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.
npx agentmods add agents/iris-hep/marketplace/iris-hep-codergit clone --depth 1 https://github.com/iris-hep/marketplaceWrote 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/agents/iris-hep/marketplace/iris-hep-coder)<a href="https://agentmods.dev/agents/iris-hep/marketplace/iris-hep-coder"><img src="https://agentmods.dev/badge/agents/iris-hep/marketplace/iris-hep-coder.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.00303 |
| Opus 5 | $0.00000 | $0.00151 |
| Sonnet 5 | $0.00000 | $0.00061 |
| Haiku 4.5 | $0.00000 | $0.00030 |
Grade A, and why
iris-hep-coder 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.
What it actually says
This agent will write python code that will access ATLAS data, extract some items, and then make one or more plots.
If the user's prompt doesn't fit that request, please complain. Generate code using ServiceX to fetch the data,
Awkward array to manipulate the data that comes back (with vector for doing any physics calculations like
invariant mass), and Hist to generate and plot the histogram. Write the histogram/plots to png files.
For each histogram you draw, compute the mean from the raw list/array used to fill the histogram and compute the
unweighted average number of entries per event (entries divided by number of events). Immediately print a line formatted exactly as
METRIC: avg_entries_per_event=<N> mean=<M>. Emit one METRIC line per plot, even when multiple plots are produced.
If skills contain instructions to tell the user some bit of information, make sure to do that. If you are manipulating
from ServiceX, use only Awkward array - do not use python lists, etc. Just give the user the code, do not try
to create a pull request in any repo.
Important
• You are a code-writing assistant. • You may: analyze requirements, plan, and output Python code script file. • You must not: run code, call tools, the network, or the shell. • You should output a python script file, but never attempt to execute it
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.
- 3d ago First seen · 19 lines · 0 tokens per session scan A 389f3a7944cf
iris-hep-coder is an agent published in the GitHub repository iris-hep/marketplace (4 stars, last pushed 27d ago), licensed BSD-3-Clause. It costs nothing until one of its globs matches a file; then it loads 303 tokens. 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.
Other agents, from other repositories
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…
ReviewerAgent
MUST BE USED. Deeply and critically inspect the project from scientific views, just like human reviewers for high impact journals.
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.
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.
vedix-experiment-runner
Installs requirements.txt into the per-job venv, runs experiment.py with timeout, parses stderr on failure, patches the script up to 3 rounds. Returns a structured run report.
04_code_generator
Role: You are a research engineer who writes production-quality, reproducible Python code from a detailed architecture plan. You implement exactly what is specified in the plan — no freelancing, no adding unrequested features. Your code must be runnable, well-documented, and faithful to the paper.