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 deep-researchgit 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/deep-research)<a href="https://agentmods.dev/skills/beita6969/scienceclaw/deep-research"><img src="https://agentmods.dev/badge/skills/beita6969/scienceclaw/deep-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/beita6969/scienceclaw/deep-research"><img src="https://agentmods.dev/badge/skills/beita6969/scienceclaw/deep-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00084 | $0.00975 |
| Opus 5 | $0.00042 | $0.00487 |
| Sonnet 5 | $0.00017 | $0.00195 |
| Haiku 4.5 | $0.00008 | $0.00097 |
Grade A, and why
deep-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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research
Autonomous multi-step research that searches multiple sources, reads full content, synthesizes findings, and produces a structured report.
When to Use
- User wants a thorough understanding of a topic (medical condition, drug, treatment, technology)
- User asks for a literature review or evidence summary
- User wants competitive or landscape analysis
- User wants to investigate an open question with multiple angles
- User asks "what does the research say about X"
Research Strategy
Step 1: Query Decomposition
Break the research question into 3–5 sub-questions covering:
- Core definition / mechanism
- Current evidence / state of the art
- Debates, limitations, or contradictions
- Clinical / practical implications (if medical)
- Recent developments (last 1–2 years)
Step 2: Multi-Source Search
Run searches across complementary sources using the available search tools:
# Use multi-search-engine for broad web coverage
# Use pubmed-search for peer-reviewed medical literature
# Use agent-browser to read full-text articles and retrieve content blocked by snippets
Search order:
- PubMed (if medical/biomedical topic) — for peer-reviewed evidence
- Multi-search-engine (Bing, Google, DuckDuckGo) — for guidelines, reviews, news
- Wikipedia — for background and structured overviews
- agent-browser — for reading full articles, PDFs, clinical guidelines
Step 3: Source Evaluation
For each source note:
- Publication type (RCT, meta-analysis, guideline, review, news)
- Date (prefer sources within 5 years for medical topics)
- Authority (journal impact, organization credibility)
- Relevance to the specific sub-question
Step 4: Synthesis
Synthesize across sources into a coherent narrative. Do NOT just concatenate summaries — identify:
- Points of consensus
- Contradictions or conflicting evidence
- Knowledge gaps
- Strongest evidence vs. weak/preliminary evidence
Step 5: Structured Report
Produce a well-formatted Markdown report with:
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 · 112 lines · 84 tokens per session scan A 0840297eac34
deep-research is a skill published in the GitHub repository beita6969/ScienceClaw (898 stars, last pushed 3mo ago), licensed MIT. It adds 84 tokens to every session and 975 once invoked, about $0.0004 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 2026-09-03.
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.