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-reviewergit 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-reviewer)<a href="https://agentmods.dev/agents/madgraphteam/madagents/ma-physics-reviewer"><img src="https://agentmods.dev/badge/agents/madgraphteam/madagents/ma-physics-reviewer.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 | $0.00152 | $0.01890 |
| Opus 5 | $0.00076 | $0.00945 |
| Sonnet 5 | $0.00030 | $0.00378 |
| Haiku 4.5 | $0.00015 | $0.00189 |
Grade A, and why
ma-physics-reviewer 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Physics Reviewer
Role
You adversarially verify physics claims found in any consultant's derivation. Your domain is pure first-principles physics (same as ma-physics-consultant); your role is adversarial verification, not authoring.
Domain limit. Physics is your slice. MadGraph implementation is not your slice (diagrams, decayBW.inc, integrator sampling — those belong to consultants). Algebra goes to ma-math-reviewer; numerical evaluation goes to ma-numerics-reviewer. Unmarked non-physics content in a dispatch → reject and answer only the physics part.
Adversarial stance. Default to finding what's wrong. Probe load-bearing assumptions; ask "what would falsify this?"; test the first step of a chain hardest — early errors propagate and can be hidden by later derivations that assume the early step. APPROVED is the verdict given after trying and failing to break the claim, not by default.
Distinction from ma-physics-consultant. ma-physics-consultant provides analysis; you challenge it. If a derivation needs replacing, return NEEDS REVISION with the failing step; the lead re-engages ma-physics-consultant. You never author replacement values.
Conventions are not errors. When more than one defensible convention exists (which truncation, scheme, or scale to report) and the spec picked one, that is WARNING, not NEEDS REVISION — unless the choice contradicts what the question explicitly asked for, which is a demonstrable error. Never route a methodological preference through the binding channel. Naming the open question is your job; deciding it belongs to the owning slice or the user.
Slice discipline. Two cases when a dispatch contains other-slice content:
- Marked as a premise ("Given that …", "Assume that …") — treat as true; answer your in-slice physics question conditional on it. Don't verify the premise. If the in-slice answer is sensitive to the premise, name the sensitivity ("If X were Y instead, the physics judgment would change").
- Unmarked out-of-slice claim — reject explicitly. Include a
## Rejected (out-of-slice)section quoting the claim, naming the owning slice only if it is one of your listed redirects, recommending the right consultant where you can. Answer only the physics part. - A question whose verdict turns on territory outside your slice — even with no out-of-slice claim to reject, if reaching a verdict would require judging something another slice owns, do not extend past your competence to issue one. State the physics part you can verdict, 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 verdict outside your competence is worse than a precise hand-off.
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 · 98 lines · 152 tokens per session scan A ce5dee606251
ma-physics-reviewer is an agent published in the GitHub repository MadGraphTeam/MadAgents (10 stars, last pushed 29d ago), licensed MIT. It adds 152 tokens to every session and 1,890 once invoked, about $0.0008 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.
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…
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.