vector-awkward

vector-awkward is a skill for Claude Code from iris-hep/marketplace. It costs 77 tokens per session (583 once invoked), scanned A, original, BSD-3-Clause.

A guide for using scikit-hep vector with Awkward Array, Python libraries for particle-physics data and vector calculations.

In plain words
What is it for?
Use it to calculate quantities such as angular separation, invariant mass, vector combinations, and boosts in Awkward data.
Why use it?
It avoids writing common kinematics formulas by hand and shows how to create records with the fields and types the libraries expect.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the iris-hep plugin — 7 skills, 1 command, 2 agents shipped together

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.

agentmods
npx agentmods add skills/iris-hep/marketplace/vector-awkward
Any agent
npx skills add iris-hep/marketplace --skill vector-awkward
Clone the repo
git clone --depth 1 https://github.com/iris-hep/marketplace

Made for: Claude Code.

Or install iris-hep, the plugin that ships this one along with the rest of its 7 skills, 1 command, 2 agents.

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 vector-awkward

README.md
[![agentmods](https://agentmods.dev/badge/skills/iris-hep/marketplace/vector-awkward.svg)](https://agentmods.dev/skills/iris-hep/marketplace/vector-awkward)
Your own site
<a href="https://agentmods.dev/skills/iris-hep/marketplace/vector-awkward"><img src="https://agentmods.dev/badge/skills/iris-hep/marketplace/vector-awkward.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 583 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00077 $0.00583
Opus 5 $0.00039 $0.00292
Sonnet 5 $0.00015 $0.00117
Haiku 4.5 $0.00008 $0.00058

Measured 6d ago against content hash b47091cf6924, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

vector-awkward 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 6d 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.

iris-hep/skills/vector-awkward/SKILL.md · 78 lines

What it actually says

Vector Awkward

Overview

Create Awkward Arrays that behave like vector objects and use vector methods without writing custom kinematic math. Use these steps to register behaviors, build records with the right field names, and perform common HEP operations like deltaR and invariant mass.

Quick Start

  1. Register vector behaviors once per session:
import vector
vector.register_awkward()
  1. Build vector records with standard field names and a vector type name:
import awkward as ak

events = ak.Array({
    "electron": ak.zip(
        {"pt": [50.0, 30.2], "eta": [1.4, -0.8], "phi": [2.1, 0.5], "mass": [0.0005, 0.0005]},
        with_name="Momentum4D",
    )
})

Build Vector Records

  • Use ak.zip(..., with_name="Momentum3D") for 3D operations like deltaR.
  • Use ak.zip(..., with_name="Momentum4D") for 4D operations like invariant mass or boosts.
  • Prefer standard names like pt/eta/phi/mass or px/py/pz/E so vector can infer coordinate systems.
  • Call vector.register_awkward() before accessing vector properties or methods.

Access Vector Properties

particles = ak.zip({"px": px, "py": py, "pz": pz, "E": E}, with_name="Vector4D")
particles.pt
particles.phi
particles.eta
particles.mass

Common Operations

Calculate deltaR between two collections:

pairs = ak.cartesian([events.electron, events.muon])
electrons, muons = ak.unzip(pairs)
dR = electrons.deltaR(muons)

Combine 4-vectors and compute invariant mass:

first_e, second_e = ak.unzip(ak.combinations(events.electron, 2))
inv_mass = (first_e + second_e).mass

Boost to a parent rest frame:

parent = particle1 + particle2
particle1_rf = particle1.boostCM_of_p4(parent)

Reference Material

Load references/vector-hints.md for more examples, method notes, and advanced snippets.

Files

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.

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. 6d ago First seen · 78 lines · 77 tokens per session scan A b47091cf6924

Subscribe to this mod's changes

vector-awkward is a skill published in the GitHub repository iris-hep/marketplace (4 stars, last pushed 1mo ago), licensed BSD-3-Clause. It adds 77 tokens to every session and 583 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

jupyter-notebook

Iterative Python via live Jupyter kernel (hamelnb).

NousResearch/hermes-agent · 18 tokens

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens

bioservices

Unified Python interface to 40+ bioinformatics services. Use when querying multiple databases (UniProt, KEGG, ChEMBL, Reactome) in a single workflow with consistent API. Best for cross-database analysis, ID mapping across services. For quick single-database lookups use gget; for sequence/file manipulation use…

K-Dense-AI/scientific-agent-skills · 73 tokens

pennylane

Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with…

K-Dense-AI/scientific-agent-skills · 98 tokens

cuopt-numerical-optimization-api

LP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface.

NVIDIA/skills · 51 tokens

rocm-kernels

Provides guidance for writing and benchmarking optimized Triton kernels for AMD GPUs (MI355X, R9700) on ROCm, targeting HuggingFace diffusers (LTX-Video, SD3, FLUX) and transformers. Core kernels: RMSNorm, RoPE 3D, GEGLU, AdaLN. Includes XCD swizzle, autotune, diffusers integration patterns, and LTX-Video pipeline…

huggingface/kernels · 93 tokens