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 skills/madgraphteam/madagents/installnpx skills add MadGraphTeam/MadAgents --skill installgit 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 | $0.00062 | $0.02468 |
| Opus 5 | $0.00031 | $0.01234 |
| Sonnet 5 | $0.00012 | $0.00494 |
| Haiku 4.5 | $0.00006 | $0.00247 |
Grade B, and why
install scanned grade B with 1 finding 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 2d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cp ../madagents_codex/.codex/config.toml <target>/.codex/ How it starts
The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install MadAgents into a folder
Your working directory is install/; the repo root is ... You perform the
install — there is no installer script. What is left of installer.py is a
read-only verify command.
Read install-policy.md before you write anything. It holds the five
invariants (never remove what you do not own; copy bytes, never transcribe;
report collisions by name; no automatic git init; always verify) and the
manifest format. This file is the procedure; that one is the contract, and the
Claude Code installer works to the same one.
In install/ beside the policy, read on demand:
example-install.md— a finished install in full: the tree, the wrapper, the manifest.troubleshooting.md— the failure modes and how to tell them apart.
1. Ask, then survey — and survey before you write
Where. The folder to install into. It becomes the project root, so it should
be the folder the user will actually work in. Accept ~.
Which memory pack. List them from the source of truth, not from memory:
python3 -c "import sys; sys.path.insert(0,'../src'); from launcher.setup import memory_options; [print(f'{n:18} {d}') for n, d in memory_options()]"
pretrained is the default and right for Anthropic models; the -local packs
are for a self-hosted model; none starts cold.
Which CLI to install for. codex or claude_code. This is independent of
which CLI you run under: you are Codex, and you can install either. An install
belongs to one provider, and there is no conversion afterwards.
Then survey the target and report what you find before writing anything:
ls -A <target> 2>/dev/null
cat <target>/.madagents/install.json 2>/dev/null
2. Classify — the step that used to be a bad guess
| What you see | What it is | What you do |
|---|---|---|
| Folder empty or absent | a fresh install | §3 |
.madagents/install.json present |
an existing MadAgents install | §4, upgrade |
| Files present, no manifest | the user's own project | §5, additive — ask first |
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.
- 2d ago First seen · 214 lines · 62 tokens per session scan B 43aae40d4bed
install is a skill published in the GitHub repository MadGraphTeam/MadAgents (10 stars, last pushed 26d ago), licensed MIT. It adds 62 tokens to every session and 2,468 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
experimental-design
Design experiments and studies BEFORE data is collected — choosing a design, randomizing, blocking, and laying out treatment combinations so results are interpretable. Use whenever someone is planning a study, asks how to assign subjects/samples to groups, mentions randomization, blocking, stratification, controls…
arboreto
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for…
flux-analyzer
Analyse FBA flux distributions to extract biological insights. Covers gene essentiality, phenotypic phase planes, flux sampling, pathway-level aggregation, secretion product prediction, and production of publication- quality figures.
ligandmpnn
Inverse-fold a backbone with ligand, nucleic-acid, and metal context using LigandMPNN (Dauparas et al. 2023, github.com/dauparas/LigandMPNN). Reach for this skill to redesign the residues lining a binding pocket around a bound small molecule or cofactor, to design metal-coordinating sites where the geometry must be…
happiness-skill
当用户问「怎么才能更幸福/为什么得到了还不满足/怎么减少焦虑」时调用。 核心理念: 幸福是缺憾感清空的默认状态, 是可训练的技能; 欲望是与自己的契约(得到前不快乐), 同时只留一个重大欲望; 活在当下。 不适用于: 临床抑郁等需要专业治疗的场景(本书方法不能替代医疗)。 Triggers: 幸福/不快乐/欲望/焦虑/知足/活在当下/happiness/desire/anxiety.
evo2
Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model. Use this skill when: (1) Computing per-nucleotide or per-sequence likelihoods for variant effect scoring, (2) Embedding genomic windows for downstream classification, (3) Generating DNA conditioned on a prefix, (4) Scoring…