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 beita6969/ScienceClaw --skill crossref-searchgit clone --depth 1 https://github.com/beita6969/ScienceClawWrote 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/beita6969/scienceclaw/crossref-search)<a href="https://agentmods.dev/skills/beita6969/scienceclaw/crossref-search"><img src="https://agentmods.dev/badge/skills/beita6969/scienceclaw/crossref-search.svg" alt="Measured on agentmods" 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 | $0.00040 | $0.01274 |
| Opus 5 | $0.00020 | $0.00637 |
| Sonnet 5 | $0.00008 | $0.00255 |
| Haiku 4.5 | $0.00004 | $0.00127 |
Grade C, and why
crossref-search scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s "https://api.crossref.org/works/10.1038/nature12373" | python3 -c " Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
metadata: { "openclaw": { "emoji": "🔗", "requires": { "bins": ["curl"] } } } How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CrossRef Search
Academic metadata search and DOI resolution via the public CrossRef REST API.
When to Use
- Resolving a DOI to get full citation metadata
- Searching for papers by title, author, or keywords
- Looking up journal ISSN metadata or publisher info
- Finding citation counts and reference lists
- Retrieving funder information for grants/awards
When NOT to Use
- Full-text access or downloading papers (use publisher sites)
- Preprint search (use arxiv-search)
- Biomedical literature (use pubmed-search)
- Author profile pages or h-index (use openalex-search)
DOI Resolution
curl -s "https://api.crossref.org/works/10.1038/nature12373" | python3 -c "
import sys, json
data = json.load(sys.stdin)['message']
title = data.get('title', [''])[0]
authors = ', '.join(f\"{a.get('given','')} {a.get('family','')}\" for a in data.get('author', []))
journal = data.get('container-title', [''])[0]
cited = data.get('is-referenced-by-count', 0)
print(f'Title: {title}')
print(f'Authors: {authors}')
print(f'Journal: {journal} | Citations: {cited}')
"
Works Search
# Search by query terms
curl -s "https://api.crossref.org/works?query=machine+learning+protein+folding&rows=5&[email protected]" | python3 -c "
import sys, json
data = json.load(sys.stdin)['message']
for item in data['items']:
title = item.get('title', [''])[0]
doi = item.get('DOI', '')
cited = item.get('is-referenced-by-count', 0)
print(f'{title}')
print(f' DOI: {doi} | Citations: {cited}')
"
# Filter by date, type, and sort by citations
curl -s "https://api.crossref.org/works?query=CRISPR&filter=from-pub-date:2023-01-01,type:journal-article&rows=10&sort=is-referenced-by-count&order=desc&[email protected]"
# Search by author
curl -s "https://api.crossref.org/works?query.author=Jennifer+Doudna&rows=10&sort=published&order=desc&[email protected]"
Journal Lookup
# Search journals by title
curl -s "https://api.crossref.org/journals?query=nature+biotechnology&rows=5" | python3 -c "
import sys, json
for j in json.load(sys.stdin)['message']['items']:
print(f\"{j['title']} (ISSN: {', '.join(j.get('ISSN', []))})\")
"
# Get journal metadata by ISSN
curl -s "https://api.crossref.org/journals/0028-0836"
# Recent works from a journal
curl -s "https://api.crossref.org/journals/0028-0836/works?rows=5&sort=published&order=desc"
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 · 127 lines · 40 tokens per session scan C 72a5342f3841
crossref-search is a skill published in the GitHub repository beita6969/ScienceClaw (895 stars, last pushed 3mo ago), licensed MIT. It adds 40 tokens to every session and 1,274 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
biopython
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use…
scanpy
Standard single-cell RNA-seq analysis pipeline. Use for QC, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, differential expression, and visualization. Best for exploratory scRNA-seq analysis with established workflows. For deep learning models use scvi-tools; for data format questions use…
structure-prediction
Protein structure prediction from sequence. ESMFold-based, single GPU, no MSA needed. Predicts 3D structures with pLDDT confidence scores for drug discovery targets.
biomcp
Search and retrieve biomedical data - genes, variants, clinical trials, diagnostic tests, articles, drugs, diseases, pathways, proteins, adverse events, pharmacogenomics, and phenotype-disease matching. Use for gene function, variant pathogenicity, trials, diagnostics, drug safety, pathway context, disease workups…
biomcp-research
Do biomedical literature and variant research with the BioMCP CLI, and file what you learn about the tool itself as issues in the biomcp repo.
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.