World-Anvil-MCP: Instructions file for Claude Code

CLAUDE.md

World-Anvil-MCP CLAUDE.md is an instructions file for Claude Code from datagen24/World-Anvil-MCP. It costs 3,491 tokens per session, scanned A, original, BSD-3-Clause.

Project instructions for an MCP server that connects Claude Code to the World Anvil API, a service for managing Dungeons & Dragons campaign worlds. They describe the project architecture, design principles, and planned campaign workflows.

In plain words
What is it for?
Use them when developing or extending the World Anvil MCP server for D&D campaign management and worldbuilding.
Why use it?
They give a coding agent the context needed to work consistently in an early-stage Python project, including its asynchronous design, data models, retries, rate limits, and caching.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions subagents; names the TodoWrite tool.

This is datagen24/World-Anvil-MCP's own configuration. It tells Claude Code how to work on World-Anvil-MCP itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything World-Anvil-MCP configures →

Reuse

Borrowing it

Nothing to install: this file belongs to datagen24/World-Anvil-MCP. 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/datagen24/World-Anvil-MCP/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/datagen24/World-Anvil-MCP

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 World-Anvil-MCP CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/datagen24/world-anvil-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/datagen24/world-anvil-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/datagen24/world-anvil-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/datagen24/world-anvil-mcp/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.

agentmods 80×15 button for World-Anvil-MCP CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/datagen24/world-anvil-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/datagen24/world-anvil-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,491 This file is loaded in full into every session.
When invoked 3,491 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.03491 $0.03491
Opus 5 $0.01746 $0.01746
Sonnet 5 $0.00698 $0.00698
Haiku 4.5 $0.00349 $0.00349

Measured 9d ago against content hash e907af5c14bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

World-Anvil-MCP 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 9d 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 · 478 lines

How it starts

The opening of the file, as written. The whole thing — 478 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.


Project Overview

World Anvil MCP Server - An MCP (Model Context Protocol) server that bridges Claude Code with the World Anvil API for AI-assisted D&D campaign management and worldbuilding.

Status: Phase 0.4 (Early Implementation) — Architecture complete; core scaffolding in progress License: BSD 3-Clause Python: 3.11+ required


Architecture

Core Design Principles

  1. MCP-Native: Built-in FastMCP Context integration (not bolted on)
  2. Async-First: All I/O uses async/await with httpx.AsyncClient
  3. Type-Safe: Pydantic v2 models for all API responses
  4. Resilient: Built-in retry logic, rate limiting, and caching
  5. Workflow-Driven: Designed for 10 specific D&D campaign workflows (see docs/workflows/)

Component Architecture

MCP Server (FastMCP)
  └─> WorldAnvilClient (main entry point)
       ├─> Endpoint Classes (ArticleEndpoint, WorldEndpoint, etc.)
       │    └─> BaseEndpoint (generic request handling)
       │         ├─> ResponseCache (TTL-based caching)
       │         ├─> RateLimiter (token bucket, 60 req/min)
       │         └─> Retry Logic (tenacity with exponential backoff)
       └─> httpx.AsyncClient (connection pooling, timeout management)

Key Pattern: The client delegates to specialized endpoint classes (15+ endpoints planned), each inheriting from BaseEndpoint[T] generic that handles:

  • Request execution with MCP Context logging
  • Automatic retries for transient failures (RateLimitError, ServerError)
  • Response caching with granularity-aware keys
  • Error parsing and exception mapping

Critical Implementation Details

Authentication: World Anvil uses custom headers (NOT Bearer tokens):

headers = {
    "x-auth-token": user_token,      # Lowercase, not X-Auth-Token
    "x-application-key": app_key,    # Lowercase, not X-Application-Key
}

Read the full file on GitHub · 478 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. 9d ago First seen · 478 lines · 3,491 tokens per session scan A e907af5c14bf

Subscribe to this mod's changes

World-Anvil-MCP CLAUDE.md is an instructions file published in the GitHub repository datagen24/World-Anvil-MCP (1 stars, last pushed 9mo ago), licensed BSD-3-Clause. It adds 3,491 tokens to every session, about $0.0175 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 instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens