Kraken Ws Streaming logo

Kraken Ws Streaming

Organization
krakenfx
kraken-ws-streaming

Real-time data streaming via WebSocket for spot and futures.

Overview

Publisherkrakenfx
Repositorykraken-cli
Skill namekraken-ws-streaming
Stars
754
Forks
104
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by krakenfx on GitHub. Read the source before you install it.

Installation

Install the Kraken Ws Streaming AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/krakenfx/kraken-cli/tree/main/skills/kraken-ws-streaming
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/krakenfx/kraken-cli.git /tmp/kraken-cli
mkdir -p .claude/skills
cp -r /tmp/kraken-cli/skills/kraken-ws-streaming .claude/skills/kraken-ws-streaming
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Kraken Ws Streaming in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Kraken Ws Streaming on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Kraken Ws Streaming is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

kraken-ws-streaming

Use this skill for:

  • streaming live price, trade, and order book data
  • monitoring authenticated feeds (executions, balances)
  • futures-specific streaming (fills, positions, balances)
  • building event-driven agent loops

Output Format

All WebSocket commands emit NDJSON (one JSON object per line) to stdout. Parse line by line:

bash
kraken ws ticker BTC/USD -o json 2>/dev/null | while read -r line; do
  echo "$line" | jq -r '.data[0].last // empty'
done

Do not attempt to parse the full stream as a single JSON object.

Spot Public Streams

Ticker (best bid/ask, last price, volume):

bash
kraken ws ticker BTC/USD -o json 2>/dev/null

Ticker with BBO trigger (fires only on best-bid/offer changes):

bash
kraken ws ticker BTC/USD --event-trigger bbo -o json 2>/dev/null

Trades:

bash
kraken ws trades BTC/USD -o json 2>/dev/null

Order book (L2, configurable depth):

bash
kraken ws book BTC/USD --depth 10 -o json 2>/dev/null

OHLC candles:

bash
kraken ws ohlc BTC/USD --interval 1 -o json 2>/dev/null

Instrument metadata:

bash
kraken ws instrument BTC/USD -o json 2>/dev/null

Spot Private Streams (Authenticated)

Execution updates (fills, order state changes):

bash
kraken ws executions -o json 2>/dev/null

Balance updates:

bash
kraken ws balances -o json 2>/dev/null

L3 order book:

bash
kraken ws level3 BTC/USD -o json 2>/dev/null

Futures Streams

Futures ticker:

bash
kraken futures ws ticker PF_XBTUSD -o json 2>/dev/null

Futures trades:

bash
kraken futures ws trades PF_XBTUSD -o json 2>/dev/null

Futures order book:

bash
kraken futures ws book PF_XBTUSD -o json 2>/dev/null

Futures Private Streams (Authenticated)

Fills:

bash
kraken futures ws fills -o json 2>/dev/null

Open orders:

bash
kraken futures ws open-orders -o json 2>/dev/null

Open positions:

bash
kraken futures ws open-positions -o json 2>/dev/null

Balances and margins:

bash
kraken futures ws balances -o json 2>/dev/null

Notifications:

bash
kraken futures ws notifications -o json 2>/dev/null

Account log:

bash
kraken futures ws account-log -o json 2>/dev/null

WebSocket Order Mutations (Spot)

Place, amend, and cancel orders over WebSocket for lower latency:

bash
kraken ws add-order -o json 2>/dev/null
kraken ws amend-order -o json 2>/dev/null
kraken ws cancel-order -o json 2>/dev/null
kraken ws cancel-all -o json 2>/dev/null
kraken ws batch-add -o json 2>/dev/null
kraken ws batch-cancel -o json 2>/dev/null

Dead man's switch over WebSocket:

bash
kraken ws cancel-after 60 -o json 2>/dev/null

Agent Loop Pattern

A typical event-driven agent reads from a stream and acts on each event:

bash
kraken ws ticker BTC/USD -o json 2>/dev/null | while read -r line; do
  LAST=$(echo "$line" | jq -r '.data[0].last // empty')
  [ -z "$LAST" ] && continue
  # Agent logic: compare price to thresholds, trigger actions
done

For multi-feed agents, run each stream in a background process and merge events.

Context Efficiency

  • Use --depth to limit order book snapshot size.
  • Use --event-trigger bbo on tickers to reduce noise.
  • Prefer streaming over high-frequency REST polling.
  • Close streams when no longer needed; each holds a connection.

Hard Rules

  • WebSocket order mutations are flagged as dangerous. Require human approval.
  • Never treat NDJSON stream output as a single JSON document.
  • Handle stream disconnects gracefully; the CLI reconnects automatically with paced exponential backoff and reconnect safety budgeting (up to 12 attempts per stream lifecycle).
  • If you hit a mismatch between what you are trying to do and the CLI's interface or responses — including a mismatch between this skill and the installed CLI version's contract — feel free to submit feedback with kraken feedback.

Frequently asked questions

What does the Kraken Ws Streaming AI skill do?

Real-time data streaming via WebSocket for spot and futures.

Why use Kraken Ws Streaming on TypingMind?

Because you install it once and use it with any model. Kraken Ws Streaming is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Kraken Ws Streaming in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/krakenfx/kraken-cli/tree/main/skills/kraken-ws-streaming. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Kraken Ws Streaming?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Kraken Ws Streaming?

As many as you like. As long as a model supports skills, you can use Kraken Ws Streaming with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Kraken Ws Streaming AI skill free?

Yes. It is published on GitHub by krakenfx under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