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 agentmods add skills/chainstacklabs/polymarket-alpha-bot/alphapoly-experimentnpx skills add chainstacklabs/polymarket-alpha-bot --skill alphapoly-experimentgit clone --depth 1 https://github.com/chainstacklabs/polymarket-alpha-botWrote 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/chainstacklabs/polymarket-alpha-bot/alphapoly-experiment)<a href="https://agentmods.dev/skills/chainstacklabs/polymarket-alpha-bot/alphapoly-experiment"><img src="https://agentmods.dev/badge/skills/chainstacklabs/polymarket-alpha-bot/alphapoly-experiment.svg" alt="Measured on agentmods" 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 | $0.00077 | $0.00417 |
| Opus 5 | $0.00039 | $0.00209 |
| Sonnet 5 | $0.00015 | $0.00083 |
| Haiku 4.5 | $0.00008 | $0.00042 |
Grade A, and why
Creating Alphapoly Experiments 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 4d 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.
What it actually says
Creating Alphapoly Experiments
Scaffold a new standalone script in experiments/.
Rules
- Completely standalone — no shared modules; no imports from
backend/or otherexperiments/files - Sequential numbering — check existing files in
experiments/and use the next number - Dependencies from backend — experiments share
backend/pyproject.tomldeps (httpx, polars, etc.); no inline PEP 723 headers needed - Run with
uv run experiments/<script>.pyfrom the project root
Template
"""NN: What this experiment explores.
WHAT IT DOES
Brief description of what the script does.
WHY WE NEED THIS
What question or hypothesis this experiment addresses.
"""
import json
import logging
from pathlib import Path
import httpx
DATA_DIR = Path(__file__).parent.parent / "data"
log = logging.getLogger(__name__)
# ... experiment code
Scripts needing API keys should load .env with an explicit path:
from dotenv import load_dotenv
load_dotenv(Path(__file__).parent.parent / ".env")
Naming
experiments/NN_short_description.py — e.g. experiments/09_test_llm_model.py
Subdirectories (e.g. experiments/trading/) have their own numbering sequence.
Running
uv run experiments/NN_script.py
Run from the project root. Dependencies resolve from backend/pyproject.toml via uv.
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.
- 4d ago First seen · 56 lines · 77 tokens per session scan A f2f48dcbd6a9
Creating Alphapoly Experiments is a skill published in the GitHub repository chainstacklabs/polymarket-alpha-bot (174 stars, last pushed 29d ago), licensed Apache-2.0. It adds 77 tokens to every session and 417 once invoked, about $0.0004 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 skills, from other repositories
polymarket
Query Polymarket: markets, prices, orderbooks, history.
polymarket-profile
Polymarket address profiler — input any 0x address, get a complete trading profile with PnL, win rate, positions, category breakdown, and top trades. All data from public APIs, no local database needed.
polymarket-pnl
Precise PnL calculator for any Polymarket address — reconstructs profit/loss from Data API cashflow (BUY/SELL/REDEEM/MERGE/SPLIT/REBATE) plus unrealized position value. Matches official /profit within 0.2% MAPE on leaderboard validation. Bring-your-own Python (httpx).
polymarket-brier
Brier Score calculator for Polymarket addresses — measures prediction accuracy independent of PnL. Separates skilled predictors from market makers and arbitrageurs.
moonpay-scout
Prediction market arbitrage & alpha scout. Searches Polymarket and Kalshi for the same event, runs cross-platform arb math (including fees), and ranks opportunities by profitability. Use when asked to "find arb", "scout markets", "find edge", or scan a specific topic across prediction markets.
moonpay-prediction-market
Trade on prediction markets (Polymarket, Kalshi). Search markets, buy/sell positions, track PnL, and view trade history.