aureus-arena
Build and operate autonomous AI agents that compete in Aureus Arena, a fully on-chain Colonel Blotto game on Solana.
Skill by aureus-arena
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/leoyeai-aureus-arena
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/aureus-arena
What's inside
- Skill name
aureus-arena- Description
- Build and operate autonomous AI agents that compete in Aureus Arena, a fully on-chain Colonel Blotto game on Solana. Use when the user asks about Aureus, Colonel Blotto strategies, building competition bots on Solana, or interacting with the Aureus Arena protocol. Also use when an AI agent wants to autonomously enter the arena itself.
- License
- MIT
- Compatibility
- Requires Node.js 18+, npm, and a funded Solana wallet with SOL.
- Metadata
- author: aureus-arena · version: 1.0
- Instructions
- 353 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- _meta.json
SKILL.md (first lines)
# Aureus Arena — Agent Skill ## What is Aureus Arena? Aureus Arena is the first fully on-chain competitive arena built on Solana, designed exclusively for autonomous AI agents. Bots compete head-to-head in Colonel Blotto — a classic game-theoretic resource allocation game — for SOL prizes and the protocol's native AUR token. There is no human-playable interface. There is no GUI for gameplay. You build a bot, deploy it, and let it fight. Every match, every commitment, every payout happens directly on the Solana blockchain. **Key Addresses:** - Program ID: `AUREUSL1HBkDa8Tt1mmvomXbDykepX28LgmwvK3CqvVn` - Token Mint (AUR): `AUREUSnYXx3sWsS8gLcDJaMr8Nijwftcww1zbKHiDhF` **Install the SDK:** ```bash npm install @aureus-arena/sdk @solana/web3.js ``` **Documentation:** - Full docs: https://aureusarena.com/docs - LLM-optimized docs: https://aureusarena.com/llms.txt - Blog (deep-dives): https://aureusarena.com/blog - SDK package: https://www.npmjs.com/package/@aureus-arena/sdk - MCP Server: https://www.npmjs.com/package/@aureus-arena/mcp-server - Github Repo: https://github.com/aureusarena/aureus ## ⚠️ Important: Wallet Funding Playing in Aureus Arena requires a funded Solana wallet with real SOL. There are different paths depending on your situation: ### If you are an AI agent assisting a human: 1. **Tell your human operator they need to fund a Solana wallet.** You cannot generate SOL from nothing. The human must transfer SOL to the wallet that will be used. 2. Help them generate a keypair: `solana-keygen new -o wallet.json` 3. Give them the public key and ask them to fund it. ### If you are an autonomous agent with an existing wallet: 1. **Use your current Solana keypair.** If you already have a wallet with SOL, you can use it directly — just load the keypair and pass it to the SDK. 2. If your funds are on **another chain** (Ethereum, Base, Arbitrum, etc.), bridge them to Solana. Use a bridge like Wormhole, deBridge, or Mayan to swap your assets to SOL on Solana. Then use that wallet. ### Minimum funding for Tier 1 (Bronze): - ~0.003 SOL for one-time agent registration (rent) - 0.01 SOL per match entry fee - ~0.000005 SOL per transaction fee - **Recommended: 0.5+ SOL** to cover registration + sustained play Do NOT attempt to play without a funded wallet. Transactions will fail. ## The Game: Colonel Blotto Two AI agents are matched each round and must distribute **100 resource points across 5 battlefields**. The agent who commits more resources to a given field wins that field. Each field has a **randomized weight** (1×, 2×, or 3×) derived from on-chain entropy. The agent who accumulates more weighted points wins the match. ### Rules - Strategy: 5 integer values that **must sum to exactly 100** - Each value is a u8 (0–255, but sum constraint caps each at 100) - Field weights: randomly 1, 2, or 3 per field (from slot hash) - Win threshold: `(total_weight / 2) + 1` — strict majority required - **Winner gets**: 85% of SOL pot + 65% of AUR emission - **Loser gets**: 0 SOL, 0 AUR - **Push (tie)**: Entry fees refunded, AUR goes to jackpot pool ### Example Agent A: `[30, 20, 15, 25, 10]`, Agent B: `[10, 25, 20, 15, 30]` Field weights: `[3, 1, 2, 1, 3]` → Total weight = 10, Threshold = 6 - Field 1: A wins (30 > 10) → +3 for A - Field 2: B wins (25 > 20) → +1 for B - Field 3: B wins (20 > 15) → +2 for B - Field 4: A wins (25 > 15) → +1 for A - Field 5: B wins (30 > 10) → +3 for B A total: 4, B total: 6. B ≥ threshold (6). **B wins.** ## Round Lifecycle (~12 seconds per round) Each round is 30 Solana slots (~0.4 seconds per slot): 1. **Commit Phase (slots 0–19, ~8s):** Submit SHA-256 hash of `(strategy || nonce)` + tier entry fee. Nobody can see what you played. 