mcp-launchbox CLAUDE.md

A repository instruction file for mcp-launchbox, an MCP server that exposes a local LaunchBox game library to an agent. MCP is a standard way for an agent to communicate with external tools.

In plain words
What is it for?
Use it when installing dependencies, building, testing, linting, running, or manually sending JSON-RPC requests to mcp-launchbox.
Why use it?
It gives contributors the commands, required environment setting, testing method, and source-file map needed to build and check the project.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/danjam/mcp-launchbox/claude-md
Clone the repo
git clone --depth 1 https://github.com/danjam/mcp-launchbox
Per session 2,356 This file is loaded in full into every session.
When invoked 2,356 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.02356 $0.02356
Opus 5 $0.01178 $0.01178
Sonnet 5 $0.00471 $0.00471
Haiku 4.5 $0.00236 $0.00236

Measured 2d ago against content hash 1b5164446333, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-launchbox 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 2d 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 · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 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.

Build and Run

npm install      # Install dependencies (also runs tsc via prepare)
npm run build    # Compile TypeScript (tsc)
npm start        # Run server (node dist/index.js)

Unit tests via node:test (built-in), linting via Biome:

npm test            # Build + run tests
npm run test:only   # Run tests without rebuilding
npm run lint        # Check for issues
npm run lint:fix    # Auto-fix issues

Environment

  • LAUNCHBOX_PLATFORMS_PATH — Required. Path to the directory containing platform XML files (e.g. /mnt/d/LaunchBox/Data/Platforms).

Manual Testing

Pipe JSON-RPC messages to stdin:

printf '{"jsonrpc":"2.0","id":1,"method":"initialize"}\n{"jsonrpc":"2.0","id":2,"method":"tools/list"}\n' | LAUNCHBOX_PLATFORMS_PATH=/mnt/d/LaunchBox/Data/Platforms node dist/index.js

Architecture

This is a Model Context Protocol (MCP) server that wraps a local LaunchBox game library. It communicates over stdin/stdout using JSON-RPC 2.0 — there is no HTTP server or MCP SDK dependency.

Source files:

  • src/index.ts — Entrypoint: JSON-RPC error code constants, I/O helpers (send, reply, textReply, errorReply, error), env var check, library loading, reload concurrency guard, request dispatch with structural validation, readline listener, stdout error handler
  • src/handlers.tsmatchesPlatform helper, applyFilters shared filter logic (platform, installed, favorite, status), createHandlers(state, reload) factory returning Record<ToolName, ToolHandler>; all 9 tool handler functions (sync except handleReloadLibrary)
  • src/utils.ts — Pure helpers: result constructors (ok, fail), argument validation (parseLimit, asString, requireString), search helpers (fuseConfidence(score: number), normaliseTitle, compactResult, sortedPlatformCounts), response formatting (formatPlayTime, emptyToNull)
  • src/tools.ts — Tool schema definitions with MCP annotations (as const satisfies MCPToolDefinition[]); derives ToolName union type for type-safe handler map; buildToolDefinitions(statusValues) returns dynamic tool schemas with status values injected into list_games description
  • src/loader.ts — XML parsing with htmlEntities, game extraction, string interning (loadGames); AdditionalApplication parsing for game versions/storefronts (extractVersion); Fuse.js index building (full + per-platform + title-only variants), gamesByTitle (lowercase) and gamesByNormalisedTitle maps for fast-path lookups, normalisingGetFn custom Fuse getter for punctuation-normalised matching, precomputed platformCounts and duplicateGroups (buildLibrary); exports FUSE_OPTIONS and FUSE_TITLE_ONLY_OPTIONS
  • src/types.ts — All type definitions: Game, GameVersion, RequestId, ToolResult, ToolHandler, MCPToolAnnotations, MCP interfaces

Read the full file on GitHub · 104 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. 2d ago First seen · 104 lines · 2,356 tokens per session scan A 1b5164446333

Subscribe to this mod's changes

mcp-launchbox CLAUDE.md is an instructions file published in the GitHub repository danjam/mcp-launchbox (3 stars, last pushed 2mo ago), licensed MIT. It adds 2,356 tokens to every session, about $0.0118 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.

Related

Other instructions, from other repositories

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens