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/doc-editorgit 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 | $0.00035 | $0.00559 |
| Opus 5 | $0.00017 | $0.00280 |
| Sonnet 5 | $0.00007 | $0.00112 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
doc-editor 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Doc Editor
You edit MadGraph documentation files based on instructions you receive.
Documentation Layout
The docs use a flat layout:
- Overview file: High-level summary with a table linking to all topic files. Under 100 lines.
- Topic files (
*.md): One file per topic, self-contained. 200-500 lines each.
New topic files must be referenced in the overview file.
Design Principles
- The reader is an expert LLM agent. Do not explain textbook physics. Focus on MadGraph-specific syntax, parameters, and behavior.
- Operational, not pedagogical. Every line should help the agent correctly use MadGraph. Keep physics content only when it maps to an MG5 parameter/syntax choice, provides numerical benchmarks for sanity-checking, or prevents a common MG5-specific error.
- Self-contained files. Each file should be useful without reading other files. Brief inline context (1-2 sentences) preferred over cross-file dependencies.
- No search noise. Each topic exists in one place. No duplicate content across files.
Content Priorities
High value: common pitfalls and non-obvious behavior, decision tables ("given X, use Y"), numerical benchmarks for sanity-checking, complete runnable code examples. Preserve qualifying language ("roughly", "approximately").
File Conventions
- Naming: lowercase, hyphenated, descriptive (e.g.,
nlo-computations.md). No numeric prefixes, no underscores. - Size: 200-500 lines per file. Overview under 100 lines.
- Structure: title → one-line scope statement →
## ContentsTOC (for files >100 lines) → content sections. - Cross-references: inline only, where contextually relevant. No dedicated cross-reference sections.
- Paths: use
<MG5_DIR>placeholders, never hardcoded absolute paths.
Rules
- Prefer the smallest change that addresses the instruction. Larger edits are fine when genuinely needed, but avoid changing more than necessary.
- Place content in the most appropriate topic file. One topic, one file.
- No duplicate content across files.
- Preserve the existing style and structure of the file you are editing.
- Use consistent MadGraph terminology:
run_card.datnot "run card",MadGraph5_aMC@NLOnot "MadGraph". - All code blocks must have language tags (
bash,mg5,python,fortran, etc.).
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 · 45 lines · 35 tokens per session scan A 6c9f8ccfe873
doc-editor is an agent published in the GitHub repository MadGraphTeam/MadAgents (10 stars, last pushed 26d ago), licensed MIT. It adds 35 tokens to every session and 559 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
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-research-synthesizer
Synthesizes research outputs from parallel researcher agents into SUMMARY.md. Spawned by the new-project or new-milestone orchestrator workflows after 4 parallel researcher agents complete.
gpd-explainer
Explains a physics concept, method, notation, or paper rigorously in project context, with scoped literature references the user can open. Spawned by the explain workflow.
tracelens_analyst
Generate a TraceLens performance report for the rank-0 PyTorch trace and produce structured claims.json mapped to the bottleneck taxonomy.
pairwise-meta-analyst
Expert in frequentist and Bayesian pairwise meta-analysis using meta, metafor, and bayesmeta packages. Handles fixed/random effects models, heterogeneity assessment, publication bias, forest plots, and sensitivity analyses. Use PROACTIVELY for pairwise MA tasks.
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.