What is clausewitz-mcp CLAUDE.md?

A set of Claude Code instructions for clausewitz-mcp, an MCP server that reads and checks files for Paradox games such as Europa Universalis IV. It describes the project layout, commands, design rules, and tests.

Use it when developing or testing tools that parse, index, document, or validate Clausewitz/Jomini game scripts and localisation files.

It helps the assistant use exact game-generated documentation instead of guessing rules that may change between game updates.

How jacklenzotti/clausewitz-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jacklenzotti/clausewitz-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/jacklenzotti/clausewitz-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/jacklenzotti/clausewitz-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/jacklenzotti/clausewitz-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/jacklenzotti/clausewitz-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/jacklenzotti/clausewitz-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jacklenzotti/clausewitz-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.

Your own site · 80×15

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

Per session 621 This file is loaded in full into every session.

When invoked 621 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	$0.00621	$0.00621
Opus 5.5	$0.00248	$0.00248
Sonnet 5.5	$0.00124	$0.00124
Haiku 4.5	$0.00062	$0.00062

Measured 2mo ago against content hash c1c4bffd23f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

clausewitz-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 2mo 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 · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

clausewitz-mcp

MCP server for Paradox Clausewitz/Jomini modding. Static analysis only — it reads game files, never launches or attaches to a game.

Layout

clausewitz_mcp/
  parser.py        Clausewitz script tokenizer + error-tolerant parser
  docs.py          script_docs / dump_data_types ingester
  localisation.py  Paradox .yml loc reader (not YAML, don't use a YAML parser)
  games.py         per-game adapters + auto-detection
  index.py         workspace indexer, symbol tables, block rendering
  validate.py      validation passes
  server.py        FastMCP tool surface
tests/fixtures/    miniature EU4-shaped game + deliberately buggy mod

Commands

uv sync
uv run pytest tests/ -q
uv run clausewitz-mcp          # stdio server

Design rules

Grounding over recall. The whole point is that script_docs output is generated by the game binary and therefore exact for that patch. Never add a hand-maintained list of triggers/effects — it goes stale on the next update and reintroduces the confident-but-wrong failure mode the server exists to prevent.

Skip, don't guess. Checks that need authoritative data are skipped with an explanation when that data is absent (see unknown_script without a docs dump). A skipped check is honest; a guessed one destroys trust in every other check.

Low noise beats high coverage. A validation pass that fires on well-formed script is worse than no pass at all — modders stop reading the output. When adding a check, run it against the fixture mod and confirm it flags only the planted bug. _STRUCTURAL / _METADATA / _LOC_KEYS in validate.py exist for exactly this and will need extending per game.

Parse tolerantly. parser.py recovers from syntax errors and keeps going so one pass reports every problem in a file. Don't make it raise on bad input.

Docs format drifts. The dump layout varies by game and version, so docs.py keeps every entry's raw text verbatim and returns that to callers; structured fields are best-effort on top. If a split heuristic needs changing, keep the raw-text guarantee.

Read the full file on GitHub · 65 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.

2mo ago First seen · 65 lines · 621 tokens per session scan A c1c4bffd23f4

Subscribe to this mod's changes

clausewitz-mcp CLAUDE.md is an instructions file published in the GitHub repository jacklenzotti/clausewitz-mcp (3 stars, last pushed 2mo ago), licensed MIT. It adds 621 tokens to every session, about $0.0025 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.

Game development

clausewitz-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
clausewitz-mcp CLAUDE.mdjacklenzotti/clausewitz-mcp	Instructions file	3	2mo ago	MIT	A	621	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	144k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	281k	today	MIT	A	4,335	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot

clausewitz-mcp: Instructions file for Claude Code