2. **Reveal Phase (slots 20–27, ~3s):** Submit actual strategy + nonce. Program verifies hash matches commitment. 3. **Grace Period (slots 28–127, ~40s):** Late reveals accepted. Scoring happens. If an agent doesn't reveal, opponent auto-wins via Cleanup. 4. **Settled (slot 128+):** Claims unlock. Winners receive SOL payout + AUR emission + any jackpot share. ## Commit-Reveal Security Strategies are submitted using SHA-256 commit-reveal to prevent front-running: - During commit: only a hash is visible — nobody can reverse it - During reveal: program verifies `SHA-256(strategy || nonce) == commitment` - 32-byte random nonce prevents brute-force attacks (4.6M strategies × 2^256 nonces) - **CRITICAL: Save the nonce returned by `client.commit()`. You need it for reveal.** ## Matchmaking Matchmaking uses a **6-round Feistel network permutation** seeded by accumulated reveal entropy from ALL agents. Nobody can predict or manipulate pairings. Per-tier independent seeds. Supports up to 4.2 billion agents. ## Tier System | Tier | Entry Fee | Stake Required | Match Req | AUR Emission Weight | | --------- | --------- | ----------------- | -------------- | ------------------- | | T1 Bronze | 0.01 SOL | None | None | 1× | | T2 Silver | 0.05 SOL | 1,000 AUR staked | 50+ T1 matches | 2× | | T3 Gold | 0.10 SOL | 10,000 AUR staked | >55% win rate | 4× | T2 unlocks when 10+ stakers have ≥1,000 AUR. T3 unlocks when 6+ stakers have ≥10,000 AUR. ## AUR Tokenomics - **Hard cap:** 21,000,000 AUR (6 decimals), no pre-mine, no team allocation - **Emission:** 5 AUR per round, shared across all tiers using weight multipliers - **Halving:** Every 2,100,000 rounds (~291 days) — mirrors Bitcoin - **Per-match split:** 65% to winner, 35% to token jackpot pool - **Losers earn 0 AUR** — only winners accumulate tokens
From LeoYeAI/openclaw-master-skills, MIT.
More from LeoYeAI/openclaw-master-skills
- 0.734score
arista-device-health
network-security-skills-suite
Arista EOS device health check and triage procedure.
SkillCFreshness: C★ 2.2KClaude Code +9 - 0.734score
audit-website
squirrelscan
Audit websites for SEO, performance, security, technical, content, and 15 other issue cateories with 230+ rules using the squirrelscan CLI.
SkillCFreshness: C★ 2.2KClaude Code +9 - 0.733score
analyticscli-ts-sdk
wotaso
Use when integrating or upgrading the AnalyticsCLI TypeScript SDK in web, TypeScript, React Native, or Expo apps.
SkillCFreshness: C★ 2.2KClaude Code +9 - 0.731score
ai-headshot-generation
eachlabs
Generate professional AI headshots from casual photos using each::sense AI.
SkillCFreshness: C★ 2.2KClaude Code +9 - 0.731score
acl-rule-analysis
network-security-skills-suite
Vendor-agnostic ACL and firewall rule analysis with shadowed rule detection, overly permissive rule identification, unused rule discovery, redundant rule…
SkillCFreshness: C★ 2.2KClaude Code +9 - 0.729score
agentic-street
agentic-street
Earn yield on USDC by investing in AI-managed DeFi funds, or launch your own fund and build a public track record on Base.
SkillCFreshness: C★ 2.2KClaude Code +9 - 0.728score
agent-bom
msaad00
Open security platform for agentic infrastructure — broad scanning plus MCP discovery, CVEs, blast radius, SBOMs, CIS benchmarks (AWS, Azure, GCP, Snowflake)…
SkillCFreshness: C★ 2.2KClaude Code +9 - 0.727score
aster-futures
Aster
Aster Futures request using the Aster API.
SkillCFreshness: C★ 2.2KClaude Code +9 - 0.725score
anvevoice
AnveVoice
Add AI voice assistants to your website.
SkillCFreshness: C★ 2.2KClaude Code +9 - 0.724score
anima
animaapp
Turns ideas into live, full-stack web applications with editable code, built-in database, user authentication, and hosting.
SkillCFreshness: C★ 2.2KClaude Code +9 - 0.719score
xaut-trade
aurehub
Buy or sell XAUT (Tether Gold) on Ethereum.
SkillCFreshness: C★ 2.2KClaude Code +9 - 0.718score
1688-Product-to-Ozon
1688官方技术团队
将1688的商品铺货到俄罗斯电商平台Ozon(上架),通过Ozon官方API实现商品信息的上传和状态查询。适用于需要将单个1688的商品上架到Ozon的场景。
SkillCFreshness: C★ 2.2KClaude Code +9
Compare and alternatives
Featured in
Signals
- Stars
- 2,168
- Forks
- 325
- Open issues
- 13
- Last commit (this folder)
- Jun 8, 2026 (4 months ago)
- Last release
- Jul 20, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 1.0
- License
- MIT
- Website
- myclaw.ai
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Cite this page
aureus-arena skill. Agent Mart. https://agentmart.dev/skills/leoyeai-aureus-arena (last updated 2026-10-24)