Borrowing it
Nothing to install: this file belongs to Txpple/nwn-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.
curl -O https://raw.githubusercontent.com/Txpple/nwn-mcp/master/CLAUDE.mdgit clone --depth 1 https://github.com/Txpple/nwn-mcpWrote 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.
[](https://agentmods.dev/instructions/txpple/nwn-mcp/claude-md)<a href="https://agentmods.dev/instructions/txpple/nwn-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/txpple/nwn-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.05761 | $0.05761 |
| Opus 5 | $0.02880 | $0.02880 |
| Sonnet 5 | $0.01152 | $0.01152 |
| Haiku 4.5 | $0.00576 | $0.00576 |
Grade A, and why
nwn-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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NWN MCP Server
MCP (Model Context Protocol) server for Neverwinter Nights Enhanced Edition module files (.mod). Wraps neverwinter.nim CLI tools to expose module content as structured, queryable data for LLMs.
Working Style
- Do NOT auto-export HTML reports after creating or painting areas. Only export reports when the user explicitly asks for one.
- Always repack after creating/painting test areas so the user can see them in the toolset. Mention that you repacked.
- MCP server restart required after code changes. After editing TypeScript source and running
npm run build, the MCP server must be restarted for new/changed tools to become available. Ask the user to restart before attempting to use newly added tools. - Keep skills in sync with tools. When adding, renaming, or changing tool parameters/behavior, immediately update the
.claude/skills/SKILL.md files that reference those tools. The LLM follows skill instructions, not tool schemas — if a skill doesn't mention a parameter, the LLM won't use it.
Design Intent
This MCP serves two purposes:
(a) AI-assisted human module design — A human author works with an AI assistant to build, modify, and extend NWN modules via natural language. The human stays in creative control.
(b) AI-driven creative module building — A small, proof-of-concept tool for building one-shot adventures for yourself and friends. Spoiler-free by design, so the DM can be surprised too. An LLM autonomously designs and constructs module content based on high-level goals: generating quests, writing dialogue, designing areas, placing objects, building story. This is orchestrated via the /create-adventure skill and its sub-skill agents.
Spatial Awareness
The visualize_area tool returns a canonical JSON spatial payload — the LLM's primary instrument for understanding an area (tile grid, walkable zones, zone connectivity, all placed objects with positions and properties). Call it before making placement or quest decisions.
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.
- 7d ago First seen · 251 lines · 5,761 tokens per session scan A 2bea90a84265
nwn-mcp CLAUDE.md is an instructions file published in the GitHub repository Txpple/nwn-mcp (10 stars, last pushed 5mo ago), licensed MIT. It adds 5,761 tokens to every session, about $0.0288 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.
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.
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.
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).
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).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.