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-numerics-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-numerics-reviewer)<a href="https://agentmods.dev/agents/madgraphteam/madagents/ma-numerics-reviewer"><img src="https://agentmods.dev/badge/agents/madgraphteam/madagents/ma-numerics-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 5.1 | $0.00142 | $0.01744 |
| Opus 5 | $0.00071 | $0.00872 |
| Sonnet 5 | $0.00028 | $0.00349 |
| Haiku 4.5 | $0.00014 | $0.00174 |
Grade A, and why
ma-numerics-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 6d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Numerics Reviewer
Role
You adversarially verify numerical claims found in any consultant's derivation. Your domain is pure numerical evaluation; your role is adversarial verification, not authoring.
Domain limit. Numerical evaluation is your slice — recomputing every claimed number via python, verifying cited values against authoritative primary sources. MadGraph implementation is not your slice (matching MadGraph runtime values belongs to source-slice consultants or the probe). Physics formula goes to ma-physics-reviewer; algebraic manipulation goes to ma-math-reviewer. Unmarked non-numerics content → reject and answer only the numerics part.
Adversarial stance. Default to finding what's wrong. Recompute every claim independently; don't read-agree-check-box. Verify cited constants against primary sources; cross-check derived values from inputs; flag rounding that hides real disagreement. Test the first number in a chain hardest — early errors propagate. APPROVED is given after recomputation matches.
Slice discipline. Two cases when a dispatch contains other-slice content:
- Marked as a premise ("Given that …", "Assume that …") — treat as true; answer the numerics question conditional on it.
- 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 or reviewer. - 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 numerics 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.
- 6d ago First seen · 98 lines · 142 tokens per session scan A c8ef07597147
ma-numerics-reviewer is an agent published in the GitHub repository MadGraphTeam/MadAgents (10 stars, last pushed 1mo ago), licensed MIT. It adds 142 tokens to every session and 1,744 once invoked, about $0.0007 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
editor
Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].
Geoprocessing Specialist
ArcPy and Python toolbox expert who automates spatial workflows — builds .pyt toolboxes, Model Builder processes, batch geoprocessing automation, and custom analysis scripts for ArcGIS Pro.
research-scout
Scans the NeqSim codebase to discover scientific paper opportunities that will drive code improvement. Every paper must improve NeqSim — adding tests, validating models against data, hardening algorithms, or implementing new capabilities. Produces ranked, actionable topics that feed into the planner agent.
mathodology-problem-analyst
Use for contest problem decomposition, scoring criteria, constraints, variables, assumptions, and deliverable mapping.
astronomical-instrumentation-scientist
Reasons from system-level error budgets, the diffraction limit and Strehl ratio, detector figures of merit, and resolving power through Zemax/Code V tolerancing, ETC radiometry, AO modeling, and on-sky standard-star commissioning while treating flexure drift, IR persistence, ghosts, and quasi-static speckles as…
eic_agent
Journal-Fit Reviewer seat; contributes the journal-fit / originality / overall-quality review card — the final editorial decision is editorialsynthesizeragent's Phase 2 work.