A tool for examining and testing markets on Polymarket, a website where people trade contracts on future events. It evaluates trades using a fair-probability estimate that you provide.

Use it to scan active or liquid markets, find unusual pricing across related outcomes, evaluate a specific market, and run repeatable backtests on JSON data.

It separates your prediction about an event from the practical details of placing a trade, such as price, available orders, size, and slippage.

autopredict — Skill for Claude Code by ckorhonen

Install

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.

Any agent

npx skills add ckorhonen/claude-skills --skill autopredict

Clone the repo

git clone --depth 1 https://github.com/ckorhonen/claude-skills

Made for: Claude Code.

Or install claude-skills, the plugin that ships this one along with the rest of its 62 skills, 4 commands, 7 agents.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ckorhonen/claude-skills/autopredict/github.svg)](https://agentmods.dev/skills/ckorhonen/claude-skills/autopredict)

Your own site

<a href="https://agentmods.dev/skills/ckorhonen/claude-skills/autopredict"><img src="https://agentmods.dev/badge/skills/ckorhonen/claude-skills/autopredict/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ckorhonen/claude-skills/autopredict"><img src="https://agentmods.dev/badge/skills/ckorhonen/claude-skills/autopredict.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,799 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00075	$0.02799
Opus 5	$0.00037	$0.01399
Sonnet 5	$0.00015	$0.00560
Haiku 4.5	$0.00007	$0.00280

Measured 10d ago against content hash d64afa30551c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

autopredict 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.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/run_backtest.sh, scripts/scan_markets.sh, scripts/setup.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/autopredict/SKILL.md · 284 lines

How it starts

The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AutoPredict

Quick Start — Simple Examples

New to AutoPredict? Start here before reading the full docs.

1. Scan what's trending on Polymarket right now

python3 predict.py --top 10

Shows the 10 most active markets with spreads, depth, and overround signals.

2. Show me the 5 most liquid markets

python3 predict.py --top 5 --verbose

Lists markets sorted by liquidity with full execution details.

3. Browse multi-outcome events for structural mispricing

python3 predict.py --events --top 10

Checks whether event probabilities sum to more or less than 100%.

4. What does the order book look like for a specific market?

python3 predict.py --fair 0.55 <condition_id>

Replace <condition_id> with the Polymarket ID. Provide your own fair probability estimate and AutoPredict evaluates the trade.

Run python3 predict.py --help for all flags. No credentials required for live reads.

AutoPredict is an execution framework for prediction-market trading. It is not a forecasting model.

You provide fair_prob.
The repo evaluates execution quality: side, order type, size, spread, depth, slippage, and risk.
Live market reads require internet but no credentials.
Real trading is scaffolded, not production-ready.

This skill was audited against the upstream repository layout and command surface, not just the README.

What Is Real vs Scaffold

Reliable entry points

python3 predict.py scans live Polymarket markets.
python3 predict.py --events inspects multi-outcome event overround / underround.
python3 predict.py --fair 0.60 <condition_id> evaluates one market using your explicit probability.
python3 -m autopredict.cli backtest --dataset ... runs an offline backtest.
python3 -m autopredict.cli score-latest prints the most recent saved metrics JSON.

Partially implemented or scaffold-only

python3 -m autopredict.cli learn analyze only works if you already have JSONL trade logs. Plain CLI backtests do not create those logs.
python3 -m autopredict.cli learn tune and learn improve are placeholders that point to a nonexistent scripts/learn_and_improve.py.
python3 -m autopredict.cli trade-live is intentionally disabled by config.
scripts/run_paper.py and scripts/run_live.py are deployment scaffolds. run_live.py uses a MockVenueAdapter, so it is not a real exchange adapter.

Read the full file on GitHub · 284 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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 · 284 lines · 75 tokens per session scan A d64afa30551c

Subscribe to this mod's changes

autopredict is a skill published in the GitHub repository ckorhonen/claude-skills (14 stars, last pushed 2mo ago), licensed MIT. It adds 75 tokens to every session and 2,799 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.

Claude Code Finance and fintech agent-skills ai-agents claude-plugins codex llm-tools

cost

Deep cost exploration and transparency. Shows real token usage, session costs, campaign spend, burn rates, and model breakdown. Reads Claude Code's native session data for exact numbers. Complements /dashboard with focused cost views.

SethGammon/Citadel · 46 tokens

consult-startup

A step-by-step startup planning aid covering an idea, its market, business model, investor presentation, finances, and execution plan.

modu-ai/moai-cowork · 187 tokens

finance-investor-relations

An investor-relations tool for preparing pitch decks and three-year financial models for fundraising. An IR, or investor-relations, deck explains a company to potential investors, while the model covers sales, profit, cash flow, and valuation.

modu-ai/moai-cowork · 180 tokens

consult-gov-grant

A guide to Korean government and public-sector funding programmes for applicants such as founders, small businesses, companies, researchers, nonprofits, and individuals. It can help find suitable programmes and prepare application documents.

modu-ai/moai-cowork · 283 tokens

finance-financial-statements

A financial-reporting assistant for preparing statements under K-IFRS, the Korean version of international financial reporting standards. It covers the balance sheet, income statement, cash-flow statement, statement of changes in equity, notes, and financial-ratio analysis.

modu-ai/moai-cowork · 108 tokens

finance-tax-helper

A Korean tax guide for freelancers, employees, and businesses. It explains withholding tax, income tax, value-added tax, and filing steps through HomeTax, Korea’s online tax service.

modu-ai/moai-cowork · 95 tokens