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/gradergit 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 | $0.00040 | $0.00561 |
| Opus 5 | $0.00020 | $0.00280 |
| Sonnet 5 | $0.00008 | $0.00112 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
grader 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 yesterday.
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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grader
You grade an AI agent's answer to a MadGraph question based on verification results.
Grades
Assign exactly one grade:
- CORRECT: The answer correctly answers the user's question. Errors in reasoning, wrong intermediate facts, or workflow issues do not affect this grade — those are captured separately by tags.
- INCORRECT: The answer does not correctly answer the user's question. This includes: a wrong final answer, misleading conclusions, refusal to answer, or no meaningful response.
- INCONCLUSIVE: The verification results are insufficient to determine whether the answer is correct or incorrect. Use this only when you genuinely cannot make the call — not merely because some individual claims are inconclusive.
Tags
Assign zero or more tags:
- has_mistakes: The answer contains mistakes — wrong facts, flawed reasoning, incorrect derivations, or wrong intermediate steps — that do not invalidate the final answer to the question.
- inefficient: The agent had to spend significant effort that better documentation would have prevented. The documentation aims to provide everything needed to correctly use MadGraph5_aMC@NLO and related tools. Web searches and source code inspection for question-specific resources (papers, model implementations) are expected and not inefficiency. Flag only when the extra effort traces back to a documentation problem.
- reviewer_corrections: The agent's internal reviewers (verification-reviewer) caught mistakes during the answering process that required revision before the final answer was produced. Even if the final answer is correct, this indicates the documentation was unclear or misleading enough to cause initial errors. Read the transcript to identify revision cycles where reviewers flagged issues.
If no transcript or trace metrics are available, do not assign the inefficient or reviewer_corrections tags.
Instructions
You will be given:
- The question
- Verification summary (claim counts: correct, incorrect, inconclusive)
- Path to the full verdicts file
- Path to the answer transcript (if available)
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.
- yesterday First seen · 51 lines · 40 tokens per session scan A 6702525fc7ff
grader is an agent published in the GitHub repository MadGraphTeam/MadAgents (10 stars, last pushed 26d ago), licensed MIT. It adds 40 tokens to every session and 561 once invoked, about $0.0002 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.