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 fmschulz/omics-skills --skill biorxiv-searchgit clone --depth 1 https://github.com/fmschulz/omics-skillsWrote 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/fmschulz/omics-skills/biorxiv-search)<a href="https://agentmods.dev/skills/fmschulz/omics-skills/biorxiv-search"><img src="https://agentmods.dev/badge/skills/fmschulz/omics-skills/biorxiv-search/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/fmschulz/omics-skills/biorxiv-search"><img src="https://agentmods.dev/badge/skills/fmschulz/omics-skills/biorxiv-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 45 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00045 | $0.02225 |
| Opus 5 | $0.00023 | $0.01112 |
| Sonnet 5 | $0.00009 | $0.00445 |
| Haiku 4.5 | $0.00005 | $0.00222 |
Grade A, and why
biorxiv-search 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 6d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bioRxiv Search
Search bioRxiv through its official API for recent-preprint discovery, date-range scans, DOI lookups, author shortlisting, and local keyword filtering over title, abstract, and author metadata.
Instructions
- Prefer this skill when the request is about bioRxiv-native preprints, recent biology submissions, or preprint metadata that may lag in PubMed, PMC, or Crossref.
- Use the bundled CLI:
- In this repository:
skills/biorxiv-search/scripts/search - After installation:
~/.agents/skills/biorxiv-search/scripts/search
- In this repository:
- The official bioRxiv API does not provide a general server-side keyword search endpoint.
- Use the CLI to fetch metadata from a bounded recent window or explicit date range, then filter locally.
- When keywords are provided, search
title,abstract, andauthorsby default.- If the user wants abstract-only matching, pass
--fields abstract.
- If the user wants abstract-only matching, pass
- Keep the search window bounded.
- Use
--days Nfor recent scans or--start-date YYYY-MM-DD --end-date YYYY-MM-DDfor explicit intervals. - If you omit the interval, the CLI defaults to the most recent 30 days.
- The CLI converts
--days Ninto an explicit date range before calling the API so pagination stays predictable.
- Use
- Use
--category <name>when the topic should stay narrow.- The API accepts the bioRxiv category as a query parameter such as
cell_biology,genomics, orneuroscience.
- The API accepts the bioRxiv category as a query parameter such as
- Use
--authorfor author-specific requests.- By default, consider both the supplied full-name form and an abbreviated-first-name form, for example
--author "Peter Nugent"and--author "P. Nugent". - Do not silently merge these in the final answer. Report full-name matches and abbreviated-first-name matches in separate groups because initials can be ambiguous.
- The CLI normalizes both given-name-first and API-style
Surname, F. M.forms. Prefer separate passes or a local partition of returned records by the literalauthorstext when you need clean buckets.
- By default, consider both the supplied full-name form and an abbreviated-first-name form, for example
- The API currently returns up to 30 records per page.
- The API orders an interval from oldest to newest. The CLI reads
countandtotal, starts at the newest page, and scans backward. - Increase
--scan-limitwhen a broad query needs more of the interval inspected.
- The API orders an interval from oldest to newest. The CLI reads
- By default, the CLI collapses multiple versions of the same preprint and keeps the latest version for each DOI.
- Use
--all-versionsonly when version-by-version output matters.
- Use
- Treat the API output as discovery metadata.
- If exact citation details or the latest abstract-page presentation matter, verify the shortlisted candidates on bioRxiv or the DOI landing page before finalizing the answer.
- If the user wants peer-reviewed biomedical literature or PMC full text rather than bioRxiv preprints, use
polars-dovmedinstead. - The CLI retries
HTTP 429and transient5xxresponses with bounded exponential backoff. Output records the retry policy, the exact latest-version rule, and separate match groups for every requested author form; initial-only groups remain explicitly ambiguous.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago Changed e6ea1759f69d
- 12d ago First seen · 188 lines · 45 tokens per session scan A 5962ae88c0fb
biorxiv-search is a skill published in the GitHub repository fmschulz/omics-skills (7 stars, last pushed 6d ago), licensed MIT. It adds 45 tokens to every session and 2,225 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 skills, from other repositories
imaging-data-commons
Query and download public cancer imaging data from NCI Imaging Data Commons. Invoke for any question about IDC collections, cancer imaging datasets, DICOM data access, radiology (CT, MR, PET) or pathology AI training sets, metadata queries, visualization, or license checks — even when the user doesn't explicitly…
genomic-intelligence
Predict regulatory features, gene structure, and expression directly from DNA sequence using Genomic Intelligence's hosted transformer DNA language models — no local GPU or model weights. Six tasks over a REST API and a hosted MCP server (keyless public demo): promoter regions, splice donor/acceptor sites, enhancer…
lab-hardware-cad
Design custom laboratory hardware as parametric build123d models and export fabrication-ready STEP, STL, and DXF files - microfluidic chips and molds, optomechanical mounts and breadboard adapters, cuvette and microplate holders, tube racks, animal-behavior rigs, and 3D-printed instrument fixtures. Use when a research…
pkpd-modeling
Pharmacokinetic and pharmacodynamic modelling and simulation - non-compartmental analysis, compartmental and population PK, PK/PD and exposure-response, TMDD, PBPK orientation, bioequivalence, allometric scaling and first-in-human dose, drug interaction prediction, and Bayesian therapeutic drug monitoring. Use when…
pptx
Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary)…
scikit-bio
Biological data toolkit. Sequence analysis, alignments, phylogenetic trees, diversity metrics (alpha/beta, UniFrac), ordination (PCoA), PERMANOVA, FASTA/Newick I/O, for microbiome analysis.