Borrowing it
Nothing to install: this file belongs to ethpandaops/ethereum-package. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ethpandaops/ethereum-package/main/.claude/skills/kurtosis-ethereum/SKILL.mdgit clone --depth 1 https://github.com/ethpandaops/ethereum-packageWrote 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.
[](https://agentmods.dev/skills/ethpandaops/ethereum-package/kurtosis-ethereum)<a href="https://agentmods.dev/skills/ethpandaops/ethereum-package/kurtosis-ethereum"><img src="https://agentmods.dev/badge/skills/ethpandaops/ethereum-package/kurtosis-ethereum/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.
<a href="https://agentmods.dev/skills/ethpandaops/ethereum-package/kurtosis-ethereum"><img src="https://agentmods.dev/badge/skills/ethpandaops/ethereum-package/kurtosis-ethereum.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00078 | $0.01651 |
| Opus 5 | $0.00039 | $0.00826 |
| Sonnet 5 | $0.00016 | $0.00330 |
| Haiku 4.5 | $0.00008 | $0.00165 |
Grade A, and why
kurtosis-ethereum scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://127.0.0.1:<cl-port>/eth/v1/beacon/states/head/finality_checkpoints | jq How it starts
The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kurtosis Devnet
Run Ethereum consensus/execution client devnets via kurtosis + ethereum-package.
Config Principle
Only include fields that differ from defaults. If the task doesn't mention a setting, don't include it. Shorter configs are better — let the defaults handle the rest.
Quick Start
# ALWAYS start the OTel stack first — runs an OTel collector + ClickHouse on the
# Docker host for centralized log (and trace) collection while debugging.
# Docker-only. Logs are stamped with the enclave name; traces require the
# `otel` additional_service (see below). ClickHouse on :18123, OTLP on :14317/:14318.
kurtosis otel start
# Write a network_params.yaml, then:
kurtosis run github.com/ethpandaops/ethereum-package \
--enclave <name> \
--args-file network_params.yaml \
--image-download always
kurtosis enclave ls # list enclaves
kurtosis enclave inspect <name> # inspect services + ports
kurtosis service logs <enclave> <svc> # view logs
kurtosis enclave rm -f <name> # cleanup
If you are told to use a fork or a branch of the ethereum-package, then replace github.com/ethpandaops/ethereum-package with github.com//ethereum-package@branch
If you want to quickly sanity check something, then use preset: "minimal". This will lead to much faster networks, but do not default to this approach. Only use it when you are sure you want to quickly check something. When the user expects it to behave like mainnet, then use preset: "mainnet".
Config Structure (network_params.yaml)
participants
Each entry is a CL+EL node. Only specify fields you need to override:
participants:
- el_type: geth # geth, reth, nethermind, besu, erigon
cl_type: lighthouse # lighthouse, lodestar, prysm, teku, nimbus
Available overrides (only use when needed):
el_image/cl_image/vc_image— custom Docker imagesel_extra_params/cl_extra_params/vc_extra_params— extra CLI flagsel_max_cpu/el_max_mem/cl_max_cpu/cl_max_mem— resource limits (millicores / MB)vc_type— separate validator client type (creates a dedicated vc service)use_remote_signer: true+remote_signer_type: web3signer— remote signingcount— number of identical instances (default: 1)validator_count— validators assigned (default: from network config)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 195 lines · 78 tokens per session scan A 574475407d05
kurtosis-ethereum is a skill published in the GitHub repository ethpandaops/ethereum-package (477 stars, last pushed 2d ago), licensed MIT. It adds 78 tokens to every session and 1,651 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
verification-protocol
How to prove a hypothesis is TRUE or FALSE using Move unit tests.
buy-x402
Buy from any x402-gated endpoint. Start with go — it probes, detects the offer type, and runs the right flow. Expert flows underneath: pay for one-shot HTTP services (single authorization, no sidecar), pay-agent for one-shot streaming agent calls, and buy for long-running paid inference (pre-authorized batch via…
bridging
Move assets between Ethereum L1 and L2s — canonical Arbitrum-style bridges (Arbitrum One, Robinhood Chain), Base's OP-stack bridge, and fast third-party routes (Across, CCIP). Quote the full round trip before moving anything: canonical deposits take 10-15 min, canonical withdrawals lock capital for 7 DAYS plus an L1…
building-blocks
DeFi legos and protocol composability on Ethereum and L2s. Major protocols per chain — Aerodrome on Base, GMX/Pendle on Arbitrum, Velodrome on Optimism — plus mainnet primitives (Uniswap, Aave, Compound, Curve). How they work, how to build on them, and how to combine them. Use when building DeFi integrations, choosing…
indexing
How to read historical onchain data at scale — events, logs, The Graph subgraphs, Ponder, and indexing patterns. Use when building a backend that needs past blockchain state (not live queries — use ethereum-networks for that). Covers why you cannot loop through blocks and what to use instead.
l2s
Ethereum Layer 2 landscape — Arbitrum, Optimism, Base, zkSync, Scroll, Unichain, Celo, and more. How they work, how to deploy on them, how to bridge, when to use which. Includes per-chain DeFi ecosystems and critical corrections. Use when choosing an L2, deploying cross-chain, or when a user asks about Ethereum…