kraken-lab-experiment

kraken-lab-experiment is a skill for Claude Code from krakenfx/kraken-cli. It costs 61 tokens per session (2,731 once invoked), scanned A, original, MIT.

A process for testing a trading hypothesis in a recorded paper-trading workspace. It freezes the hypothesis and success rules, runs and scores the experiment, then produces a pass-or-fail verdict that can be resumed from files.

In plain words
What is it for?
Use it to register experiment criteria, run replayed paper trades, score sessions, resume unfinished work, and reproduce a verdict from saved files.
Why use it?
It prevents changing the goal after seeing results and preserves progress across restarts or lost sessions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: built for openclaw.

Part of the kraken-cli plugin — 59 skills, 1 MCP server shipped together

Good fit Use it to register experiment criteria, run replayed paper trades, score sessions, resume unfinished work, and reproduce a verdict from saved files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/krakenfx/kraken-cli/kraken-lab-experiment
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 krakenfx/kraken-cli --skill kraken-lab-experiment
Clone the repo
git clone --depth 1 https://github.com/krakenfx/kraken-cli

Made for: Claude Code.

Or install kraken-cli, the plugin that ships this one along with the rest of its 59 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 kraken-lab-experiment

README.md
[![agentmods](https://agentmods.dev/badge/skills/krakenfx/kraken-cli/kraken-lab-experiment/github.svg)](https://agentmods.dev/skills/krakenfx/kraken-cli/kraken-lab-experiment)
Your own site
<a href="https://agentmods.dev/skills/krakenfx/kraken-cli/kraken-lab-experiment"><img src="https://agentmods.dev/badge/skills/krakenfx/kraken-cli/kraken-lab-experiment/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 kraken-lab-experiment

Your own site · 80×15
<a href="https://agentmods.dev/skills/krakenfx/kraken-cli/kraken-lab-experiment"><img src="https://agentmods.dev/badge/skills/krakenfx/kraken-cli/kraken-lab-experiment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,731 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00061 $0.02731
Opus 5 $0.00030 $0.01366
Sonnet 5 $0.00012 $0.00546
Haiku 4.5 $0.00006 $0.00273

Measured 9d ago against content hash 373500d91962, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

kraken-lab-experiment 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 9d 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.

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/kraken-lab-experiment/SKILL.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lab Experiment Lifecycle

PREREQUISITE: Load kraken-playground to understand what a session is and where it lives.

Turn a trading hunch into a mechanical verdict: pre-register the hypothesis and its success criteria (hash-sealed, so the goalposts cannot move), run it as recorded paper runs, score each session against its own tape, and let the frozen criteria — not vibes — say pass or fail. Every step reads and writes plain files under the active scope, so the lifecycle survives kills, restarts, and context loss: whatever step you find half-done on disk is the step you resume.

Use this skill for:

  • driving one experiment end-to-end under /loop (freeze → run → score → verdict)
  • resuming an experiment a previous context started
  • reproducing a verdict cold, from files alone

Safety rules

  • Paper only: run experiments inside a paper workspace (export KRAKEN_WORKSPACE=<name>), where the order verbs fill on the paper account and no real funds are reachable.
  • Never edit a frozen experiment file. The seal exists to catch exactly that; a tampered spec fails every later step with a parse envelope.
  • Never report a verdict you did not obtain from lab score --experiment or lab compare output in this session. No estimating, no "it would probably pass".

The state machine

With a sealed session plan the whole table collapses to one command — run kraken lab next <exp> and do what it says:

kraken lab next momentum-1 -o json 2>/dev/null
# state: "start"         → run the exact `command` it prints, then stop+score
# state: "running"       → drive or wait, then `kraken session stop` + `lab score`
# state: "plan_complete" → `kraken lab compare <exp>`, conclude (Step 5)

lab next re-derives progress from the sessions tree on every call: completed runs consume plan entries in order, aborted sessions keep their ordinals and count for nothing, and a replay entry whose tape no longer matches its sealed hash is refused outright. Stop and score a finished run before asking again — an unstopped run has no summary and reads as aborted.

Read the full file on GitHub · 252 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. 9d ago First seen · 252 lines · 61 tokens per session scan A 373500d91962

Subscribe to this mod's changes

kraken-lab-experiment is a skill published in the GitHub repository krakenfx/kraken-cli (711 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 2,731 once invoked, about $0.0003 per session on Opus 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 2026-08-30.

Related

Other skills, from other repositories