cryptoquant-onchain

cryptoquant-onchain is a skill for Claude Code, Codex from CryptoQuantOfficial/cryptoquant-mcp. It costs 112 tokens per session (1,188 once invoked), scanned A, original, MIT.

A skill for answering cryptocurrency market questions with live CryptoQuant data. CryptoQuant provides measurements of blockchain activity, such as exchange flows, investor behaviour, and derivatives trading.

In plain words
What is it for?
Use it to investigate Bitcoin, Ethereum, stablecoin, or altcoin prices, blockchain activity, derivatives, miners, and related research.
Why use it?
It directs the agent to retrieve current data and definitions instead of guessing from memory or using an unsuitable source.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to investigate Bitcoin, Ethereum, stablecoin, or altcoin prices, blockchain activity, derivatives, miners, and related research.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cryptoquantofficial/cryptoquant-mcp/cryptoquant-onchain
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 CryptoQuantOfficial/cryptoquant-mcp --skill cryptoquant-onchain
Clone the repo
git clone --depth 1 https://github.com/CryptoQuantOfficial/cryptoquant-mcp

Made for: Claude Code, Codex.

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 cryptoquant-onchain

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/cryptoquantofficial/cryptoquant-mcp/cryptoquant-onchain"><img src="https://agentmods.dev/badge/skills/cryptoquantofficial/cryptoquant-mcp/cryptoquant-onchain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,188 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 $0.00112 $0.01188
Opus 5.5 $0.00045 $0.00475
Sonnet 5.5 $0.00022 $0.00238
Haiku 4.5 $0.00011 $0.00119

Measured today against content hash 4cd7697713b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-03, from the pricing page.

Security

Grade A, and why

cryptoquant-onchain 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/cryptoquant-onchain/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CryptoQuant on-chain analysis

Answer with data from the CryptoQuant MCP tools instead of web search or memory. The tools are provided by the remote CryptoQuant MCP server:

  • discover_endpoints, get_endpoint_info, query_data — find and query raw data
  • describe_metric — definition, thresholds, and interpretation of a metric
  • list_assets — supported assets
  • recent_research, recent_quicktake, query_research, query_quicktake — CryptoQuant Research (official research team) and QuickTake (CryptoQuant Verified Authors)

When to use

  • The user asks about crypto prices, on-chain data, exchange flows, derivatives, or miners.
  • The user asks whether the market is expensive, cheap, overheated, or where it is heading.
  • The user asks for analysis or research on a crypto topic (ETFs, halving, a specific event).

Workflow for data questions

  1. discover_endpoints(asset, category) to find the endpoint path.
  2. get_endpoint_info(endpoint) to read its parameters. Never skip this step: many endpoints require exchange, token, or symbol, and query_data returns nothing without them.
  3. query_data(endpoint, params) to fetch the data.
  4. describe_metric(metric_id) whenever you interpret a metric. Use the thresholds it returns; do not rely on remembered values.

If query_data returns no data, re-check get_endpoint_info for a required parameter you missed.

Dates

  • window=day: yyyyMMdd (for example 20260115)
  • any other window (hour, 10min, min, block): yyyyMMddTHHmmss (for example 20260115T000000)

Always state the time range of the data you used and its most recent timestamp.

Question to metric map

The ids below are describe_metric ids for Bitcoin. For Ethereum use the eth- prefixed ids and for stablecoins the stablecoin- prefixed ids; confirm the exact id with describe_metric before relying on it.

