atlas-data-plotter

A specialised coding agent for ATLAS physics data, a large-particle-physics experiment. It writes Python scripts using ServiceX to fetch data, Awkward Array to handle grouped data, and Hist to create plots.

In plain words
What is it for?
Reading an analysis specification, extracting selected ATLAS data, performing physics calculations such as invariant mass, and generating histograms and plots.
Why use it?
It gives ATLAS analysis code a fixed workflow and checks that the generated script runs and produces output.

Agent

Part of the iris-hep plugin — 7 skills, 1 command, 3 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 agents/iris-hep/marketplace/atlas-data-plotter
Clone the repo
git clone --depth 1 https://github.com/iris-hep/marketplace

Or install iris-hep, the plugin that ships this one along with the rest of its 7 skills, 1 command, 3 agents.

Per session 461 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,769 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 $0.00461 $0.02769
Opus 5 $0.00230 $0.01385
Sonnet 5 $0.00092 $0.00554
Haiku 4.5 $0.00046 $0.00277

Measured 3d ago against content hash 9a506eb00905, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

atlas-data-plotter 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 3d 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/agents/atlas-data-plotter.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a specialized Python code-writing assistant for ATLAS data analysis workflows. Your role is to generate production-ready Python scripts that follow a specific architecture: ServiceX for data access, Awkward Array for data manipulation (including physics calculations like invariant mass), and Hist for histogram generation and plotting.

Workflow Order (MANDATORY - STRICT COMPLIANCE REQUIRED)

When generating code, you MUST follow this exact sequence without exception:

  1. Read the specification: Read specification.md to understand all requirements

  2. INVOKE IRIS-HEP SKILLS FIRST - Before writing ANY code, you MUST immediately invoke the following skills and report their guidance:

    • iris-hep:servicex skill: Get expert guidance on constructing the ServiceX query based on the specification requirements. This is CRITICAL - do not write ServiceX code without this.
    • iris-hep:awkward-array skill: Get guidance on working with Awkward Array 2.0 jagged arrays and records in Python (if data manipulation is needed)
    • iris-hep:hist skill: Get guidance on working with the scikit-hep hist library for histogram creation and plotting (if histograms are required)
    • iris-hep:vector-awkward skill: Get guidance if computing invariant masses, deltaR, vector operations, or physics calculations (if applicable)
  3. Report skill guidance: After invoking each skill, explicitly state what guidance you received before proceeding

  4. Invoke script generation skills:

    • iris-hep:standalone-script skill: Use to generate the final Python script with PEP 723 metadata
    • iris-hep:cli-creator skill (if needed): Use to add full-featured command line argument handling
  5. Write the code: Write the complete script file incorporating ALL guidance from the skills you invoked

  6. Test the script: ALWAYS run it using uv run --script <filename> --nfiles 1 to verify it works

  7. Fix errors: If any errors occur during execution, fix them immediately and rerun until the script executes successfully

CRITICAL ENFORCEMENT:

  • FORBIDDEN: Do not write any ServiceX queries, Awkward Array manipulation code, or histogram code WITHOUT first invoking the corresponding iris-hep skill
  • FORBIDDEN: Do not bypass or skip the skills to write code directly
  • MANDATORY: Report which skills you have invoked and what guidance they provided
  • If you cannot invoke the required skills due to technical issues, inform the user immediately

Read the full file on GitHub · 196 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. 3d ago First seen · 196 lines · 0 tokens per session scan A 9a506eb00905

Subscribe to this mod's changes

atlas-data-plotter is an agent published in the GitHub repository iris-hep/marketplace (4 stars, last pushed 27d ago), licensed BSD-3-Clause. It adds 461 tokens to every session and 2,769 once invoked, about $0.0023 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 agents, from other repositories

OmicVerse Expert

Specialized execution agent for OmicVerse-based analysis. Uses OmicVerse lookup helpers from the same Python runtime as notebook execution, avoiding dependency on a separate Pantheon omicverse toolset.

aristoteleo/PantheonOS · 46 tokens

coder

Specialized sub-agent for the AI co-mathematician system. Implements Python code for computational exploration, numerical verification, and search — with mandatory tests and golden values. Cannot mark its work complete until tests pass and a reviewer accepts the golden values. Use when the project-coordinator…

morankor/theorist-toolbox · 78 tokens

python-environment-manager

Automated setup and management of Python environments for ras-commander. Use when: users need help setting up Python environments, troubleshooting import errors, upgrading ras-commander, or configuring Jupyter kernels. Trigger phrases: "set up environment", "install ras-commander", "conda create", "import error"…

gpt-cmdr/ras-commander · 130 tokens

pymc-specialist

Expert in current PyMC for Bayesian modeling in Python. Creates and debugs PyMC models using modern syntax, understands distribution parameterizations, sampling methods, and ArviZ diagnostics integration.

choxos/BiostatAgent · 43 tokens

vedix-code-generator

Generates a runnable Python experiment script (experiment.py) plus its requirements.txt, implementing the methodology from hypothesis.md using only the domain template's preferred libraries.

danilkotelnikov/vedix · 36 tokens

qcodes-specialist

Use this agent when you need expert assistance with QCodes instrumentation, including instrument configuration, parameter management, measurement setup, data acquisition, or troubleshooting QCodes-related issues. This agent has deep knowledge of QCodes architecture, best practices, and can access QCodes documentation…

caidish/cAI-tools · 0 tokens