agentmods.dev

whale-flow

whale-flow is a skill for Claude Code from CoinLobster/agent-skills. It costs 102 tokens per session (1,554 once invoked), scanned A, original, MIT.

A guide to large executed cryptocurrency trades and the net buying or selling flow behind them, gathered from 15 exchanges and decentralized exchanges on Ethereum, Base and Arbitrum. In this context, whale means a very large trader or transaction.

In plain words
What is it for?
Use it to inspect recent whale trades, hourly buy-versus-sell flow, on-chain swaps, Hyperliquid fills and the positions of named Hyperliquid wallets.
Why use it?
It helps distinguish actual large trades from simple wallet transfers and shows whether large participants are buying or selling a named coin.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the coinlobster plugin — 6 skills, 1 MCP server shipped together

not rated 9repo 1mo ago A scan 102 tokens original MIT

Good fit Use it to inspect recent whale trades, hourly buy-versus-sell flow, on-chain swaps, Hyperliquid fills and the positions of named Hyperliquid wallets.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/coinlobster/agent-skills/whale-flow
View source ↗ CoinLobster/agent-skills coinlobster.com
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 CoinLobster/agent-skills --skill whale-flow
Clone the repo
git clone --depth 1 https://github.com/CoinLobster/agent-skills

Made for: Claude Code.

Or install coinlobster, the plugin that ships this one along with the rest of its 6 skills, 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 whale-flow

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/coinlobster/agent-skills/whale-flow"><img src="https://agentmods.dev/badge/skills/coinlobster/agent-skills/whale-flow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,554 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00102 $0.01554
Opus 5 $0.00051 $0.00777
Sonnet 5 $0.00020 $0.00311
Haiku 4.5 $0.00010 $0.00155

Measured 12d ago against content hash 31c50c1c81ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

whale-flow scanned grade A with 1 finding 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 12d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

3. **No MCP: curl the keyless API** (GET only, JSON):
skills/whale-flow/SKILL.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Whale Flow

Executed whale trades (not wallet transfers): side, size, price, venue, the moment they happen, merged across 15 centralized exchanges and on-chain DEX swaps on Ethereum, Base and Arbitrum.

Data sources (in order)

  1. CoinLobster MCP connected? Use its tools, fully qualified: coinlobster:whale_trades (recent trades; args: coin, source cex|dex|all, min_usd, limit) and coinlobster:whale_flow (hourly buy/sell USD buckets; args: coin, hours). whale_tape is a deprecated alias of whale_trades kept working for existing callers; prefer whale_trades, and fall back to whale_tape only if tools/list shows just that name.
  2. Named-wallet and DEX lanes (MCP). coinlobster:onchain_whales (args: chain, coin, min_usd, limit) returns executed DEX swaps on Ethereum, Base and Arbitrum, each carrying the wallet and the DEX. coinlobster:hl_whales (args: coin, limit) returns Hyperliquid whale fills WITH the wallet address, and coinlobster:hl_wallet (args: address) opens that account's live book (positions, leverage, net bias). Hyperliquid is the one venue whose public feed names the account on both sides of a fill, so an HL row is followable in a way a CEX row is not. Say which lane a number came from.
  3. No MCP: curl the keyless API (GET only, JSON): 
    curl -s "https://coinlobster.com/api/public/crypto-whales?coin=BTC&limit=50"
curl -s "https://coinlobster.com/api/public/onchain-whales?chain=ethereum&limit=50"
curl -s "https://coinlobster.com/api/public/hyperliquid/whales?coin=ETH&limit=50"
curl -s "https://coinlobster.com/api/public/whale-flow-history?coin=BTC&hours=168"
    Keyless, the measurement window on the three trade feeds is whatever the returned rows span; compute it from the min/max timestamps and state it. whale-flow-history is the REST twin of the whale_flow tool: hourly { t, buyUsd, sellUsd, netUsd, count, price } rows, flow on the same grid as the hourly close, 7 days keyless (maxFreeHours), 30 (proHours) on a coinlobster.com website subscription. An API key does not widen this REST route; on an agent surface the 30-day window is the whale_flow MCP tool on a developer plan. available: false means no recorded whale hours for that coin yet; coverage.hoursWithPrice says how much of the window actually has a price behind it.
  4. Quick read without parsing: fetch https://coinlobster.com/crypto-whales.md (markdown table of the latest trades).

Read the full file on GitHub · 47 lines

Files

What ships with it

1 file 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.

  1. 12d ago First seen · 47 lines · 102 tokens per session scan A 31c50c1c81ef

Subscribe to this mod's changes

whale-flow is a skill published in the GitHub repository CoinLobster/agent-skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 102 tokens to every session and 1,554 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Finance and fintechWeb3 and blockchainagent-skillsai-agentai-agentschatgpt-skillsclaude-skillscrypto
Related

Other skills, from other repositories

crypto-token-analysis

Deep-dive framework for analyzing crypto tokens — market data, liquidity health, tokenomics, unlock schedules, and risk assessment. Combines on-chain data, API queries, and multi-source validation to generate actionable investment verdicts.

kevinnft/ai-agent-skills · 49 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

freqtrade-bot

Freqtrade — open-source Python crypto trading bot. Backtesting, hyperopt (ML parameter optimization), FreqAI (self-training adaptive strategies), Telegram + WebUI control. Supports Binance, Kraken, Bybit, OKX, Gate.io (spot + futures). SQLite trade h.

mahmoud20138/Tradecraft · 61 tokens

trading-signals

Fetches live AI crypto trading signals with entry price, stop-loss, take-profit, leverage, confidence scores, and automated verification. Covers 50+ coins including BTC, ETH, SOL. Use when the user asks for crypto signals, trade ideas, market direction, portfolio analysis, or wants to build a trading bot.

roman-rr/trading-skills · 69 tokens

defi-yield

DeFi yield analysis and optimization — lending rates, LP yields, staking returns, yield farming strategies, risk-adjusted yield comparison, and protocol-level sustainability assessment.

HKUDS/Vibe-Trading · 37 tokens

crypto-derivatives

Crypto-derivatives strategies — perpetual funding-rate arbitrage, futures term-structure contango/backwardation trading, and option volatility-smile / Greeks analysis.

HKUDS/Vibe-Trading · 37 tokens