Borrowing it
Nothing to install: this file belongs to thomandretti/ck3-strategy-advisor. 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/thomandretti/ck3-strategy-advisor/main/CLAUDE.mdgit clone --depth 1 https://github.com/thomandretti/ck3-strategy-advisorWrote 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/thomandretti/ck3-strategy-advisor/claude-md)<a href="https://agentmods.dev/instructions/thomandretti/ck3-strategy-advisor/claude-md"><img src="https://agentmods.dev/badge/instructions/thomandretti/ck3-strategy-advisor/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.
<a href="https://agentmods.dev/instructions/thomandretti/ck3-strategy-advisor/claude-md"><img src="https://agentmods.dev/badge/instructions/thomandretti/ck3-strategy-advisor/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01662 | $0.01662 |
| Opus 5 | $0.00831 | $0.00831 |
| Sonnet 5 | $0.00332 | $0.00332 |
| Haiku 4.5 | $0.00166 | $0.00166 |
Grade A, and why
ck3-strategy-advisor 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.
How it starts
The opening of the file, as written. The whole thing — 119 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 local stdio Model Context Protocol server that reads the player's latest
Crusader Kings III save and exposes their strategic situation to Claude as
curated, read-only tools (realm_overview, military, succession,
diplomacy, vassals, titles, factions, expansion, find_character,
character, foreign_realm).
It never modifies the save or the game. See README.md for install/config/usage.
Commands
npm install
npm run build # tsc -> dist/ (the registered MCP entry is dist/index.js)
npm run dev # run the server from source via tsx (no build step)
npm test # vitest run (whole suite)
npm run test:watch
npx vitest run tests/military.test.ts # single test file
There is no lint step. The build itself (tsc with strict: true) is the type gate.
Architecture
The data flows in one direction, save file → markdown tool output:
source.ts(SaveFileSource) — finds the newest parseable (text).ck3in the save dir: sorts candidates by mtime (ignoringlast_save.ck3), then reads each one's 256-byte header newest-first and returns the first whosedetectFormatis"text". This skips CK3 autosaves (always binary token format, regardless of Ironman) and Ironman saves, which are usually the newest file and would otherwise shadow a readable manual save. Falls back to the newest overall if none are text, so the binary/Ironman message still surfaces.envelope.ts(extractGamestate) — a.ck3isSAV-header + an embedded PKZIP. Detects Ironman vs text saves, unzips, returns thegamestateentry as a Buffer. Ironman detection is by the plaintextmeta_data={marker in the first 256 bytes, NOT by PK presence — both formats embed a zip. Ironman throwsIronmanError(surfaced as a friendly message, not an error).parser.ts(queryGamestate) — wraps a lazily-initializedjominiWASM parser singleton. Gives extractors aQuerywith.at(jsonPointer).snapshot.ts(buildSnapshot) — parses once and eagerly runs every extractor inside a singlequeryGamestatepass, producing aSnapshot(overview + military + succession + diplomacy + factions + vassals + expansion). One parse feeds all tools.cache.ts(SnapshotCache) — keyed bypath:mtimeMs. Returns the cachedSnapshotif the newest save is unchanged; coalesces concurrent builds of the same save into one parse; serves the last good snapshot on a transient/mid-write read failure. Also lazily materializes the gamestate as text once per save (rawGamestateText) forfind_character's substring search, and exposesquery()for tools that need a fresh jomini pass beyond the snapshot (e.g.character).extract/*.ts— pure functions(q: Query, loc: Localizer, ...) => Info. No I/O, no MCP. This is where save-field knowledge lives.tools/*.ts— eachregisterXTool(server, cache)registers one MCP tool: pull fromcache.get()(orcache.query()), format markdown, return it.tools/index.tswires them all up viaregisterAllTools.
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.
- 9d ago First seen · 119 lines · 1,662 tokens per session scan A a3672b63aa30
ck3-strategy-advisor CLAUDE.md is an instructions file published in the GitHub repository thomandretti/ck3-strategy-advisor (2 stars, last pushed 7d ago), licensed MIT. It adds 1,662 tokens to every session, about $0.0083 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.
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.