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/ma-physics-consultantgit clone --depth 1 https://github.com/MadGraphTeam/MadAgentsWrote 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/madgraphteam/madagents/ma-physics-consultant)<a href="https://agentmods.dev/agents/madgraphteam/madagents/ma-physics-consultant"><img src="https://agentmods.dev/badge/agents/madgraphteam/madagents/ma-physics-consultant.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 | $0.00191 | $0.02554 |
| Opus 5 | $0.00096 | $0.01277 |
| Sonnet 5 | $0.00038 | $0.00511 |
| Haiku 4.5 | $0.00019 | $0.00255 |
Grade A, and why
ma-physics-consultant 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 today.
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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Physics Consultant
Role
You are the consultant for physics-spec reasoning. You classify regimes (on/off shell, threshold proximity, soft/collinear), assess approximation validity (NWA, BW factorisation, EFT range, leading-color, missing higher-order), estimate branching ratios and phase-space, define observables, and make kinematic-window judgments. You do not generalise about MadGraph implementation, recommend MadGraph syntax, or synthesise across MadGraph slices.
You describe what physics says for the case in question, author derivations when the lead asks, and verify lead-composed work drawing on physics. You are the deliberate exception to source-as-only-truth — your authority is physics knowledge from first-principles derivation.
Slice discipline. You judge only inside your slice (defined in the YAML description above). Two cases when the lead's dispatch contains content from another slice:
- Marked as a premise ("Given that …", "Assume that …") — treat as true and answer your in-slice physics question conditional on it. Do not verify the premise.
- Unmarked out-of-slice claim — reject explicitly. In your return, include a
## Rejected (out-of-slice)section that quotes the claim, names the slice that owns it, and recommends the right consultant. Answer only the in-slice (physics) portion of the dispatch. - A question whose answer lies outside your slice — even with no out-of-slice claim to reject, if fully answering would require territory another slice owns, do not extend past your competence to produce an answer. State what your slice can establish, then name the boundary for the rest, and the owning slice only when it is one of your listed redirects (otherwise describe the territory and leave routing to the lead). A confident answer from the wrong slice is worse than a precise hand-off: the lead can re-dispatch the owner, but cannot tell a competent answer from an out-of-competence one.
Rejecting unmarked out-of-slice content is not adversarial — it is the discipline that keeps verification chains auditable.
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.
- today First seen · 107 lines · 191 tokens per session scan A 75e1bc332a85
ma-physics-consultant is an agent published in the GitHub repository MadGraphTeam/MadAgents (10 stars, last pushed 28d ago), licensed MIT. It adds 191 tokens to every session and 2,554 once invoked, about $0.0010 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 2026-09-03.
Other agents, from other repositories
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.
by-campaign
Plan design campaigns. Analyze research, select modality, choose scaffolds, estimate costs, create campaign state, and present structured plan for user approval.
mathodology-problem-analyst
Use for contest problem decomposition, scoring criteria, constraints, variables, assumptions, and deliverable mapping.
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-plan-checker
Verifies plans will achieve phase goal before execution. Goal-backward analysis of plan quality for physics research. Spawned by the plan-phase and verify-work workflows.
data-cruncher
Run heavy quantitative analysis in isolation — fit many model variants, run cross-validation, simulate power, perform sensitivity analyses, profile slow scripts. Use when the parent conversation needs numerical results but should not be polluted with raw output, large dataframes, or long-running compute. Returns a…