rekko

rekko is a skill for Claude Code from Rekko-AI/rekko-mcp. It costs 58 tokens per session (3,070 once invoked), scanned A, original, MIT.

A research skill for prediction markets, which are markets where prices represent estimates about future events.

In plain words
What is it for?
Researching markets on Kalshi, Polymarket, and Robinhood, including market details, price history, resolutions, and possible arbitrage or trading signals.
Why use it?
It provides context for market movements and probability estimates before you decide whether or how to trade.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

Part of the rekko plugin — 1 skill, 1 MCP server shipped together

Good fit Researching markets on Kalshi, Polymarket, and Robinhood, including market details, price history, resolutions, and possible arbitrage or trading signals.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rekko-ai/rekko-mcp/rekko
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 Rekko-AI/rekko-mcp --skill rekko
Clone the repo
git clone --depth 1 https://github.com/Rekko-AI/rekko-mcp

Made for: Claude Code.

Or install rekko, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

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.

agentmods badge for rekko

README.md
[![agentmods](https://agentmods.dev/badge/skills/rekko-ai/rekko-mcp/rekko/github.svg)](https://agentmods.dev/skills/rekko-ai/rekko-mcp/rekko)
Your own site
<a href="https://agentmods.dev/skills/rekko-ai/rekko-mcp/rekko"><img src="https://agentmods.dev/badge/skills/rekko-ai/rekko-mcp/rekko/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.

agentmods 80×15 button for rekko

Your own site · 80×15
<a href="https://agentmods.dev/skills/rekko-ai/rekko-mcp/rekko"><img src="https://agentmods.dev/badge/skills/rekko-ai/rekko-mcp/rekko.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,070 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00058 $0.03070
Opus 5 $0.00029 $0.01535
Sonnet 5 $0.00012 $0.00614
Haiku 4.5 $0.00006 $0.00307

Measured 10d ago against content hash 308b1c1c8146, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

rekko 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.

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/rekko/SKILL.md · 292 lines

How it starts

The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rekko — Prediction Market Intelligence

Rekko AI provides deep causal research for prediction markets on Kalshi, Polymarket, and Robinhood. It is the intelligence layer ("the brain") that sits alongside execution skills:

  • PolyClaw — executes trades on Polymarket
  • Kalshi Trader — executes trades on Kalshi
  • Rekko (this skill) — provides the WHY behind market movements

You consume finished insights; Rekko handles all research internally.

Getting Started

Tools appear as mcp__rekko__* when the plugin is installed. Requires REKKO_API_KEY — get one at rekko.ai or RapidAPI.

Tools

Market Intelligence

Tool Description Key Parameters
list_markets Browse current prediction markets source ("kalshi", "polymarket", "robinhood", ""), limit (1-100)
get_market Get details for a single market market_id, source (platform hint)
search_markets Search markets by keyword query, limit
get_market_history Price history with configurable period platform, market_id, period ("48h", "7d", "30d"), max_points
get_resolution Resolution intelligence for a market platform, market_id — returns time urgency, mechanism, theta estimate
get_execution_guidance Execution guidance (spread, slippage, timing) platform, market_id — returns order recommendation

Screening & Discovery

Tool Description Key Parameters
screen_markets Batch screen markets by score, volume, or IDs market_ids[], platform, min_volume_24h, min_score, limit
get_calibration Signal accuracy and calibration metrics category, period ("7d", "30d", "all"), mode ("shadow", "live")

Deep Research (async pattern)

Analysis takes 30-90 seconds. Use the three-step async pattern:

  1. analyze_market — starts the pipeline, returns an analysis_id immediately
    • bet_text: describe the market question
    • platform: optional platform hint
  2. check_analysis_status — poll with the analysis_id every 5 seconds until status is "complete"
  3. get_analysis — retrieve the full structured result once complete

Read the full file on GitHub · 292 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.

  1. 10d ago First seen · 292 lines · 58 tokens per session scan A 308b1c1c8146

Subscribe to this mod's changes

rekko is a skill published in the GitHub repository Rekko-AI/rekko-mcp (1 stars, last pushed 5mo ago), licensed MIT. It adds 58 tokens to every session and 3,070 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.