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.
npx agentmods add instructions/themeparks/parksapi/claude-mdgit clone --depth 1 https://github.com/ThemeParks/parksapiWhat 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 | $0.02744 | $0.02744 |
| Opus 5 | $0.01372 | $0.01372 |
| Sonnet 5 | $0.00549 | $0.00549 |
| Haiku 4.5 | $0.00274 | $0.00274 |
Grade A, and why
parksapi 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.
How it starts
The opening of the file, as written. The whole thing — 228 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.
Project Overview
ParksAPI is a TypeScript library for fetching real-time theme park data (wait times, schedules, entities) from 75+ park implementations, serving ~118 destination entities worldwide. All park implementations live in src/parks/.
Key Requirement: Node 24+, npm 11+
Skills & Agents
Detailed implementation guides live in .claude/ — always check these before writing park code:
.claude/skills/implementing-parks.md— Complete guide for building new park destinations: scaffold, decorators, entity mapping, live data, schedules, validation workflow, tips & tricks, and 12 reference implementations.claude/agents/park-ts-migrator.md— Agent for migrating JS park implementations to TypeScript
Common Commands
npm run build # Compile TypeScript to dist/
npm run watch # Auto-recompile on changes
npm run dev # Test all parks via harness
npm run dev -- <id> # Test specific park (e.g. universalorlando)
npm run dev -- --list # List available park IDs
npm test # Run Vitest tests
npm run test:coverage # Coverage report
npm run health # Health check all endpoints
npm run har -- <file> # Analyse HAR capture
Architecture
Decorator-Based Design
@config (src/config.ts)
Automatic configuration loading. Priority: instance config > env vars > prefixed env vars > defaults.
Property decorator marks properties for config injection. @destinationController auto-applies the class-level @config — never add @config to a class that uses @destinationController.
@destinationController({category: 'MyCategory'})
export class MyPark extends Destination {
@config apiKey: string = ''; // Reads MYPARK_APIKEY env var
@config timeout: number = 5000; // Reads MYPARK_TIMEOUT, coerced to number
@config enabled: boolean = true; // Reads MYPARK_ENABLED, coerced to boolean
constructor(options?: DestinationConstructor) {
super(options);
this.addConfigPrefix('MYPARK'); // Also checks MYPARK_* env vars
}
}
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.
- 2d ago First seen · 228 lines · 2,744 tokens per session scan A ea1859f34c2f
parksapi CLAUDE.md is an instructions file published in the GitHub repository ThemeParks/parksapi (140 stars, last pushed 3d ago), licensed MIT. It adds 2,744 tokens to every session, about $0.0137 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 2026-08-30.
Other instructions, from other repositories
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).
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.
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).
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.
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.