tmw-mcp: Instructions file for Claude Code

CLAUDE.md

tmw-mcp CLAUDE.md is an instructions file for Claude Code from bjorn/tmw-mcp. It costs 2,522 tokens per session, scanned D, original, MIT.

Repository instructions for a Python client for The Mana World, an online role-playing game, that exposes the game through an MCP server so an AI agent can use it. The same game client also supports a command-line program and an older file-based bot.

In plain words
What is it for?
Developing or testing the game's AI-agent interface, command-line client, bot, dashboard, combat, following, resources, and credential handling.
Why use it?
They explain how the project is structured, how to install and test it, and how to keep tests from changing the user's real local state files.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

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

Reuse

Borrowing it

Nothing to install: this file belongs to bjorn/tmw-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/bjorn/tmw-mcp/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/bjorn/tmw-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 tmw-mcp CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/bjorn/tmw-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/bjorn/tmw-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,522 This file is loaded in full into every session.
When invoked 2,522 The same file — it is already loaded in full.
Security scan D 2 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 $0.02522 $0.02522
Opus 5.5 $0.01009 $0.01009
Sonnet 5.5 $0.00504 $0.00504
Haiku 4.5 $0.00252 $0.00252

Measured 1mo ago against content hash 83a4d714328d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade D, and why

tmw-mcp CLAUDE.md scanned grade D with 2 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- **Credentials.** `credentials.json` is `chmod 600` (owner read/write only) and gitignored. Never log it or commit it.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf dist build *.egg-info
CLAUDE.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 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 is

A Python client for The Mana World (a tmwAthena-based MMORPG) that exposes the game as an MCP server. The intended consumer is an AI agent (Claude Code), but a human-driven CLI (tmw_mcp/main.py) and a legacy file-driven bot (tmw_mcp/bot.py) share the same game-client core.

All runtime code lives in the tmw_mcp/ package. The only third-party dependency is mcp. Everything else is stdlib.

Commands

# Setup
python3 -m venv .venv
.venv/bin/pip install -e .

# Run the whole suite (from repo root; loads tests/__init__.py which
# redirects XDG_STATE_HOME and XDG_CACHE_HOME to tempdirs so tests
# don't pollute your real ~/.local/state/tmw-mcp).
.venv/bin/python -m unittest discover

# Run a single test (still from repo root)
.venv/bin/python -m unittest tests.test_dashboard
.venv/bin/python -m unittest tests.test_shim_proxy
.venv/bin/python -m unittest tests.test_follow
.venv/bin/python -m unittest tests.test_ranged_combat
.venv/bin/python -m unittest tests.test_resources
.venv/bin/python -m unittest tests.test_credentials

# Console scripts (created by ``pip install -e .``)
tmw-mcp                                  # stdio MCP entry point (with self-restart shim)
tmw-mcp-server [--shim] [--dashboard-port N]   # daemon directly (advanced)
tmw-mcp-cli --credentials credentials.json     # interactive human REPL
tmw-mcp-register --user USERNAME --char-name CHARNAME

# Module form (works without installing)
.venv/bin/python -m tmw_mcp.mcp_shim
.venv/bin/python -m tmw_mcp.mcp_server [--shim]
.venv/bin/python -m tmw_mcp.main --credentials credentials.json
.venv/bin/python -m tmw_mcp.register --user USERNAME --char-name CHARNAME

# Regenerate PACKET_SIZES from upstream tmwa (dev tool)
python3 scripts/extract_packets.py    # prints a dict; paste over PACKET_SIZES in tmw_mcp/packets.py

No linter or formatter is wired up. Tests insert the repo root onto sys.path themselves so they run from any cwd.

Read the full file on GitHub · 128 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. 1mo ago Changed · +30 tokens per session 83a4d714328d
  2. 2mo ago First seen · 128 lines · 2,492 tokens per session scan D 5bbb1ce3cd65

Subscribe to this mod's changes

tmw-mcp CLAUDE.md is an instructions file published in the GitHub repository bjorn/tmw-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 2,522 tokens to every session, about $0.0101 per session on Opus 5.5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

tmw-mcp CLAUDE.md compared with instructions from other repositories

tmw-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
tmw-mcp CLAUDE.mdbjorn/tmw-mcpInstructions file01mo agoMITD2,522Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150kyesterdayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283kyesterdayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot