What is actually-prediction-markets?

A tool that looks up the current price of a prediction market for a specific future claim. A prediction market is a market where people trade contracts tied to possible outcomes, such as elections, sports results, or releases.

Use it when discussing the likelihood of a future event that people are betting on, such as a court decision, rate decision, election, sports result, or software release.

It replaces a vague statement about what may happen with a market-based probability, while showing exactly which question was matched.

actually-prediction-markets — Skill for Claude Code by Sofiia7

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 Sofiia7/actually --skill actually-prediction-markets

Clone the repo

git clone --depth 1 https://github.com/Sofiia7/actually

Made for: Claude Code.

Or install actually, the plugin that ships this one along with the rest of its 1 skill, 2 MCP servers.

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/sofiia7/actually/actually-prediction-markets/github.svg)](https://agentmods.dev/skills/sofiia7/actually/actually-prediction-markets)

Your own site

<a href="https://agentmods.dev/skills/sofiia7/actually/actually-prediction-markets"><img src="https://agentmods.dev/badge/skills/sofiia7/actually/actually-prediction-markets/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/sofiia7/actually/actually-prediction-markets"><img src="https://agentmods.dev/badge/skills/sofiia7/actually/actually-prediction-markets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,045 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	$0.00055	$0.01045
Opus 5	$0.00028	$0.00522
Sonnet 5	$0.00011	$0.00209
Haiku 4.5	$0.00006	$0.00104

Measured today against content hash 4a005b332c68, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

actually-prediction-markets 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 today.

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/actually-prediction-markets/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

What markets actually think

Someone says a thing is likely. You do not have to guess whether it is, and you do not have to argue about it either. If the claim is one people bet real money on, a market is already pricing it, and that price is a number you can quote.

This skill uses the actually-mcp-server MCP server to find that number.

When to reach for this

A claim about a future event shows up in a conversation, an article, or a headline, and the interesting question is "how likely is that, really".
You are about to write "experts expect" or "odds are rising" and would rather write a percentage.
Someone asks you to summarise news and the story hinges on an outcome that has not happened yet.

When not to

The claim is about the past, or about something nobody trades on. There is no market for "did the author mean this ironically".
The user wants your opinion. A market price is not an opinion, and swapping one for the other is a bad trade.
Precision matters more than availability. Matching is semantic, so a thin story can land on a related-but-different market. Always show the matched question, not just the number.

Setup

The server is on npm and needs no key, no wallet, and no account for the read-only tools:

{
  "mcpServers": {
    "actually": {
      "command": "npx",
      "args": ["actually-mcp-server"]
    }
  }
}

The first call takes about twenty seconds while the package downloads and a local embedding model warms up. Later calls are fast. If a probe times out at five seconds it will look like a broken install; it is not.

Using it

check_news(text) takes arbitrary text - a headline, a paragraph, a sentence someone said - and returns:

hasMarket - whether anything matched at all
market - the matched market, including its question and probabilityYes
confidence - how sure the match is
alternatives - the runners-up it considered

get_market(marketId) takes an id from that response and adds live price and an orderbook snapshot.

Read the full file on GitHub · 114 lines

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.

today Changed 4a005b332c68
9d ago First seen · 114 lines · 55 tokens per session scan A 8604c9f6b79c

Subscribe to this mod's changes

actually-prediction-markets is a skill published in the GitHub repository Sofiia7/actually (0 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 1,045 once invoked, about $0.0003 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 2026-08-31.

Finance and fintech

sector-rotation

An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.

HKUDS/Vibe-Trading · 39 tokens

strategy-pivot-designer

Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.

tradermonty/claude-trading-skills · 28 tokens

twitter-reader

Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…

himself65/finance-skills · 161 tokens

actually-prediction-markets