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 skills add JamesZor/antigravity --skill science-researchgit clone --depth 1 https://github.com/JamesZor/antigravityWrote 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/skills/jameszor/antigravity/science-research)<a href="https://agentmods.dev/skills/jameszor/antigravity/science-research"><img src="https://agentmods.dev/badge/skills/jameszor/antigravity/science-research/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jameszor/antigravity/science-research"><img src="https://agentmods.dev/badge/skills/jameszor/antigravity/science-research.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00174 | $0.01584 |
| Opus 5 | $0.00087 | $0.00792 |
| Sonnet 5 | $0.00035 | $0.00317 |
| Haiku 4.5 | $0.00017 | $0.00158 |
Grade A, and why
science-research 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 8d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Science Research (primary sources)
You (Claude) are the orchestrator and verifier. The Antigravity MCP server drives agy's installed science skills — one worker per sub-question, each pinned to a real database CLI.
When to use this — and when not to
Two distinct families of skill live here. Do not assume this pipeline is biomedical-only — that mistake makes you skip it for questions it is genuinely good at:
1. All-discipline academic literature. literature-search-arxiv covers every arXiv category — statistics (stat.ME, stat.AP), maths, computer science, physics, economics, quantitative finance. literature-search-openalex indexes all scholarly work in every field, with real DOIs, citation counts and open-access PDFs. So a question like "what's the literature on Bayesian in-play updating of Poisson goal intensities?" or "how do people handle overdispersion in count models?" is squarely in scope — these will return real, citable papers.
2. Domain databases (life sciences / chemistry): PubMed, UniProt, PDB, ChEMBL, ClinVar, gnomAD, AlphaFold, ClinicalTrials.gov. Use when the answer must come from a primary record — a variant's clinical significance, a protein structure, a compound's bioactivity, a registered trial.
Do NOT use it for:
- General web topics — market scans, news, "what do people think of X", vendor comparisons, blog posts, documentation. Use
/deep-research(agy web search, any source, any topic). - Pure derivation or reasoning — "derive the posterior update for X". No database can answer that; just do the maths. (Though a literature scan for prior art via arXiv/OpenAlex is often a useful complement.)
The distinction that matters: /deep-research is web search, and web search will cheerfully hand you a plausible-looking DOI or PMID that does not exist. These skills call the real APIs and are forbidden to fabricate. Reach for /science-research when you need citations you can trust; reach for /deep-research when you need breadth across the open web.
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.
- 8d ago First seen · 72 lines · 0 tokens per session scan A c28331dd2d46
science-research is a skill published in the GitHub repository JamesZor/antigravity (0 stars, last pushed 1mo ago), licensed MIT. It adds 174 tokens to every session and 1,584 once invoked, about $0.0009 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 skills, from other repositories
personal-genomics
Analyse personal DNA / genome files for pharmacogenomics, disease risk, carrier status, ancestry and traits. Use whenever the user mentions DNA or genome analysis, a raw genome file, gene names, drug-gene interactions, or wants to combine multiple DNA sources.
biological-expert
Expert-level biology, biotechnology, genetics, bioinformatics, and computational biology. Use when the user mentions biology, biotechnology, genetics, bioinformatics, or genomics, or when the task involves Molecular Biology, Genomics & Bioinformatics, Systems Biology, or Data Analysis.
research-expert
Expert-level research methodology, academic writing, statistical analysis, and scientific investigation. Use when the user mentions methodology, statistics, academic writing, or experimental design, or when the task involves Research Design, Statistical Analysis, or Data Analysis.
r-expert
Expert-level R statistical computing, data analysis, and visualization. Use when the user mentions statistics, data analysis, ggplot2, or the tidyverse, or when the task involves R Fundamentals, Statistical Analysis, Data Visualization, or Code Style.
quantum-expert
Expert-level quantum computing, Qiskit, quantum algorithms, and quantum information. Use when the user mentions quantum computing, Qiskit, quantum algorithms, or quantum information, or when the task involves Quantum Mechanics Basics, Quantum Hardware, Circuit Design, or Algorithm Implementation.
publish-the-run-that-did-not-work
Report the experiment that failed, preserve the superseded one unchanged, and never re-roll for significance. Selection is the bias, not the number.