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 skills add iris-hep/marketplace --skill servicexgit 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/skills/iris-hep/marketplace/servicex)<a href="https://agentmods.dev/skills/iris-hep/marketplace/servicex"><img src="https://agentmods.dev/badge/skills/iris-hep/marketplace/servicex/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/iris-hep/marketplace/servicex"><img src="https://agentmods.dev/badge/skills/iris-hep/marketplace/servicex.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00074 | $0.00890 |
| Opus 5 | $0.00037 | $0.00445 |
| Sonnet 5 | $0.00015 | $0.00178 |
| Haiku 4.5 | $0.00007 | $0.00089 |
Grade A, and why
servicex 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ServiceX
Overview
Provide concise, correct func_adl query patterns for ServiceX on ATLAS xAOD, with best practices for selections, outputs, and deliver usage.
Workflow
- Identify the dataset type and base query.
- Use
FuncADLQueryPHYSLITEfor PHYSLITE or OpenData. - Use
FuncADLQueryPHYSfor PHYS or other derivations.
- Use
- Build a top-level
Selectthat gathers all required collections and singletons.- Apply object-level filters with nested
.Whereinside thisSelect. - Do not pick columns yet.
- Apply object-level filters with nested
- Apply event-level filtering with a top-level
.Whereafter the collectionsSelect. - Create a final top-level
Selectthat returns a single dictionary of output columns.- Convert units to standard LHC units (GeV, meters, etc.).
- Never return a nested dictionary.
- Use
deliveronce withNFiles=1by default and appropriate dataset source(s). - Make sure that the layout of the data that will be returned is remembered - downstream tasks that want to work with the data will need to understand it.
Core Rules
- Prefer two top-level
Selectcalls: collections first, output columns second. - Filter objects with nested
.Where; filter events with a top-level.Where. - Use a single final
Selectthat returns a dictionary of outputs. - Do not use
awkwardfunctions inside ServiceX queries. - Use
dataset.Ruciofor rucio DIDs anddataset.FileListfor URL lists. - Always set
NFiles=1by default. - For fetches where cache bypass matters, use
ignore_local_cache=Trueindeliver. - If a transform fails and logs are required, respond with
HELP USER. - Ensure
func_adl_servicex_xaodr25is listed as a dependency in the active project and installed in the current virtual environment before running or generating code that uses it. - When using xAOD tool helpers, add
hep-llm-helpers>=1.0.0b1to the active project; standalone PEP 723 scripts must list it in their dependency block, and imports usehep_llm_helpers.xaod_hints. - When defining an xAOD accessor, the Python variable assigned by
make_tool_accessormust exactly match itsfunction_name(for example,tag_weight = make_tool_accessor(..., function_name="tag_weight", ...)); use that same name in the later query. A mismatch causes an unknown-type translation error. - In standalone-script metadata, declare
jinja2explicitly if the environment requires it forfunc_adl_servicex_xaodr25usage.
What ships with it
9 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.
- references/datamodel-xaod-event-weights.md 4.1 KB
- references/datamodel-xaod-missing-et.md 434 B
- references/datamodel-xaod-objects.md 654 B
- references/datamodel-xaod-tau.md 395 B
- references/datamodel-xaod-tlorentzvector.md 363 B
- references/datamodel-xaod-tools-btagging.md 4.7 KB
- references/datamodel-xaod-units.md 288 B
- references/servicex-async-hints.md 1.5 KB
- references/servicex-hints.md 8.9 KB
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.
- 9d ago First seen · 55 lines · 74 tokens per session scan A 5604021e9427
servicex is a skill published in the GitHub repository iris-hep/marketplace (4 stars, last pushed 1mo ago), licensed BSD-3-Clause. It adds 74 tokens to every session and 890 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.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
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.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…