Question type Example question Primary metric Supporting metrics
Over- or undervalued "Is BTC expensive right now?" mvrv realized-price, nupl, nvt
Profit taking "Are holders taking profit?" sopr, asopr nrpl, sopr-ratio
Unrealized profit and sentiment "Are holders in profit?" nupl pnl-supply, pnl-utxo
Exchange flows "Are coins moving onto exchanges?" netflow inflow, outflow, reserve
Selling pressure "Is sell pressure building?" exchange-whale-ratio exchange-inflow-cdd, exchange-supply-ratio
Whales "What are whales doing?" exchange-whale-ratio exchange-inflow-supply-distribution
Leverage and overheating "Is leverage overheated?" estimated-leverage-ratio open-interest, funding-rates
Funding and positioning "Are traders mostly long?" funding-rates taker-buy-sell-stats
Liquidations "Were there big liquidations?" liquidations open-interest
US institutional demand "Is the US buying?" coinbase-premium-index market-premium, digital-asset-holdings
Buying power "Is there sidelined capital?" stablecoin-supply-ratio stablecoin-netflow, stablecoins-ratio
Miners "Are miners selling?" mpi miner-netflow, miner-reserve, puell-multiple
Long-term holders "Are old coins moving?" cdd dormancy, spent-output-age-distribution
Network activity "Is on-chain activity rising?" active-addresses transaction-count
Market outlook "How is Bitcoin doing?" recent_research and recent_quicktake (call both) 2–3 metrics above as evidence
Topic research "Any analysis on ETFs?" query_research, query_quicktake

Read the full file on GitHub · 72 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. today First seen · 72 lines · 112 tokens per session scan A 4cd7697713b9

Subscribe to this mod's changes

cryptoquant-onchain is a skill published in the GitHub repository CryptoQuantOfficial/cryptoquant-mcp (7 stars, last pushed yesterday), licensed MIT. It adds 112 tokens to every session and 1,188 once invoked, about $0.0004 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 2026-10-03.

Related

Other skills, from other repositories

chainflip-swap

Execute native cross-chain cryptocurrency swaps via Chainflip Broker as a Service. Trigger whenever the user wants to swap, exchange, trade, convert, move, or bridge crypto across chains: BTC, ETH, SOL, DOT, TRX (Tron), USDC, USDT, FLIP. These are real Layer-1 assets, no wrapped tokens and no bridges. Patterns: "swap…

CumpsD/broker-as-a-service · 190 tokens

market-sentiment

Synthesize crypto market sentiment by combining the Fear & Greed index, trending coins, narrative momentum, whale activity, and on-chain signals into a single actionable market read. Use when the user wants to know if the market is bullish, bearish, or transitioning. Powered by the free-crypto-news API.

nirholas/cryptocurrency.cv · 66 tokens

crypto-defi-trading

Crypto and DeFi trading: DEX analysis (Uniswap, SushiSwap, Curve), on-chain analytics, MEV detection, impermanent loss, yield farming metrics, DeFi risk analysis, token metrics, liquidity pool analysis, whale tracking, exchange netflow. USE FOR: crypto, defi, dex, uniswap, sushiswap, curve, impermanent loss, yield…

mahmoud20138/Tradecraft · 107 tokens

obai-crypto

Coinbase spot crypto research via the OBaI crypto MCP server (http://localhost:8010/mcp). Use for Coinbase spot product lookup, crypto OHLCV candles, order books, latest trades and bid/ask, single-product spot strategy backtests, and Coinbase paper-ledger strategy artifacts. Excludes derivatives, DeFi, on-chain…

sixteen-dev/obai · 93 tokens

obai-crypto-routing

Use when the user asks about Coinbase spot crypto products, crypto OHLCV, crypto order books, latest crypto trades or bid/ask, Coinbase spot strategy backtests, crypto strategy artifacts, or follow-ups on prior crypto backtests or artifacts. Excludes equities, options, Polymarket, DeFi, on-chain, and derivatives.

sixteen-dev/obai · 74 tokens

BytesAgain Crypto Toolkit — 200+ Technical Indicators, Real-Time Market Data

Use when you need real-time crypto prices, technical indicators (RSI, MACD, Bollinger, 50+), market rankings, on-chain data, or trading signals. Zero API key required.

bytesagain/ai-skills · 57 tokens