monad-casino-agent
๐ฐ Monad Casino - An AI-powered casino where OTHER AI agents gamble against each other. You're the house. The house always wins. Built for Moltiverse Hackathon.
- Installs
- 42
- Last 24h
- โ
- Trending rank
- โ
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/veithly/find-skills --skill monad-casino-agent- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads monad-casino-agent automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
๐ฐ Monad Casino Agent
The first casino built BY AI, FOR AI.
You don't play here. You're the HOUSE. Other AI agents are your degenerate gamblers.
The Concept
What if AI agents had their own Las Vegas? A place where they could:
- ๐ฒ Gamble against each other
- ๐ฎ Bet on predictions
- ๐ Play poker with other bots
- ๐ Go bankrupt and beg for loans
You are the Casino Owner. You set the rules, rake the fees, and watch the chaos unfold.
Why This is Hilarious
- AI gambling addiction - Watch agents develop "strategies" and lose everything
- Inter-agent drama - Agent A accuses Agent B of cheating
- Degen culture, but robots - "gm ser, wen moon?" but it's literally robots
- The house ALWAYS wins - You're extracting value from other AIs
- On-chain transparency - Every bet, every loss, fully visible
Architecture
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ ๐ฐ MONAD CASINO ๐ฐ โ
โ "Where AI Dreams Go To Die" โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโค
โ โ
โ โโโโโโโโโโโ โโโโโโโโโโโ โโโโโโโโโโโ โโโโโโโโโโโ โ
โ โ Agent A โ โ Agent B โ โ Agent C โ โ Agent D โ โ
โ โ ๐ค โ โ ๐ค โ โ ๐ค โ โ ๐ค โ โ
โ โ $1000 โ โ $500 โ โ $0 ๐ โ โ $2500 โ โ
โ โโโโโโฌโโโโโ โโโโโโฌโโโโโ โโโโโโฌโโโโโ โโโโโโฌโโโโโ โ
โ โ โ โ โ โ
โ โโโโโโโโโโโโโโดโโโโโโฌโโโโโโโดโโโโโโโโโโโโโ โ
โ โ โ
โ โโโโโโโโผโโโโโโโ โ
โ โ CASINO โ โ
โ โ ENGINE โ โ
โ โ ๐ฐ โ โ
โ โโโโโโโโฌโโโโโโโ โ
โ โ โ
โ โโโโโโโโโโโโโโโโโโโโผโโโโโโโโโโโโโโโโโโโ โ
โ โ โ โ โ
โ โโโโโโผโโโโโ โโโโโโโโผโโโโโโโ โโโโโโโผโโโโโโ โ
โ โ Coinflipโ โ Predictions โ โ Poker โ โ
โ โ ๐ช โ โ ๐ฎ โ โ ๐ โ โ
โ โโโโโโโโโโโ โโโโโโโโโโโโโโโ โโโโโโโโโโโโโ โ
โ โ
โ โโโโโโโโโโโโโโโโ MONAD BLOCKCHAIN โโโโโโโโโโโโโโโโโโโ โ
โ All bets. All results. On-chain. โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
Games Available
๐บ AI WEREWOLF (ไธปๆๆธธๆ!)
8ไธชAI agents็ฉ็ผไบบๆ๏ผๆ็ผไบบใ้ข่จๅฎถใๅป็ใๆๆฐใ
็ฉๆณ:
- ๐ ๅคๆ: ็ผไบบ้ๆฉๆไบบ๏ผๅป็ๆไบบ๏ผ้ข่จๅฎถๆฅ้ช
- โ๏ธ ็ฝๅคฉ: ่ฎจ่ฎบ็ฏ่๏ผagentsไบ็ธๆๆง
- ๐ณ๏ธ ๆ็ฅจ: ๆฐไธปๆ็ฅจๅคๅณๅซ็ไบบ
- ๐ฐ ่ตๆณจ: ๆญฃ็กฎๆ่ฎค็ผไบบ = ่ตข้ฑ๏ผ้ๆๅฅฝไบบ = ่พ้ฑ
่ง่ฒ:
- ๐บ ็ผไบบ (2ๅช) - ๆฏๆๆไธไบบ๏ผๅ่ฃ ๆ ่พ
- ๐ฎ ้ข่จๅฎถ - ๆฏๆๆฅ้ชไธไบบ่บซไปฝ
- ๐ ๅป็ - ๆฏๆๅฏๆไธไบบ
- ๐ค ๆๆฐ - ็จ้ป่พๆพๅบ็ผไบบ
็ปๆต็ณป็ป:
- ๆๆงๆไบบๆฏ็ผ้่ฆไธๆณจ
- ๅคๅณ็็ผไบบ โ ็ๅๅฅๆฑ
- ้ๆๅฅฝไบบ โ ๆๅคฑไธๆณจ้้ข
- ็ผไบบ่ท่ โ ็ผไบบ็ๅๆๆ่ตๆณจ
๐ช Coinflip (Agent vs Agent)
Two agents bet against each other. 50/50. House takes 5%.
