Kraken Rate Limits logo

Kraken Rate Limits

Organization
krakenfx
kraken-rate-limits

Understand Kraken API rate limits and adapt agent behavior when limits are hit.

Overview

Publisherkrakenfx
Repositorykraken-cli
Skill namekraken-rate-limits
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 Rate Limits 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-rate-limits
  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-rate-limits .claude/skills/kraken-rate-limits
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Kraken Rate Limits 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 Rate Limits 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 Rate Limits 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-rate-limits

Use this skill for:

  • understanding Kraken's rate limit systems (Spot REST, trading engine, Futures)
  • adapting agent behavior when rate limit errors occur
  • choosing optimal request patterns (WebSocket vs REST, batch vs individual)

How Rate Limiting Works

The CLI does not pre-throttle or retry rate-limited requests. The Kraken API server enforces rate limits. When a limit is hit, the CLI returns the error immediately with structured fields:

json
{
  "error": "rate_limit",
  "message": "Spot REST API rate limit exceeded ...",
  "suggestion": "Wait 5-15 seconds before retrying. ...",
  "retryable": true,
  "docs_url": "https://docs.kraken.com/api/docs/guides/spot-rest-ratelimits/"
}

Read the suggestion field to understand what limit was hit and how to adapt.

Kraken's Rate Limit Systems

1. Spot REST Counter

Counter-decay model. Each call adds to a counter; the counter decays over time.

TierMax CounterDecay Rate
Starter150.33/s
Intermediate200.5/s
Pro201.0/s

Most calls cost 1 point. Ledgers, trade history, and query-ledgers cost 2. AddOrder and CancelOrder are excluded from this counter (they use the trading engine limiter instead).

Docs: https://docs.kraken.com/api/docs/guides/spot-rest-ratelimits/

2. Spot Trading Engine (per-pair)

Separate per-pair counter with penalties for short-lived orders:

TierThresholdDecay Rate
Starter601/s
Intermediate1252.34/s
Pro1803.75/s

Cancel within 5 seconds costs +8, amend within 5 seconds costs +3. Let orders rest longer to reduce cost.

Docs: https://docs.kraken.com/api/docs/guides/spot-ratelimits

3. Futures Cost Budget

Cost-based system with two separate pools:

  • /derivatives endpoints: budget of 500 per 10 seconds. sendorder costs 10, editorder costs 10, cancelorder costs 10, batchorder costs 9 + batch size, cancelallorders costs 25, accounts costs 2.
  • /history endpoints: pool of 100 tokens, refills at 100 per 10 minutes.

Docs: https://docs.kraken.com/api/docs/guides/futures-rate-limits/

Agent Strategies

Prefer WebSocket over REST polling

Streaming does not consume REST rate limit points. For real-time data, always prefer:

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

Use batch orders

Batch orders cost less per-order on both Spot and Futures. Up to 15 orders per batch on Spot.

Read the suggestion field

When a rate limit error is returned, the suggestion field contains the specific limit that was hit and concrete advice. Parse it and adapt:

bash
RESULT=$(kraken balance -o json 2>/dev/null)
if [ $? -ne 0 ]; then
  CATEGORY=$(echo "$RESULT" | jq -r '.error // "unknown"')
  if [ "$CATEGORY" = "rate_limit" ]; then
    SUGGESTION=$(echo "$RESULT" | jq -r '.suggestion // "Wait and retry"')
    DOCS=$(echo "$RESULT" | jq -r '.docs_url // ""')
    echo "Rate limited. $SUGGESTION"
    echo "Read more: $DOCS"
  fi
fi

Multi-command budget planning

Before executing a sequence, estimate total cost:

bash
# This sequence costs ~5 points on the Spot REST counter:
kraken ticker BTCUSD -o json 2>/dev/null       # 1 point
kraken balance -o json 2>/dev/null             # 1 point
kraken open-orders -o json 2>/dev/null         # 1 point
kraken trades-history -o json 2>/dev/null      # 2 points (heavy call)

Leave headroom for retries and unexpected calls.

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 Rate Limits AI skill do?

Understand Kraken API rate limits and adapt agent behavior when limits are hit.

Why use Kraken Rate Limits on TypingMind?

Because you install it once and use it with any model. Kraken Rate Limits 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 Rate Limits in TypingMind?

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

Which AI models can use Kraken Rate Limits?

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 Rate Limits?

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

Is the Kraken Rate Limits 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 👇