starlark-dev

starlark-dev is a skill for Claude Code, Codex from kurtosis-tech/kurtosis. It costs 50 tokens per session (1,191 once invoked), scanned A, original, Apache-2.0.

A guide for writing and troubleshooting Kurtosis Starlark packages. Kurtosis is a tool for describing and running groups of services, while Starlark is the scripting language used to define them.

In plain words
What is it for?
Use it to create packages, add services, run commands, debug with print statements, handle future references, and test packages locally.
Why use it?
It explains Kurtosis's plan-first execution model, where scripts describe actions before they run, which helps avoid mistakes when using returned future values or debugging packages.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to create packages, add services, run commands, debug with print statements, handle future references, and test packages locally.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kurtosis-tech/kurtosis/starlark-dev
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 kurtosis-tech/kurtosis --skill starlark-dev
Clone the repo
git clone --depth 1 https://github.com/kurtosis-tech/kurtosis

Made for: Claude Code, Codex.

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 starlark-dev

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/kurtosis-tech/kurtosis/starlark-dev"><img src="https://agentmods.dev/badge/skills/kurtosis-tech/kurtosis/starlark-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,191 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 $0.00050 $0.01191
Opus 5 $0.00025 $0.00596
Sonnet 5 $0.00010 $0.00238
Haiku 4.5 $0.00005 $0.00119

Measured 9d ago against content hash 1e580d6c4743, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

starlark-dev 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/starlark-dev/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Starlark Dev

Create, debug, and test Kurtosis Starlark packages.

Package structure

A minimal Kurtosis package needs two files:

my-package/
  kurtosis.yml    # Package metadata
  main.star       # Entry point

kurtosis.yml

name: github.com/your-org/my-package

main.star

def run(plan, args):
    plan.add_service(
        name="my-service",
        config=ServiceConfig(
            image="nginx:latest",
            ports={
                "http": PortSpec(number=80, transport_protocol="TCP"),
            },
        ),
    )

Running packages

# Run a local package
kurtosis run ./my-package

# Run with parameters
kurtosis run ./my-package '{"param1": "value1"}'

# Run a remote package from GitHub
kurtosis run github.com/ethpandaops/ethereum-package

# Run with a custom config file
kurtosis run github.com/ethpandaops/ethereum-package --args-file config.yaml

# Dry run (plan only, no execution)
kurtosis run ./my-package --dry-run

Execution model

Kurtosis Starlark executes in two phases:

  1. Planning phase — Your code runs and builds a plan of actions. add_service(), exec(), etc. don't execute immediately — they return future references.
  2. Execution phase — The plan is executed in order. Future references are resolved to actual values.

This means you cannot use the return value of plan.exec() in Python-level logic like if/else during the planning phase. Use plan.verify() or plan.assert() instead.

# WRONG: result is a future reference, not a real value during planning
result = plan.exec(service_name="my-service", recipe=ExecRecipe(command=["echo", "hello"]))
if result["output"] == "hello":  # This won't work as expected
    plan.print("matched")

# RIGHT: use plan.verify for conditional checks
result = plan.exec(service_name="my-service", recipe=ExecRecipe(command=["echo", "hello"]))
plan.verify(result["exit_code"], "==", 0)

Debugging with print

def run(plan, args):
    plan.print("Args received: {}".format(args))

    service = plan.add_service(
        name="my-service",
        config=ServiceConfig(image="nginx:latest"),
    )
    plan.print("Service IP: {}".format(service.ip_address))
    plan.print("Service hostname: {}".format(service.hostname))

Read the full file on GitHub · 189 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 · 189 lines · 50 tokens per session scan A 1e580d6c4743

Subscribe to this mod's changes

starlark-dev is a skill published in the GitHub repository kurtosis-tech/kurtosis (551 stars, last pushed 6d ago), licensed Apache-2.0. It adds 50 tokens to every session and 1,191 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

Pair Programming

AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with…

amangit1314/repo-rag · 61 tokens

run-llms

Comprehensive guide for setting up and running local LLMs using Harbor. Use when user wants to run LLMs locally, set up or troubleshoot Ollama, Open WebUI, llama.cpp, vLLM, SearXNG, Open Terminal, or similar local AI services. Covers full setup from Docker prerequisites through running models, per-service…

av/harbor · 114 tokens

harbor

CLI toolkit for managing containerized LLM services. Use when the user wants to start, stop, configure, or manage AI/LLM services like Ollama, Open WebUI, llama.cpp, vLLM, LiteLLM, ComfyUI, and 250+ others. Triggers on requests to "run a model", "start ollama", "set up an LLM", "configure harbor", "manage services"…

av/harbor · 114 tokens

submit-github-bug-issue

Use when converting QA findings, black-box failures, red-team reports, regression evidence, or local bug notes into GitHub Issues for NVIDIA/TensorRT-Model-Connect. Standardizes checking issue templates, checking labels, de-duplicating existing issues, drafting a bug report, creating the issue on GitHub, applying the…

NVIDIA/TensorRT-Model-Connect · 82 tokens

examples-qa

Verify Instructor behavior through the repository's ./examples/ suite in pass, live record, or hermetic replay mode. Use when running selected examples or the corpus, capturing and reusing recorded LLM HTTP responses, diagnosing hub results, or distinguishing real errors, assertion failures, skipped examples, and…

cognesy/instructor-php · 67 tokens

playwright-e2e-testing

This skill should be used when the user asks to "create an E2E test", "write a Playwright scenario", "add a Playwright test", "generate e2e tests", "create actions and checks", "write playwright checks", "add scenario for feature", or when modifying, reviewing, or debugging Playwright E2E test files in the workspace.

AmadeusITGroup/otter · 82 tokens