling ticket resolution. Agents are assigned beads for different query types (e.g., billing, technical issues), with the Mayor agent overseeing workflows. The GUPP principle ensures agents autonomously process tickets without delays, improving response times.
A research institute leverages Gas Town to coordinate AI agents analyzing large datasets. Agents work on distinct analysis steps (e.g., data cleaning, modeling, visualization) tracked as molecules. The NDI principle ensures reliable outcomes despite potential agent failures, with the Deacon agent managing data integrity.
A marketing team uses Gas Town to orchestrate AI agents for campaign execution, from content creation to performance tracking. Agents handle beads for tasks like ad copy generation and analytics, with the system's communication systems facilitating coordination. Persistent work state allows campaigns to continue uninterrupted during agent updates.
Offer Gas Town as a cloud-based service with tiered pricing based on the number of agents and workflows. Revenue comes from monthly subscriptions, with premium features like advanced monitoring and custom integrations. This model targets enterprises needing scalable multi-agent orchestration.
Sell perpetual licenses for on-premises deployment to large organizations with strict data security requirements. Revenue includes upfront licensing fees and annual support contracts. This model suits industries like finance or healthcare where data cannot leave internal systems.
Provide professional services to customize and integrate Gas Town into existing client workflows. Revenue is generated from project-based fees for setup, training, and ongoing optimization. This model targets companies lacking in-house expertise for complex AI agent deployments.
💬 Integration Tip
Start by defining clear molecules and beads for workflows, then use the quick start guide to set up agents with persistent hooks to avoid context loss.
Scored Jun 17, 2026
AI Analysis
The skill contains potentially destructive shell commands (rm -rf, sudo rm) in tool definitions which could be misused, but these appear to be part of a legitimate multi-agent orchestration system's cleanup operations. External API usage (go.dev, raw.githubusercontent.com) is consistent with development tool installation and appears legitimate.
Audited Apr 16, 2026 · audit v1.0
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.