gas-town-workflow

gas-town-workflow is a skill for Claude Code, Codex from vosslab/vosslab-skills. It costs 48 tokens per session (1,944 once invoked), scanned A, original, MIT.

A workflow for coordinating multiple coding agents using named roles and convoy-based task groups. Gas Town is the name of this repository's role system, and a convoy is a tracked group of smaller tasks.

In plain words
What is it for?
Use it when explicitly working with Gas Town roles, convoys, or this repository's agent-coordination conventions.
Why use it?
It gives teams a shared way to split large jobs into clear pieces and keep assigned work moving toward completion.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: mentions subagents; mentions Claude Code.

Part of the vosslab-skills plugin — 42 skills, 14 agents shipped together

Good fit Use it when explicitly working with Gas Town roles, convoys, or this repository's agent-coordination conventions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vosslab/vosslab-skills/gas-town-workflow
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add vosslab/vosslab-skills --skill gas-town-workflow
Clone the repo
git clone --depth 1 https://github.com/vosslab/vosslab-skills

Made for: Claude Code, Codex.

Or install vosslab-skills, the plugin that ships this one along with the rest of its 42 skills, 14 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for gas-town-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/vosslab/vosslab-skills/gas-town-workflow/github.svg)](https://agentmods.dev/skills/vosslab/vosslab-skills/gas-town-workflow)
Your own site
<a href="https://agentmods.dev/skills/vosslab/vosslab-skills/gas-town-workflow"><img src="https://agentmods.dev/badge/skills/vosslab/vosslab-skills/gas-town-workflow/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for gas-town-workflow

Your own site · 80×15
<a href="https://agentmods.dev/skills/vosslab/vosslab-skills/gas-town-workflow"><img src="https://agentmods.dev/badge/skills/vosslab/vosslab-skills/gas-town-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,944 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00048 $0.01944
Opus 5 $0.00024 $0.00972
Sonnet 5 $0.00010 $0.00389
Haiku 4.5 $0.00005 $0.00194

Measured 10d ago against content hash ea8be789a30a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

gas-town-workflow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/management/gas-town-workflow/SKILL.md · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gas Town workflow

Gas Town is a role-based multi-agent coordination system. It maps theatrical role names to Claude Code agent types and uses convoy patterns to decompose work into atomic, trackable units. This skill teaches agents how to coordinate using Gas Town conventions within Claude Code's task and messaging system.

Core principles

GUPP (Gas Town Universal Propulsion Principle)

If there is work on your hook, you must run it. Agents autonomously proceed with available work without waiting for external input. GUPP is the heartbeat of autonomous operation. In Claude Code terms: if a task is assigned to you, start it immediately.

MEOW (Molecular Expression of Work)

Break large goals into detailed, atomic instructions. Every piece of work should be decomposed into trackable units that agents can execute autonomously. In Claude Code terms: use TaskCreate to break work into single-responsibility tasks with clear done-when criteria.

NDI (Nondeterministic Idempotence)

Orchestration of potentially unreliable processes toward useful outcomes. Persistent tasks and oversight agents (monitor, scheduler) guarantee eventual workflow completion even when individual operations fail. Retry and escalate, do not silently drop work.

Role mapping

This repo maps Gas Town theatrical roles to Claude Code agent types. Each role has a defined authority boundary and escalation target.

Gas Town role Agent Primary responsibility
Crew coder Production code, small doc updates
Refinery integrator Merge, rebase, conflict resolution
Witness monitor Observe progress, detect stalls, report
Deacon scheduler Trigger workflows, retry blocked/stalled tasks
Dogs maintainer Cleanup, lint, index regeneration
-- reviewer Read-only code review and plan auditing
-- tester Tests, coverage, validation
-- architect Cross-cutting design approval
-- planner Plans and docs only, never production code
-- orchestrator Parallel task coordination

Read the full file on GitHub · 214 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 214 lines · 48 tokens per session scan A ea8be789a30a

Subscribe to this mod's changes

gas-town-workflow is a skill published in the GitHub repository vosslab/vosslab-skills (2 stars, last pushed 15d ago), licensed MIT. It adds 48 tokens to every session and 1,944 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories