Agent skill

Kraken Autonomy Levels

by krakenfx in krakenfx/kraken-cli

Progress from manual trading to full agent autonomy with controlled risk at each level.

MITAuto-check passedBusiness, Finance & HR

Install Kraken Autonomy Levels

skills CLI
$ npx skills add krakenfx/kraken-cli --skill kraken-autonomy-levels -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install krakenfx/kraken-cli kraken-autonomy-levels --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/krakenfx/kraken-cli.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/kraken-autonomy-levels .claude/skills/kraken-autonomy-levels && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
kraken-autonomy-levels
GitHub stars
751
Token cost
~1.3k tokens
SKILL.md length
587 words
Files
1
Skills in repo
59
Repo updated
First seen
Licence
MIT

At a glance

Progress from manual trading to full agent autonomy with controlled risk at each level.

  • Works in 5 steps: Restricted API key. Never use a key with… → Dead man's switch. Start every session… → Position limits in agent code. The CLI… → …
  • Tasks that involve Trading and backtesting
  • SKILL.md covers Level 1: Read-Only Agent, Level 2: Paper Trading Agent, Level 3: Supervised Trading… and Level 4: Autonomous Trading…, plus 3 more sections
  • Needs KRAKEN_API_KEY and KRAKEN_API_SECRET

What it does

Kraken Autonomy Levels is an agent skill from krakenfx/kraken-cli. Progress from manual trading to full agent autonomy with controlled risk at each level.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Business, Finance & HR, covering Trading and backtesting. The repository describes itself as: The first AI-native CLI for trading crypto, stocks, forex, and derivatives. The licence is MIT.

When your agent uses it

  • Tasks that involve Trading and backtesting

Example prompts

  • “/kraken-autonomy-levels”

Requirements

  • A credential in KRAKEN_API_KEY
  • A credential in KRAKEN_API_SECRET

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Restricted API key. Never use a key with withdrawal permissions for an autonomous agent. Create a key that can trade but cannot withdraw…
  2. Dead man's switch. Start every session with cancel-after so all orders auto-cancel if the agent crashes or disconnects
  3. Position limits in agent code. The CLI does not enforce position size or frequency limits. Build these in your agent logic
  4. Error handling. Autonomous agents must handle every error category
  5. Monitoring. Run a separate read-only agent (Level 1) that monitors positions and alerts the trader if thresholds are breached.

What it can do on your machine

Read from SKILL.md and the folder at commit aa56e59. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • KRAKEN_API_KEY
    • KRAKEN_API_SECRET

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Kraken Autonomy Levels loads about 1.3k tokens when it runs. Until then it costs about 28 tokens; SKILL.md has 587 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~28
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from krakenfx/kraken-cli at commit aa56e59, republished under its MIT licence (© krakenfx). 587 words, ~1,345 tokens.

Download SKILL.mdSave it as .claude/skills/kraken-autonomy-levels/SKILL.md (or your agent's skills folder).
name
kraken-autonomy-levels
description
Progress from manual trading to full agent autonomy with controlled risk at each level.
version
1.0.0

kraken-autonomy-levels

Use this skill to help a trader move from hands-on CLI usage to fully autonomous agent trading in safe, incremental steps.

Level 1: Read-Only Agent

The agent reads market data and account state. No API key needed for public data; a query-only key for account data.

Kraken API key permissions: Query Funds, Query Open Orders & Trades

bash
export KRAKEN_API_KEY="query-only-key"
export KRAKEN_API_SECRET="query-only-secret"

kraken ticker BTCUSD -o json 2>/dev/null
kraken balance -o json 2>/dev/null
kraken open-orders -o json 2>/dev/null

The agent can inform, alert, and recommend. It cannot place orders, cancel orders, or move funds.

Level 2: Paper Trading Agent

The agent tests strategies against live prices with zero risk. No API key needed.

bash
kraken workspace create sandbox --capital 10000 --mode paper -o json 2>/dev/null
export KRAKEN_WORKSPACE=sandbox
kraken paper buy BTCUSD 0.01 -o json 2>/dev/null
kraken workspace status -o json 2>/dev/null
kraken workspace reset -o json --yes 2>/dev/null

Run paper strategies repeatedly. Compare results across parameter changes. Only move to Level 3 after consistent paper performance.

Level 3: Supervised Trading Agent

The agent places real orders, but a human confirms each one. The API key has trading permissions, but the agent validates before executing and waits for human approval.

Kraken API key permissions: Query Funds, Create & Modify Orders, Cancel/Close Orders

bash
export KRAKEN_API_KEY="trade-key"
export KRAKEN_API_SECRET="trade-secret"

# Step 1: Agent validates the order (no submission)
kraken order buy BTCUSD 0.001 --type limit --price 50000 --validate -o json 2>/dev/null

# Step 2: Agent presents the validated order to the human
# Step 3: Human approves or rejects

# Step 4: Agent executes only after approval
kraken order buy BTCUSD 0.001 --type limit --price 50000 -o json 2>/dev/null

Safety controls at this level:

  • Always --validate before executing
  • Always enable the dead man's switch for the session: kraken order cancel-after 300 -o json
  • Check open-orders after every trade to verify state

Level 4: Autonomous Trading Agent

The agent trades independently. No human in the loop. The trader trusts the agent and its strategy.

Kraken API key permissions: Create & Modify Orders, Cancel/Close Orders, Query Funds

bash
export KRAKEN_API_KEY="full-trade-key"
export KRAKEN_API_SECRET="full-trade-secret"

The agent passes --yes to skip confirmation prompts and operates on its own schedule.

Required safeguards at this level:

  1. Restricted API key. Never use a key with withdrawal permissions for an autonomous agent. Create a key that can trade but cannot withdraw funds.

  2. Dead man's switch. Start every session with cancel-after so all orders auto-cancel if the agent crashes or disconnects:

    bash
    kraken order cancel-after 600 -o json 2>/dev/null

    Refresh periodically. If the agent stops refreshing, all orders cancel.

  3. Position limits in agent code. The CLI does not enforce position size or frequency limits. Build these in your agent logic:

    • Maximum order size per trade
    • Maximum open positions
    • Maximum trades per hour
    • Pair allowlist (only trade specific pairs)
  4. Error handling. Autonomous agents must handle every error category:

    • rate_limit: back off, reduce frequency
    • network: retry with backoff, do not double-submit orders
    • auth: stop trading, alert the trader
    • validation: log and skip, do not retry unchanged
  5. Monitoring. Run a separate read-only agent (Level 1) that monitors positions and alerts the trader if thresholds are breached.

Show full SKILL.md (198 more words)Show less

Level 5: Autonomous Agent with Fund Management

The agent can also move funds (deposits, withdrawals, transfers between wallets). This is the highest trust level.

Kraken API key permissions: All permissions including Withdraw Funds

This level is rare and high-risk. Only appropriate when:

  • The agent manages a treasury or rebalances across exchanges
  • The withdrawal addresses are pre-approved and whitelisted in Kraken's account settings
  • Kraken's withdrawal address lock is enabled (prevents adding new addresses via API)

Choosing the Right Level

LevelAgent canHuman involvementRisk
1Read dataNoneZero
2Paper tradeNoneZero
3Trade with approvalConfirms every orderLow
4Trade autonomouslyMonitors, intervenes if neededMedium
5Trade and move fundsMonitorsHigh

Progression Rule

Move to the next level only after the agent demonstrates consistent behavior at the current level. Paper trading (Level 2) for at least a week before supervised trading (Level 3). Supervised trading for at least a week before autonomous (Level 4).

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.

© krakenfx, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/kraken-autonomy-levels of krakenfx/kraken-cli.

Open the folder on GitHubat commit aa56e59

Compare with similar skills

Kraken Autonomy Levels next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Kraken Autonomy Levels compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Kraken Autonomy Levels this skillkrakenfx/kraken-cli751—~1.3kAutomated safety check: PassMIT
Dr Manhattanguzus/dr-manhattan204—~2kAutomated safety check: PassApache-2.0
Polymarket Tennislivetennisapi/livetennisapi-mcp152—~3kAutomated safety check: PassMIT
Skill To Cardsundial-org/skills153—~1.5kAutomated safety check: PassNone
Alpaca Trading Paper Trading MCPalpacahq/alpaca-skills154—~11kAutomated safety check: PassApache-2.0
ClawlaunchLeoYeAI/openclaw-master-skills2.2k—~5.9kAutomated safety check: PassMIT

Similar skills

  • Dr Manhattan

    guzus/dr-manhattan

    Trade prediction markets (Polymarket, Kalshi, Opinion, Limitless, Predict.fun) using a unified CCXT-style API.

    204 GitHub stars~2k tokensUpdated 2 mo ago
    Business, Finance & HRAuto-check passed
  • Polymarket Tennis

    livetennisapi/livetennisapi-mcp

    Build observe-only Polymarket and Kalshi tennis market tooling on the polymarket-tennis Python package (MIT) plus the Live Tennis API free tier.

    152 GitHub stars~3k tokensUpdated 4 days ago
    Business, Finance & HRAuto-check passed
  • Skill To Card

    sundial-org/skills

    End-to-end workflow that creates a skill from a description and attached files, publishes it to Sundial as a private skill, generates a trading card (front + back with QR code), and sends it to a…

    153 GitHub stars~1.5k tokensUpdated 2 mo ago
    Business, Finance & HRAuto-check passed
  • Alpaca Trading Paper Trading MCP

    alpacahq/alpaca-skills

    Preview, submit, inspect, and manage Alpaca paper-trading orders using the Alpaca Trading API MCP Server.

    154 GitHub stars~11k tokensUpdated 1 mo ago
    Business, Finance & HRAuto-check passed
  • Clawlaunch

    LeoYeAI/openclaw-master-skills

    Launch and trade AI agent tokens on ClawLaunch bonding curve (Base).

