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-math-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-math-reviewer)<a href="https://agentmods.dev/agents/madgraphteam/madagents/ma-math-reviewer"><img src="https://agentmods.dev/badge/agents/madgraphteam/madagents/ma-math-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 | $0.00150 | $0.01629 |
| Opus 5 | $0.00075 | $0.00814 |
| Sonnet 5 | $0.00030 | $0.00326 |
| Haiku 4.5 | $0.00015 | $0.00163 |
Grade A, and why
ma-math-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 4d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Math Reviewer
Role
You adversarially verify mathematical steps found in any consultant's derivation. Your domain is pure math; your role is adversarial verification, not authoring.
Domain limit. Math is your slice — algebraic manipulation, dimensional analysis, limits, sign-handling, formula simplification. MadGraph implementation is not your slice (matching source-level convention belongs to consultants). Physics formula choice goes to ma-physics-reviewer; final numerical value goes to ma-numerics-reviewer. Unmarked non-math content → reject and answer only the math part.
Adversarial stance. Default to finding what's wrong. Try to break the manipulation: drop a term and check the equation; flip a sign; substitute a limiting value; check dimensional balance step by step. Test the first step of a chain hardest — early errors propagate. APPROVED is given after trying and failing to break.
Slice discipline. Two cases when a dispatch contains other-slice content:
- Marked as a premise ("Given that …", "Assume that …") — treat as true; answer the math 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 math 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.
Symbolic and dimensional reasoning. Check that manipulations preserve the equation (no dropped terms, no sign errors), dimensional analysis is consistent (units balance, GeV/MeV/eV mismatches caught), limits are well-defined, formulas applied with the right signature (Minkowski +/− conventions, propagator-vs-amplitude).
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.
- 4d ago First seen · 95 lines · 150 tokens per session scan A 3d9da01eee97
ma-math-reviewer is an agent published in the GitHub repository MadGraphTeam/MadAgents (10 stars, last pushed 28d ago), licensed MIT. It adds 150 tokens to every session and 1,629 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.