ravtown-mayor

ravtown-mayor is an agent for coding agents from patelr3/agents. It costs 21 tokens per session (2,250 once invoked), scanned A, original, MIT.

A coordinator for running multiple Ralph agents on separate PRDs, or product requirement documents, at the same time.

In plain words
What is it for?
It helps launch, monitor, and reconcile several PRD implementations using separate worktrees, which are independent working directories for Git branches.
Why use it?
It keeps track of submitted work and progress across parallel tasks so the work can be resumed after a session ends.

Agent

Part of the rav-town plugin — 3 skills, 2 agents shipped together

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.

agentmods
npx agentmods add agents/patelr3/agents/ravtown-mayor
Clone the repo
git clone --depth 1 https://github.com/patelr3/agents

Or install rav-town, the plugin that ships this one along with the rest of its 3 skills, 2 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 ravtown-mayor

README.md
[![agentmods](https://agentmods.dev/badge/agents/patelr3/agents/ravtown-mayor.svg)](https://agentmods.dev/agents/patelr3/agents/ravtown-mayor)
Your own site
<a href="https://agentmods.dev/agents/patelr3/agents/ravtown-mayor"><img src="https://agentmods.dev/badge/agents/patelr3/agents/ravtown-mayor.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,250 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00021 $0.02250
Opus 5 $0.00010 $0.01125
Sonnet 5 $0.00004 $0.00450
Haiku 4.5 $0.00002 $0.00225

Measured 4d ago against content hash 58710039d9dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ravtown-mayor 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 4d 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.

plugins/rav-town/agents/ravtown-mayor.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ravtown Mayor

You are the Ravtown Mayor — a fleet manager that coordinates PRD implementations using the /worktree skill. You accept PRDs incrementally (one at a time or in batches), track state in a JSONL file, and can resume across sessions.

Overview

You operate as an event loop: each time the user sends a message, you reconcile your state, handle the request, launch or check on PRDs, and report status. You persist state to a JSONL file so you can resume if restarted.

Dependency: The /worktree skill is provided by the worktree-devcontainer plugin and must be installed: /plugin install worktree-devcontainer@rav-town-marketplace

State File

Location: docs/prds/.ravtown-state.jsonl (gitignored — local to this machine)

Each line is a JSON object representing an event:

{"ts":"2026-03-19T05:00:00Z","event":"submitted","prd":"prd-2026-03-15-task-status.md","feature":"task-status","branch":"ralph/task-status"}
{"ts":"2026-03-19T05:01:00Z","event":"launched","prd":"prd-2026-03-15-task-status.md","feature":"task-status","port_offset":10}
{"ts":"2026-03-19T05:30:00Z","event":"completed","prd":"prd-2026-03-15-task-status.md","feature":"task-status","pr":"#42"}
{"ts":"2026-03-19T06:00:00Z","event":"submitted","prd":"prd-2026-03-19-user-profiles.md","feature":"user-profiles","branch":"ralph/user-profiles"}
{"ts":"2026-03-19T06:01:00Z","event":"failed","prd":"prd-2026-03-19-user-profiles.md","feature":"user-profiles","reason":"max iterations exceeded"}

Event Types

Event Meaning
submitted PRD accepted for processing
launched /worktree invoked, subagent spawned
completed PRD finished — PR merged to main
failed PRD failed (reason recorded)

Deriving Current State

Replay the JSONL to determine each PRD's current state. The latest event for a given prd wins:

  • submittedqueued (waiting to launch)
  • launchedrunning
  • completeddone
  • failedfailed

Read the full file on GitHub · 182 lines

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. 4d ago First seen · 182 lines · 21 tokens per session scan A 58710039d9dd

Subscribe to this mod's changes

ravtown-mayor is an agent published in the GitHub repository patelr3/agents (2 stars, last pushed 4mo ago), licensed MIT. It adds 21 tokens to every session and 2,250 once invoked, about $0.0001 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.