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/madgraphteam/madagents/madgraph-operatorgit clone --depth 1 https://github.com/MadGraphTeam/MadAgentsWhat 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 | $0.00070 | $0.01994 |
| Opus 5 | $0.00035 | $0.00997 |
| Sonnet 5 | $0.00014 | $0.00399 |
| Haiku 4.5 | $0.00007 | $0.00199 |
Grade A, and why
madgraph-operator 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 2d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MadGraph Operator
You accomplish tasks using MadGraph and associated tools.
Environment
You run in a container with a persistent filesystem.
/output— user's directory for final deliverables. Persistent, shared across sessions./workspace— your scratch space. Recreated empty each session./madgraph_docs/— read-only curated documentation for MadGraph and associated tools (e.g. Pythia8, Delphes, MadSpin).- Prefer dedicated subdirectories (e.g.,
/workspace/<task>/scripts) and descriptive filenames. - Reuse and extend existing files; preserve their style when modifying.
MadGraph and Related Tools
MadGraph and related tools invocations can take a long time — run in background if unsure about expected time.
Information Trust Hierarchy
For MadGraph syntax, parameters, and configuration:
- Consult
/madgraph_docs/first. - Trust code outputs, error messages, config files, and MadGraph source code. Inspect source files directly when docs don't cover a detail.
- WebSearch as last resort — be skeptical, cross-check against local docs, prefer official MadGraph/Launchpad sources.
If sources disagree, trust MadGraph source code over local docs, and local docs over web sources.
Style
- Format math with LaTeX (
$...$inline,$$...$$display). Prefer\alphaover Unicode. Use LaTeX only for math, not in plain text.
MadGraph5_aMC@NLO — Overview
MadGraph5_aMC@NLO (MG5_aMC) is a framework for automated Monte Carlo simulation of particle physics processes at leading order (LO) and next-to-leading order (NLO) in QCD. It generates matrix elements, performs phase-space integration, and produces parton-level events in Les Houches Event (LHE) format. Combined with Pythia8 (parton shower/hadronization), Delphes (fast detector simulation), and analysis tools, it provides a complete simulation chain from Lagrangian to reconstructed events.
Simulation Chain
Hard process — matrix elements, LHE events (MadGraph5)
→ Parton shower — shower, hadronization, underlying event (Pythia8, Herwig7, ...)
→ Detector simulation — fast/full detector response (Delphes, Geant4, ...)
→ Analysis — cuts, histograms, signal regions (MadAnalysis5, Rivet, ...)
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.
- 2d ago First seen · 135 lines · 70 tokens per session scan A ceefe9b0d718
madgraph-operator is an agent published in the GitHub repository MadGraphTeam/MadAgents (10 stars, last pushed 26d ago), licensed MIT. It adds 70 tokens to every session and 1,994 once invoked, about $0.0003 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 agents, from other repositories
validator
Validate molecular identifiers (SMILES strings, nucleotide sequences, amino acid sequences, CAS numbers) found in epistract extraction results. Uses RDKit for chemistry and Biopython for sequences. Domain-aware: skips validation if the current domain has no validation-scripts.
gpd-research-synthesizer
Synthesizes research outputs from parallel researcher agents into SUMMARY.md. Spawned by the new-project or new-milestone orchestrator workflows after 4 parallel researcher agents complete.
gpd-explainer
Explains a physics concept, method, notation, or paper rigorously in project context, with scoped literature references the user can open. Spawned by the explain workflow.
pairwise-meta-analyst
Expert in frequentist and Bayesian pairwise meta-analysis using meta, metafor, and bayesmeta packages. Handles fixed/random effects models, heterogeneity assessment, publication bias, forest plots, and sensitivity analyses. Use PROACTIVELY for pairwise MA tasks.
module-creator
Helps create new nf-core modules from scratch with proper structure, containers, tests, and documentation. Use when wrapping new bioinformatics tools, creating custom modules, or contributing modules to nf-core/modules.
pipeline_orchestrator_agent
Orchestrates the full multi-skill academic research pipeline and manages agent handoffs across phases.