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 jvogan/motif --skill motif-for-claude-sciencegit clone --depth 1 https://github.com/jvogan/motifWrote 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/jvogan/motif/motif-for-claude-science)<a href="https://agentmods.dev/skills/jvogan/motif/motif-for-claude-science"><img src="https://agentmods.dev/badge/skills/jvogan/motif/motif-for-claude-science/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/jvogan/motif/motif-for-claude-science"><img src="https://agentmods.dev/badge/skills/jvogan/motif/motif-for-claude-science.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 | $0.00034 | $0.00448 |
| Opus 5.5 | $0.00014 | $0.00179 |
| Sonnet 5.5 | $0.00007 | $0.00090 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
motif-for-claude-science 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 1mo 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.
What it actually says
Motif for Claude Science
Use the Motif connector for interactive molecular-biology review when its tools are available.
Open a connected workbench
Call motif_open_workbench with exactly one of:
payload: a bounded Motif inventory/workspace object; orcontent: exact FASTA, GenBank, raw sequence, or Motif JSON text.
Include filename when it provides a useful format and provenance hint. For
ambiguous raw sequence, include molecule (dna, rna, or protein). Do not
send binary AB1/ABI content through this text tool.
Verify the returned motif.mcp.workbench.v1 schema, source name, record count,
and residue count. A successful call is not proof that the host mounted the
App: confirm the visible Motif identity and intended sequence in the frame.
Current Claude Science local/custom connector builds may not register Motif as
an artifact viewer. Use the viewer chooser only when Motif is actually listed;
Sequence viewer unavailable—showing as text is a generic host fallback, not
a Motif parse error.
Create the portable fallback
If the host does not mount MCP Apps, call
motif_create_workbench_artifact with the same input. It returns an embedded,
self-contained HTML resource and motif.mcp.artifact-export.v1 metadata with a
safe filename, byte count, and SHA-256. It does not write a file; save or open
the exact resource through the host and verify it visually. The opened
workbench is interactive, but it is an immutable snapshot rather than a live
MCP App.
Safety boundary
These tools validate and render data in an ephemeral workbench. They do not write a durable library, run external analysis software, expose a shell, or grant generic DOM/filesystem access. Database JSON and workspace ZIP created inside Motif are ordinary unencrypted user-owned checkpoints.
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.
- 1mo ago First seen · 46 lines · 34 tokens per session scan A 9b6682fcde32
motif-for-claude-science is a skill published in the GitHub repository jvogan/motif (48 stars, last pushed 6d ago), licensed MIT. It adds 34 tokens to every session and 448 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
biorxiv-search
Search bioRxiv biology preprints with natural language queries. Semantic search powered by Valyu.
sc-perturb-prep
Load when attaching cell-barcode → sgRNA assignments from a mapping TSV/CSV onto a Perturb-seq expression AnnData, producing standardised perturbation / sgRNA / target-gene obs columns. Skip when the AnnData already has perturbation labels (use sc-perturb); raw guide-calling from FASTQ (use upstream demuxlet /…
sc-perturb
Load when classifying perturbed vs non-perturbed cells in a Perturb-seq / CRISPR-screen scRNA AnnData via the pertpy Mixscape workflow. Skip when guide labels are not yet attached to the expression object (use sc-perturb-prep); in-silico KO predictions on unperturbed data (use sc-in-silico-perturbation).
neuropixels-analysis
Analyzes Neuropixels extracellular recordings end-to-end with SpikeInterface. Covers loading SpikeGLX/Open Ephys/NWB data, preprocessing, drift/motion correction, Kilosort4 (and CPU) spike sorting, quality metrics, and unit curation (threshold-based, model-based UnitRefine, and AI-assisted visual review). Use when…
onekgpd
Queries the 1000 Genomes Project dataset (3,202 whole-genome-sequenced individuals, GRCh38) at the level of individual participants. Use when a question is about individuals or variants in the 1000 Genomes Project cohort: which individuals carry variants matching specific criteria in a gene or region, which…
pydicom
Reads, inspects, writes, transforms, and preflights local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.