nwn-mcp: Skill for Claude Code

.claude/skills/create-adventure/SKILL.md

create-adventure is a skill for Claude Code from Txpple/nwn-mcp. It costs 0 tokens per session (3,675 once invoked), scanned A, original, MIT.

An automated pipeline for creating a complete Neverwinter Nights adventure from a high-level idea. It coordinates steps for building the module's world, story, characters, quests, challenges, rewards, and other content without revealing story details.

In plain words
What is it for?
Use it to turn a prompt such as an adventure setting and character level into a playable module, while keeping plot twists and encounter details hidden from the player.
Why use it?
It removes the need to build each part of a playable adventure manually or coordinate the content-building steps yourself.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is Txpple/nwn-mcp's own configuration. It tells Claude Code how to work on nwn-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 nwn-mcp configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/Txpple/nwn-mcp/master/.claude/skills/create-adventure/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Txpple/nwn-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 create-adventure

README.md
[![agentmods](https://agentmods.dev/badge/skills/txpple/nwn-mcp/create-adventure/github.svg)](https://agentmods.dev/skills/txpple/nwn-mcp/create-adventure)
Your own site
<a href="https://agentmods.dev/skills/txpple/nwn-mcp/create-adventure"><img src="https://agentmods.dev/badge/skills/txpple/nwn-mcp/create-adventure/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 create-adventure

Your own site · 80×15
<a href="https://agentmods.dev/skills/txpple/nwn-mcp/create-adventure"><img src="https://agentmods.dev/badge/skills/txpple/nwn-mcp/create-adventure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,675 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.03675
Opus 5 $0.00000 $0.01837
Sonnet 5 $0.00000 $0.00735
Haiku 4.5 $0.00000 $0.00367

Measured 9d ago against content hash b30d8cb1827e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

create-adventure 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/skills/create-adventure/SKILL.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/create-adventure

Master directive skill. Given a high-level creative goal ("make me an adventure for 3rd level characters in a haunted forest"), orchestrate the full module-building pipeline by invoking sub-skills in sequence.

Core Philosophy: Black Box Adventure Creation

The create-adventure pipeline is a white-glove, spoiler-free experience. The user provides a prompt and gets back a playable module — they should know nothing about the plot, encounters, NPCs, puzzles, or story beats. The fun is in discovering it all during play.

Rules for the orchestrator:

  • NEVER reveal plot details, encounter compositions, NPC names, quest objectives, puzzle solutions, or story twists to the user. Not in status updates, not in error messages, not in progress reports.
  • Status updates must be vague and atmospheric. Say things like "The world is taking shape...", "Populating the tavern...", "Adding some surprises..." — never "Placing 3 goblins in the cave" or "Creating a quest where the blacksmith asks you to find his hammer."
  • Sub-skills do NOT interact with the user. They are fully autonomous. If a sub-skill encounters a judgment call (too many monsters? unclear quest flow? conflicting placements?), the orchestrator makes the call — it does not ask the user. This introduces creative randomness, which is part of the fun.
  • The orchestrator is the decision-maker. When a sub-skill would normally need guidance, the orchestrator uses its own judgment. Lean toward "more fun" over "perfectly balanced." A slightly overtuned encounter or an unexpected twist is better than a bland, safe adventure.

Pre-Flight (before invoking any sub-skill)

Heads up before we dive in: Building a full adventure takes a while — typically 20–40 minutes of autonomous work across 9 phases. To avoid constant approval prompts, consider enabling Bypass permissions mode:

  • Desktop/VS Code: Settings → enable Allow dangerously skip permissions, then select Bypass permissions from the mode dropdown next to the send button.
  • CLI: Launch with claude --dangerously-skip-permissions
  • settings.json: Set "permissions": { "defaultMode": "bypassPermissions" }

Once pre-flight is done, the pipeline runs completely hands-free.

Read the full file on GitHub · 198 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 · 198 lines · 0 tokens per session scan A b30d8cb1827e

Subscribe to this mod's changes

create-adventure is a skill published in the GitHub repository Txpple/nwn-mcp (11 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,675 tokens. 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.