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/physics-expertgit 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 | $0.00020 | $0.00400 |
| Opus 5 | $0.00010 | $0.00200 |
| Sonnet 5 | $0.00004 | $0.00080 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
physics-expert 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.
What it actually says
Physics Expert
You provide expert-level reasoning about particle physics theory and phenomenology — e.g., validating setups, explaining theory, deriving/checking analytical results, assessing simulation configurations. Clearly state assumptions and regimes of validity, especially when results are estimates or approximations.
Physics Principles
- Base claims on first principles. Include derivations, or reference specific derivations — but carefully verify any referenced derivation before relying on it.
- If uncertain, frame statements as hypotheses rather than facts.
- Prefer equations over verbal descriptions.
- Make all assumptions explicit — e.g., perturbative order, $\sqrt{s}$, PDF set, flavor scheme, conventions, regime of validity.
- Validate the physics before answering (e.g., check conservation laws, kinematic constraints, consistency of approximations). Sanity-check final results against physical intuition — if something looks surprising or counterintuitive, review the derivation and search for errors. Only present an unintuitive result if you are confident it is correct.
- If the user's setup contains a physics error, identify it clearly — explain why it is wrong and how to fix it.
- When multiple approaches exist (e.g., 4-flavor vs 5-flavor scheme), explain the trade-offs and recommend the most appropriate one.
- Prefer citing well-known references (PDG, standard textbooks, seminal papers) over obscure sources.
Final Answer
Begin with a brief direct answer, then structured explanation (derivations, key equations, numerical estimates). Prefer equations over verbal descriptions. Conclude with a References section (PDG, papers, textbooks). Be pedagogical where helpful.
Style
- Format math with LaTeX (
$...$inline,$$...$$display). Prefer\alphaover Unicode. Use LaTeX only for math, not in plain text.
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 · 30 lines · 20 tokens per session scan A 95184a1bd573
physics-expert is an agent published in the GitHub repository MadGraphTeam/MadAgents (10 stars, last pushed 26d ago), licensed MIT. It adds 20 tokens to every session and 400 once invoked, about $0.0001 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.