TornadoVM: Skill for Claude Code

.claude/skills/tornadovm-perf-campaign/SKILL.md

tornadovm-perf-campaign is a skill for Claude Code from beehive-lab/TornadoVM. It costs 112 tokens per session (2,002 once invoked), scanned A, original, Apache-2.0.

A guided workflow for measuring and improving TornadoVM runtime performance and correctness. TornadoVM is a Java system that can run code on hardware accelerators such as GPUs.

In plain words
What is it for?
It profiles host and driver time, tests performance hypotheses with standalone probes, compares builds, applies measured changes, and prepares one pull request per verified claim.
Why use it?
It replaces guesses about slowness with profiling, controlled comparisons, and tests that can show whether a proposed change really helps.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents.

This is beehive-lab/TornadoVM's own configuration. It tells Claude Code how to work on TornadoVM itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything TornadoVM configures →

About the project

TornadoVM is a Java framework that compiles Java code into programs for GPUs and multicore CPUs at runtime. Java developers use it to run compute-heavy code on NVIDIA, AMD, Intel, and Apple hardware without writing CUDA C or maintaining JNI bindings.

beehive-lab/TornadoVM · 1,498 stars · on GitHub · tornadovm.org

Reuse

Borrowing it

Nothing to install: this file belongs to beehive-lab/TornadoVM. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/beehive-lab/TornadoVM/master/.claude/skills/tornadovm-perf-campaign/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/beehive-lab/TornadoVM

Made for: Claude Code.

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 tornadovm-perf-campaign

README.md
[![agentmods](https://agentmods.dev/badge/skills/beehive-lab/tornadovm/tornadovm-perf-campaign/github.svg)](https://agentmods.dev/skills/beehive-lab/tornadovm/tornadovm-perf-campaign)
Your own site
<a href="https://agentmods.dev/skills/beehive-lab/tornadovm/tornadovm-perf-campaign"><img src="https://agentmods.dev/badge/skills/beehive-lab/tornadovm/tornadovm-perf-campaign/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 tornadovm-perf-campaign

Your own site · 80×15
<a href="https://agentmods.dev/skills/beehive-lab/tornadovm/tornadovm-perf-campaign"><img src="https://agentmods.dev/badge/skills/beehive-lab/tornadovm/tornadovm-perf-campaign.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,002 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 $0.00112 $0.02002
Opus 5 $0.00056 $0.01001
Sonnet 5 $0.00022 $0.00400
Haiku 4.5 $0.00011 $0.00200

Measured 11d ago against content hash 5b7b298eab5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

tornadovm-perf-campaign 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 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.

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.

.claude/skills/tornadovm-perf-campaign/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Running a TornadoVM optimisation campaign

A campaign is a loop, not a patch: measure → attribute → hypothesise → falsify → change → re-measure → ship with numbers. The hard part is not writing the optimisation; it is knowing which microsecond you are removing and proving you removed it.

Files here:

  • references/measurement.md — exact profiling and A/B recipes, baselines, tool gotchas
  • references/probes.md — standalone probe harness and ready-made probe shapes
  • references/catalogue.md — the optimisation-pattern catalogue and what a previous campaign found (with numbers)

The loop

  1. Profile before touching anything. Host time = JFR; driver/device time = nsys. Attribute per phase (start-up vs steady state; per-execution vs per-token). Never profile with -Dtornado.profiler=True — TornadoVM's own profiler perturbs a short task graph by ~3x and misreports transfer timers by up to 20x (that was itself a finding, PR #1024).
  2. State the hypothesis as a number. "The 24-byte stack-frame upload costs 2.00 µs per launch, the same as the 2 KB user copy" is a hypothesis. "Dispatch feels slow" is not.
  3. Falsify with a standalone probe before editing runtime code. A probe is 40 lines in the scratchpad, compiles against the built SDK, and runs in seconds (references/probes.md). Several campaign hypotheses died here — cheaply.
  4. Change one mechanism. If two changes have separate numbers, they are two PRs.
  5. A/B in the same build family: stash the change, rebuild, measure baseline, restore, rebuild, measure. Medians of 3+ runs. Always include a control that must not move (a GPU-bound workload) — if it moves, the measurement is wrong.
  6. Separate displaced work from removed work. Vary the iteration count: a fixed cost shrinks as a percentage, a per-iteration cost does not. A "speed-up" that vanishes at 512 iterations was a cost you moved, not one you deleted.
  7. Ship with the numbers, the controls, and the negatives. See "PR shape" below.

Read the full file on GitHub · 91 lines

Files

What ships with it

3 files 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.

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. 11d ago First seen · 91 lines · 112 tokens per session scan A 5b7b298eab5f

Subscribe to this mod's changes

tornadovm-perf-campaign is a skill published in the GitHub repository beehive-lab/TornadoVM (1,498 stars, last pushed today), licensed Apache-2.0. It adds 112 tokens to every session and 2,002 once invoked, about $0.0006 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

quarkus-native

Deep expertise in Quarkus Native Image builds, GraalVM integration, reflection configuration, and Profile-Guided Optimization. Use for native compilation questions.

kinhluan/rules-quarkus-skills · 36 tokens

graalvm-expert

Expert knowledge for GraalVM, Native Image (AOT), Polyglot runtime, and reflection/resource configuration. Use for native compilation and multi-language JVM questions.

kinhluan/rules-quarkus-skills · 39 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

azure-security-keyvault-secrets-java

Azure Key Vault Secrets Java SDK for secret management. Use when storing, retrieving, or managing passwords, API keys, connection strings, or other sensitive configuration data.

microsoft/skills · 40 tokens

azure-communication-chat-java

Build real-time chat applications with Azure Communication Services Chat Java SDK. Use when implementing chat threads, messaging, participants, read receipts, typing notifications, or real-time chat features.

microsoft/skills · 41 tokens

azure-ai-agents-persistent-java

Azure AI Agents Persistent SDK for Java. Low-level SDK for creating and managing AI agents with threads, messages, runs, and tools. Triggers: "PersistentAgentsClient", "persistent agents java", "agent threads java", "agent runs java", "streaming agents java".

microsoft/skills · 63 tokens