    2.2k GitHub stars~5.9k tokensUpdated 2 mo ago
    Business, Finance & HRAuto-check passed
  • Tushare Data

    zillionare/zillionare

    面向中文自然语言的 Tushare 数据研究技能。用于把“看看这只股票最近怎么样”“帮我查财报趋势”“最近哪个板块最强”“北向资金在买什么”“给我导出一份行情数据”这类请求,转成可执行的数据获取、清洗、对比、筛选、导出与简要分析流程。适用于 A 股、指数、ETF/基金、财务、估值、资金流、公告新闻、板块概念与宏观数据等研究场景。

    322 GitHub starsUsed in 2 repos~2.3k tokens
    Business, Finance & HRAuto-check passed

More from krakenfx/kraken-cli

All 59 skills in this repo
  • Kraken Alert Patterns

    krakenfx/kraken-cli

    Price alerts, threshold monitoring, and notification triggers for agents.

    751 GitHub stars~1.1k tokensUpdated 2 mo ago
    Auto-check passed
  • Kraken Basis Trading

    krakenfx/kraken-cli

    Capture the spot-futures price spread with delta-neutral basis trades.

    751 GitHub stars~802 tokensUpdated 2 mo ago
    Auto-check passed
  • Kraken Dca Strategy

    krakenfx/kraken-cli

    Dollar cost averaging with scheduled buys and performance tracking.

    751 GitHub stars~1k tokensUpdated 2 mo ago
    Auto-check passed
  • Kraken Earn Staking

    krakenfx/kraken-cli

    Discover staking strategies, allocate funds, and track earn positions.

    751 GitHub stars~1k tokensUpdated 2 mo ago
    Auto-check passed
  • Kraken Error Recovery

    krakenfx/kraken-cli

    Handle order failures, network errors, and duplicate submissions safely.

    751 GitHub stars~1.1k tokensUpdated 2 mo ago
    Auto-check passed
  • Kraken Fee Optimization

    krakenfx/kraken-cli

    Minimize trading fees through maker orders, volume tiers, and fee-aware execution.

    751 GitHub stars~798 tokensUpdated 2 mo ago
    Auto-check passed

Questions about Kraken Autonomy Levels

What does Kraken Autonomy Levels do?

Progress from manual trading to full agent autonomy with controlled risk at each level. Kraken Autonomy Levels is an agent skill from krakenfx/kraken-cli. Progress from manual trading to full agent autonomy with controlled risk at each level.

When should I use Kraken Autonomy Levels?

Kraken Autonomy Levels fits situations like: tasks that involve Trading and backtesting.

How do I install Kraken Autonomy Levels in Claude Code?

Run `npx skills add krakenfx/kraken-cli --skill kraken-autonomy-levels -a claude-code`. Or copy the skill folder (skills/kraken-autonomy-levels in krakenfx/kraken-cli) into .claude/skills/kraken-autonomy-levels in your project. Claude Code loads it when a task matches its description.

How do I install Kraken Autonomy Levels in Codex?

Run `npx skills add krakenfx/kraken-cli --skill kraken-autonomy-levels -a codex`. Or copy the skill folder (skills/kraken-autonomy-levels in krakenfx/kraken-cli) into .agents/skills/kraken-autonomy-levels in your project. Codex loads it when a task matches its description.

Can I use Kraken Autonomy Levels in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add krakenfx/kraken-cli --skill kraken-autonomy-levels -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/kraken-autonomy-levels, .gemini/skills/kraken-autonomy-levels, .github/skills/kraken-autonomy-levels and .opencode/skills/kraken-autonomy-levels in your project.

What does Kraken Autonomy Levels need to run?

Going by SKILL.md and its folder, Kraken Autonomy Levels needs credentials named KRAKEN_API_KEY and KRAKEN_API_SECRET. Our summary lists: A credential in KRAKEN_API_KEY; A credential in KRAKEN_API_SECRET.

Does Kraken Autonomy Levels access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Kraken Autonomy Levels safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Kraken Autonomy Levels use?

Kraken Autonomy Levels is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Kraken Autonomy Levels use?

About 1.3k tokens (SKILL.md is roughly 5.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Kraken Autonomy Levels?

Skills that share tags, products or a category with Kraken Autonomy Levels: Dr Manhattan (guzus/dr-manhattan, 204 stars), Polymarket Tennis (livetennisapi/livetennisapi-mcp, 152 stars), Skill To Card (sundial-org/skills, 153 stars) and Alpaca Trading Paper Trading MCP (alpacahq/alpaca-skills, 154 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Kraken Autonomy Levels?

krakenfx (a GitHub organization) maintains it in krakenfx/kraken-cli, which has 751 GitHub stars. The repository holds 59 skills in this directory. The repository was last updated on August 7, 2026.

Source: krakenfx/kraken-cli on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.