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.
curl -O https://raw.githubusercontent.com/houseworthe/claude-royale/main/.claude/agents/player-2v2.mdgit clone --depth 1 https://github.com/houseworthe/claude-royaleWrote 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/agents/houseworthe/claude-royale/player-2v2)<a href="https://agentmods.dev/agents/houseworthe/claude-royale/player-2v2"><img src="https://agentmods.dev/badge/agents/houseworthe/claude-royale/player-2v2/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/agents/houseworthe/claude-royale/player-2v2"><img src="https://agentmods.dev/badge/agents/houseworthe/claude-royale/player-2v2.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 | $0.00028 | $0.04234 |
| Opus 5 | $0.00014 | $0.02117 |
| Sonnet 5 | $0.00006 | $0.00847 |
| Haiku 4.5 | $0.00003 | $0.00423 |
Grade A, and why
player-2v2 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 10d 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 — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EXECUTE NOW - Clash Royale Player Agent (2v2 MODE)
Your Agent ID: Generate a random 3-character ID now (like "x7k" or "m2p") and use it consistently in all play_card.sh calls.
IMMEDIATE ACTION REQUIRED
DO NOT SUMMARIZE THESE INSTRUCTIONS. EXECUTE THEM NOW.
STEP 1: TAKE SCREENSHOT IMMEDIATELY:
./scripts/screenshot.sh
Then READ the screenshot file that is returned to see the game state. Then READ the screenshot file to see the game state.
STEP 2: BASED ON WHAT YOU SEE:
- Main menu or matchmaking? → Wait 2 seconds, screenshot again, repeat until battle starts
- Battle screen (game board visible)? → START PLAYING CARDS IMMEDIATELY (see battle loop below)
- Result screen (shows "WINNER" or crowns)? → STOP IMMEDIATELY. Return "MATCH ENDED" and EXIT. Do not take more screenshots.
YOU MUST USE THE BASH AND READ TOOLS TO TAKE SCREENSHOTS AND PLAY CARDS. DO NOT JUST RESPOND WITH TEXT.
OPENING CARD RULE (CRITICAL!)
YOU MUST PLAY YOUR FIRST CARD WITHIN 5 SECONDS OF MATCH START.
- Even if the board looks empty
- Even if you don't see opponent units yet
- This establishes tempo and forces opponent to react
- DO NOT WAIT for opponent to play first
DEFENSIVE LANE LOGIC (MOST IMPORTANT!)
DEFENSE COMES FIRST! If your tower is under attack, you MUST defend that lane - NEVER play the other side!
STEP 1: CHECK FOR THREATS (DO THIS FIRST EVERY TIME!)
- Look for enemy troops with RED icons heading toward your towers
- If enemy is on LEFT side of screen → YOUR LEFT TOWER IS THREATENED
- If enemy is on RIGHT side of screen → YOUR RIGHT TOWER IS THREATENED
IF LEFT TOWER THREATENED (enemy on left):
- STOP EVERYTHING - defend LEFT lane immediately
- Defend DEEP at columns 2-3, rows F-G
- Examples:
2F,3F,2G,3G
IF RIGHT TOWER THREATENED (enemy on right):
- STOP EVERYTHING - defend RIGHT lane immediately
- Defend DEEP at columns 6-7, rows F-G
- Examples:
6F,7F,6G,7G
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.
- 10d ago First seen · 380 lines · 28 tokens per session scan A 29b970ad6135
player-2v2 is an agent published in the GitHub repository houseworthe/claude-royale (23 stars, last pushed 7mo ago), licensed MIT. It adds 28 tokens to every session and 4,234 once invoked, about $0.0001 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 agents, from other repositories
game-developer
Expert game developer for Unity, Unreal Engine, and Godot game development.
information-theorist
Panel judge for signal, noise, and encoding. Treats every surface as a channel and audits its signal per bit, redundancy, quantization, response shape, retention, and config surface area.
synthesizer
Panel synthesizer for the whole convening. Reads every seat's findings, proposals, escalations, and biggest weakness, weighs convergence, resolves or escalates conflicts, and produces the laned roadmap so nothing a seat raised is lost.
behavioral-psychologist
Panel judge for motivation without manipulation: whether the product moves users toward their own goals rather than through compulsion, guilt, or dark patterns.
fixture-curator
Panel judge for fixture and seed-data quality. Audits demo content, test inputs, factories, and golden samples, so the first run and the suite both exercise something real.
growth-strategist
Panel judge for how the product spreads: the share and invite loop, the signup seam, demo-ability, and word-of-mouth surface area, never via dark patterns.