rpg-writers-room

rpg-writers-room is a plugin for Claude Code from vstrapasson/rpg-marketplace. Its manifest loads nothing; the 1 skill, 1 command, 2 agents it bundles cost 606 tokens per session together, scanned A, original, MIT.

A review panel for tabletop role-playing campaigns that reads your Obsidian notes and session transcripts. Five critics examine the campaign writing and how it was run at the table, using quoted evidence.

In plain words
What is it for?
Review lore, NPCs, factions, places, pacing, player choice, clues, and the handling of sessions. It produces a self-contained HTML report and does not create campaign content or edit your notes.
Why use it?
It separates problems in the written campaign from problems in play, so feedback is based on specific notes and transcript moments rather than guesses. It also shows where the critics disagree and gives prioritized fixes.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest.

Good fit Review lore, NPCs, factions, places, pacing, player choice, clues, and the handling of sessions. It produces a self-contained HTML report and does not create campaign content or edit your notes.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add vstrapasson/rpg-marketplace/plugin install rpg-writers-room
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.

Clone the repo
git clone --depth 1 https://github.com/vstrapasson/rpg-marketplace

Made for: Claude Code.

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 rpg-writers-room

README.md
[![agentmods](https://agentmods.dev/badge/plugins/vstrapasson/rpg-marketplace/rpg-writers-room/github.svg)](https://agentmods.dev/plugins/vstrapasson/rpg-marketplace/rpg-writers-room)
Your own site
<a href="https://agentmods.dev/plugins/vstrapasson/rpg-marketplace/rpg-writers-room"><img src="https://agentmods.dev/badge/plugins/vstrapasson/rpg-marketplace/rpg-writers-room/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 rpg-writers-room

Your own site · 80×15
<a href="https://agentmods.dev/plugins/vstrapasson/rpg-marketplace/rpg-writers-room"><img src="https://agentmods.dev/badge/plugins/vstrapasson/rpg-marketplace/rpg-writers-room.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 1 skill, 1 command, 2 agents cost 606 tokens a session between them.
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.
Security

Grade A, and why

rpg-writers-room 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.

plugins/rpg-writers-room/.claude-plugin/plugin.json · 9 lines

What it actually says

{
  "name": "rpg-writers-room",
  "description": "A panel of expert critics for a campaign you have already built. Reads the Obsidian vault (lore, NPCs, factions, cities, locations, the campaign bible) and the session transcripts, then convenes five rubric-grounded lenses — the Alexandrian architect, the Lazy GM, the showrunner, the player advocate, and the dramaturg — to judge two different things with two different rubrics: the quality of the writing, and the quality of the conducting at the table. Every claim is anchored to a verbatim quote with a vault path or a transcript timecode; anything unsupported is rated as insufficient evidence rather than guessed. The orchestrator synthesizes consensus, surfaces disagreement as trade-offs instead of resolving it silently, and renders a self-contained HTML report with prioritized, constructive fixes. Critique only — it never generates campaign content, never edits the vault, and never claims to be an objective score.",
  "version": "0.2.0",
  "author": { "name": "Vagner Strapasson", "email": "[email protected]" },
  "license": "MIT",
  "keywords": ["rpg", "ttrpg", "pathfinder", "pf2e", "gm-tools", "critique", "review", "feedback", "session-transcripts", "writing-craft", "llm-judge", "panel-of-judges"]
}
Contents

What it installs

The manifest is a name and a version. 1 skill, 1 command, 2 agents travel with it, and installing the plugin installs all of them — 606 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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 · 9 lines scan A 4fa34a139149

Subscribe to this mod's changes

rpg-writers-room is a plugin published in the GitHub repository vstrapasson/rpg-marketplace (2 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.