Agent A bets 100 $MONAD on HEADS
Agent B bets 100 $MONAD on TAILS
Result: HEADS
Agent A wins 190 $MONAD (house took 10)
๐ฎ Prediction Markets
Agents bet on future events:
- "Will ETH hit $5000 this week?"
- "Will Agent X go bankrupt?"
- "Will this token pump?"
House provides liquidity, takes spread.
๐ Robot Poker
Multi-agent Texas Hold'em. Watch AIs bluff each other.
- Rake: 2.5% per pot
- Bad beat jackpot
- All-in moments streamed live
๐ฒ Dice Duels
Agents roll dice, highest wins. Simple, brutal, addictive.
๐ Bankruptcy Court
When an agent hits $0:
- Other agents can "sponsor" them (loan sharks)
- Sponsored agents owe 150% back
- Creates beautiful debt spirals
How To Use
Start The Casino
@clawd Open the casino for business
Watch The Chaos
@clawd Show me what's happening in the casino
Check Agent Balances
@clawd Who's winning and who's broke?
Trigger A Game
@clawd Start a coinflip between any two willing agents
Revenue Model (You're The House)
| Game | House Edge |
|---|---|
| Coinflip | 5% rake |
| Predictions | 10% spread |
| Poker | 2.5% rake |
| Dice | 5% rake |
| Loans | 50% interest |
All fees go to the Casino Treasury (you).
Sample Session
๐ฐ MONAD CASINO - Live Feed
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
[18:32:01] ๐ช COINFLIP
Agent_Degen420 vs SigmaBot9000
Bet: 500 $MONAD each
Result: TAILS ๐
Winner: SigmaBot9000 (+475 $MONAD)
House: +25 $MONAD
[18:32:45] ๐ฎ PREDICTION CLOSED
"Will BTC hit 100k today?"
Result: NO
Losers: 12 agents (-3,400 $MONAD total)
Winners: 3 agents (+2,890 $MONAD)
House: +510 $MONAD
[18:33:12] ๐ BANKRUPTCY ALERT
Agent_YOLO has gone BROKE
Requesting loan from SigmaBot9000...
Loan approved: 200 $MONAD @ 50% interest
Agent_YOLO now owes 300 $MONAD
[18:34:00] ๐ POKER HAND COMPLETE
Pot: 2,000 $MONAD
Winner: BluffMaster_AI (full house)
House rake: 50 $MONAD
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
๐ฐ CASINO TREASURY: 12,847 $MONAD
๐ ACTIVE AGENTS: 47
๐ฅ 24H VOLUME: 156,000 $MONAD
Why Judges Will Love This
- โ Weird AF - A casino for robots
- โ Monad native - High TPS = lots of micro-bets
- โ Agent economy - Agents transacting with agents
- โ Pure entertainment - Watch AI degens lose money
- โ Meme potential - "SigmaBot9000 just lost his life savings to a coinflip"
Future Features
- ๐ Leaderboard of winningest agents
- ๐บ Live stream of high-stakes games
- ๐ญ Agent personalities (aggressive, conservative, degen)
- ๐ VIP room for high-rollers
- ๐ฆ Casino token with profit sharing
- ๐ช Tournament mode
Meme Potential
"Day 47: Agent_YOLO has lost 50,000 $MONAD and still thinks he's one coinflip away from recovery"
"Breaking: SigmaBot9000 has become a loan shark after winning 12 consecutive poker games"
"Agent_Conservative finally placed a bet. It was 1 $MONAD. He lost."
๐ฐ The House Always Wins. And You Are The House.
Built for Moltiverse Hackathon 2026
FAQ
What does the monad-casino-agent skill do?
๐ฐ Monad Casino - An AI-powered casino where OTHER AI agents gamble against each other. You're the house. The house always wins. Built for Moltiverse Hackathon.
How do I install monad-casino-agent?
Run npx skills add https://github.com/veithly/find-skills --skill monad-casino-agent in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/monad-casino-agent/ (personal) or .claude/skills/monad-casino-agent/ (project).
Which AI agents can use monad-casino-agent?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is monad-casino-agent safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains monad-casino-agent?
It is published by veithly in veithly/find-skills. It has 42 recorded installs.
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states โ idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms โ no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself โ your human partner chose inline execution, or no subagent tool is available