What is rpg-marketplace CLAUDE.md?

A repository guide for Claude Code, an AI coding assistant, explaining the project structure, commands, and two included plugins.

Use it when developing, testing, or running the RPG vault validator, or when editing the prompt-based RPG Loremaster plugin.

It gives the assistant and contributors the project-specific context needed to work safely without confusing code with instruction files.

How vstrapasson/rpg-marketplace configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to vstrapasson/rpg-marketplace. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/vstrapasson/rpg-marketplace/main/CLAUDE.md

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/vstrapasson/rpg-marketplace/claude-md/github.svg)](https://agentmods.dev/instructions/vstrapasson/rpg-marketplace/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/vstrapasson/rpg-marketplace/claude-md"><img src="https://agentmods.dev/badge/instructions/vstrapasson/rpg-marketplace/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/vstrapasson/rpg-marketplace/claude-md"><img src="https://agentmods.dev/badge/instructions/vstrapasson/rpg-marketplace/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,476 This file is loaded in full into every session.

When invoked 2,476 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.02476	$0.02476
Opus 5.5	$0.00990	$0.00990
Sonnet 5.5	$0.00495	$0.00495
Haiku 4.5	$0.00248	$0.00248

Measured 1mo ago against content hash 72a5f9e949a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rpg-marketplace CLAUDE.md 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 1mo 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.

CLAUDE.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this repo is

A Claude Code plugin marketplace (.claude-plugin/marketplace.json), not an application. It ships two plugins that are fundamentally different in kind — don't assume one's conventions apply to the other:

plugins/rpg-vault-guardian — real Node.js code (ESM .mjs) + a test suite. Validates/repairs Obsidian RPG vaults.
plugins/rpg-loremaster — pure prompt engineering. No code, no tests: just SKILL.md files, references/*.md, and agent markdown. Nothing here "runs"; it's instructions for the model.

Each plugin has its own .claude-plugin/plugin.json; the root marketplace.json registers both.

Commands

All runnable code lives in rpg-vault-guardian. There is no build step and no linter.

cd plugins/rpg-vault-guardian
npm test                                      # all tests (node --test scripts/test/*.test.mjs)
node --test scripts/test/checks-schema.test.mjs   # a single test file

# Run the tools directly (CWD must be a vault root, not this repo):
node scripts/validate.mjs --vault <dir> [--json] [--file <path>]   # exit 1 = errors, 2 = broken schema registry
node scripts/init.mjs                          # scaffold the 14 folders in CWD
node scripts/gen-mocs.mjs --vault <dir>        # regenerate _indices/ MOCs

rpg-vault-guardian architecture

scripts/schema.mjs is the single source of truth. It declares ENTITIES (the 12 entity types), COMMON_FIELDS, NON_ENTITY, IGNORED_TOP (with GLOSAS_FOLDER), MIRRORS_FOLDER, and SUMMARY_FIELDS (the types and fields the Vault module's Entity summary names directly). Folder names, required fields, enum values, and which relations may point where all derive from this one object. To add/change an entity type, field, or relation, edit only schema.mjs — folder scaffolding (init), validation, coherence checks, and MOCs all follow automatically. checkSchemaIntegrity() self-validates the registry (relation targets must reference known types; enums must have values; every name in SUMMARY_FIELDS must exist in ENTITIES), and validate.mjs aborts with exit code 2 if the registry is malformed.

Read the full file on GitHub · 61 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.

1mo ago Changed · +1 lines · +512 tokens per session 72a5f9e949a3
2mo ago First seen · 60 lines · 1,964 tokens per session scan A 61ee4ac12f7e

Subscribe to this mod's changes

rpg-marketplace CLAUDE.md is an instructions file published in the GitHub repository vstrapasson/rpg-marketplace (2 stars, last pushed 1mo ago), licensed MIT. It adds 2,476 tokens to every session, about $0.0099 per session on Opus 5.5. 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.

rpg-marketplace CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
rpg-marketplace CLAUDE.mdvstrapasson/rpg-marketplace	Instructions file	2	1mo ago	MIT	A	2,476	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

rpg-marketplace: Instructions file for Claude Code