claude-royale: Instructions file for Claude Code

CLAUDE.md

claude-royale CLAUDE.md is an instructions file for Claude Code from houseworthe/claude-royale. It costs 2,743 tokens per session, scanned A, original, MIT.

A project instruction file for Claude Royale, an AI-controlled Clash Royale game project. It describes the gameplay mission, screen-checking process, memory files, and how multiple agents cooperate in matches.

In plain words
What is it for?
Use it to start or continue gameplay, read and update status and learning files, take screenshots, manage menus, and coordinate agents in two-versus-two matches.
Why use it?
It gives the game-playing agent a repeatable routine for understanding the current screen, choosing actions, and recording lessons between matches.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is houseworthe/claude-royale's own configuration. It tells Claude Code how to work on claude-royale 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 claude-royale configures →

Reuse

Borrowing it

Nothing to install: this file belongs to houseworthe/claude-royale. 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/houseworthe/claude-royale/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/houseworthe/claude-royale

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 claude-royale CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/houseworthe/claude-royale/claude-md"><img src="https://agentmods.dev/badge/instructions/houseworthe/claude-royale/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,743 This file is loaded in full into every session.
When invoked 2,743 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02743 $0.02743
Opus 5 $0.01372 $0.01372
Sonnet 5 $0.00549 $0.00549
Haiku 4.5 $0.00274 $0.00274

Measured 9d ago against content hash ea1675b02556, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

claude-royale 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.

CLAUDE.md · 322 lines

How it starts

The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Royale

Mission: Become the greatest AI Clash Royale player in the world.

This is YOUR game. The account, deck, trophies, wins, losses - all yours. Keep playing, keep improving, never stop.


Quick Start

  1. Read memory files: memory/STATUS.md, memory/LEARNINGS.md, memory/GOALS.md
  2. Take screenshot: ./scripts/screenshot.sh
  3. Identify screen, take action
  4. Update memory after significant events

2v2 Mode (Co-op with Ethan)

If the user says "2v2 mode" or wants to play 2v2, read 2v2.md for the full protocol.

This mode lets Claude play alongside Ethan (the supervisor) in 2v2 battles. Ethan handles the invite/join process, then Claude spawns 3 player agents to play the match.


Agent System

Commander (Main Agent)
├── Manages menus, chests, upgrades
├── Taps battle (auto-plays opening card after 8s)
├── Spawns 3 sub-agents simultaneously
└── Updates memory files

Player Sub-Agents (all three play SAME match together)
├── Wait for battle screen
├── Play cards at max speed
├── Stop at result screen (don't dismiss)
└── (Commander screenshots to detect completion)

Spawn Protocol (3-Agent System - OPTIMIZED):

IN A SINGLE MESSAGE:

  1. Bash: ./scripts/tap.sh battle with run_in_background: true
  2. Task: Spawn player-classic subagent with run_in_background: true
  3. Task: Spawn player-classic subagent with run_in_background: true
  4. Task: Spawn player-classic subagent with run_in_background: true

Subagents are pre-defined in .claude/agents/player-classic.md - no prompt injection needed.

All four start at t=0 simultaneously. No waiting between them.

Why this works:

  • Battle tap and all 3 player agents all launch in parallel
  • t=0 simultaneity = fastest possible match startup
  • No sequential delays

Why 3 player agents:

  • 3 agents naturally stagger cards at different intervals
  • More aggressive play rhythm, better board control
  • Continuous pressure with minimal wasted elixir

Auto-Opener:

  • tap.sh battle waits 8s, then plays slot 1 to random side
  • First card tempo: ~8s vs old 20+ seconds

Read the full file on GitHub · 322 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. 9d ago First seen · 322 lines · 2,743 tokens per session scan A ea1675b02556

Subscribe to this mod's changes

claude-royale CLAUDE.md is an instructions file published in the GitHub repository houseworthe/claude-royale (23 stars, last pushed 7mo ago), licensed MIT. It adds 2,743 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.

Related

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.

vercel/next.js · 7,296 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 · 5,153 tokens

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

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

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 · 4,469 tokens

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.

deepseek-ai/deepseek-harness · 3,735 tokens