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 skills add phara23/alpha-mcp --skill alpha-arcade-mcpgit clone --depth 1 https://github.com/phara23/alpha-mcpWrote 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/skills/phara23/alpha-mcp/alpha-arcade-mcp)<a href="https://agentmods.dev/skills/phara23/alpha-mcp/alpha-arcade-mcp"><img src="https://agentmods.dev/badge/skills/phara23/alpha-mcp/alpha-arcade-mcp/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/skills/phara23/alpha-mcp/alpha-arcade-mcp"><img src="https://agentmods.dev/badge/skills/phara23/alpha-mcp/alpha-arcade-mcp.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 | $0.00071 | $0.02295 |
| Opus 5.5 | $0.00028 | $0.00918 |
| Sonnet 5.5 | $0.00014 | $0.00459 |
| Haiku 4.5 | $0.00007 | $0.00230 |
Grade A, and why
alpha-arcade-mcp 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 2mo 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alpha Arcade — Prediction Markets on Algorand
Interact with Alpha Arcade prediction markets via the Alpha Arcade MCP server (16 tools across read-only, trading, and streaming categories).
Key Characteristics
- On-chain prediction markets — all orders and settlements happen on Algorand
- Binary and multi-choice markets — bet on YES/NO outcomes or choose from multiple options
- USDC-denominated — all collateral and payouts in USDC (ASA 31566704)
- Microunit inputs — all prices and quantities in tool inputs use microunits (1,000,000 = $1.00 or 1 share)
- Formatted outputs — read tools return human-readable strings or API snapshot JSON depending on the tool
Setup
The Alpha Arcade MCP server requires environment variables:
| Variable | Required | Description |
|---|---|---|
ALPHA_MNEMONIC |
For trading | Algorand wallet mnemonic (25 words) |
ALPHA_API_KEY |
For reward markets and full API orderbooks | Alpha Arcade API key |
ALPHA_ALGOD_SERVER |
No | Algod endpoint (default: mainnet Algonode) |
ALPHA_INDEXER_SERVER |
No | Indexer endpoint (default: mainnet Algonode) |
ALPHA_MATCHER_APP_ID |
No | Matcher app ID (default: 3078581851) |
ALPHA_USDC_ASSET_ID |
No | USDC ASA ID (default: 31566704) |
ALPHA_API_BASE_URL |
No | API base URL (default: https://platform.alphaarcade.com/api) |
Read-only tools (browsing markets, orderbooks, positions) work without ALPHA_MNEMONIC. Trading tools require it.
Units
All prices and quantities in tool inputs use microunits: 1,000,000 = $1.00 or 1 share.
| Human value | Microunit value |
|---|---|
| $0.50 | 500,000 |
| $0.05 slippage | 50,000 |
| 1 share | 1,000,000 |
| 30 shares | 30,000,000 |
Tool outputs from read tools (get_orderbook, get_full_orderbook, get_open_orders, get_positions) return either pre-formatted summaries or raw JSON snapshots. Write tools accept raw microunit integers.
Market Data Model
Binary markets
A standard yes/no market has a single marketAppId, yesAssetId, and noAssetId. Use marketAppId for all trading calls.
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.
- 2mo ago First seen · 176 lines · 71 tokens per session scan A 30ab24ddc402
alpha-arcade-mcp is a skill published in the GitHub repository phara23/alpha-mcp (10 stars, last pushed 3mo ago), licensed MIT. It adds 71 tokens to every session and 2,295 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.
alpha-arcade-mcp compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| alpha-arcade-mcpphara23/alpha-mcp | Skill | 10 | 3mo ago | MIT | A | 71 | Claude Code, Codex |
| agentic-streetLeoYeAI/openclaw-master-skills | Skill | 2.2k | 6d ago | MIT | A | 91 | Claude Code, Codex |
| token-pickaeonfun/aeon | Skill | 788 | yesterday | MIT | A | 25 | Claude Code, Codex |
| bridgealsk1992/CloddsBot | Skill | 3.1k | 1mo ago | MIT | A | 13 | Claude Code, Codex |
| hyperliquidalsk1992/CloddsBot | Skill | 3.1k | 1mo ago | MIT | A | 19 | Claude Code, Codex |
| marginfialsk1992/CloddsBot | Skill | 3.1k | 1mo ago | MIT | A | 11 | Claude Code, Codex |
| airdrop-hunting-guidenirholas/three.ws | Skill | 269 | yesterday | Apache-2.0 | A | 54 | Claude Code, Codex |