OpenBioMed is an agent platform and toolkit collection for biomedical research and drug discovery, covering areas such as molecular design, protein analysis, and single-cell data analysis. It is intended for researchers and provides the biomedical skills listed in the catalogue as workflows for Claude Code.
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 PharMolix/OpenBioMed --skill biomed-skill-routergit clone --depth 1 https://github.com/PharMolix/OpenBioMedWrote 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/pharmolix/openbiomed/biomed-skill-router)<a href="https://agentmods.dev/skills/pharmolix/openbiomed/biomed-skill-router"><img src="https://agentmods.dev/badge/skills/pharmolix/openbiomed/biomed-skill-router/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/pharmolix/openbiomed/biomed-skill-router"><img src="https://agentmods.dev/badge/skills/pharmolix/openbiomed/biomed-skill-router.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 | $0.00067 | $0.01991 |
| Opus 5 | $0.00034 | $0.00996 |
| Sonnet 5 | $0.00013 | $0.00398 |
| Haiku 4.5 | $0.00007 | $0.00199 |
Grade A, and why
biomed-skill-router 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 12d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BioMed Skill Router
Find the most suitable skill for your biomedical task by analyzing your request and matching it against available skills.
When to Use
- User describes a biomedical task but doesn't know which skill to use
- User wants to discover what skills are available for a particular domain
- User needs help choosing between multiple skills for a similar task
- User asks "What can I do with OpenBioMed?" or "Which skill should I use for X?"
How It Works
The agent analyzes the user's natural language request and determines the most suitable skill based on:
- Understanding the user's intent and goal
- Identifying what data/inputs the user has
- Matching against available skill capabilities
Available Skills
Biochemistry & Drug Discovery
| Skill | Description |
|---|---|
| drug-candidate-discovery | Generate diverse druggable molecules for a given target or disease using AI-powered drug discovery tools. |
| drug-lead-analysis | Analyze drug candidate molecules for drug-likeness (QED, Lipinski), ADMET properties, BBB penetration, and safety profiles. |
| target-based-lead-design | Generate diverse lead compounds for a specific protein target using structure-based drug design with MolCraft. |
| admet-prediction | Predict comprehensive ADMET properties (BBB penetration, side effects, Caco-2 permeability, half-life, LD50 toxicity). |
| retrosynthesis-planning | Expert-in-the-loop retrosynthetic planning workflow for breaking down target molecules into available starting materials. |
| drug-drug-interaction-analysis | Analyze potential drug-drug interactions (DDI) for up to 5 drugs using KEGG DDI database. |
| text-based-molecule-editing | Modify molecules based on natural language descriptions using MolT5/BioT5 models. |
Protein Analysis & Engineering
| Skill | Description |
|---|---|
| protein-mutation-analysis | Analyze protein mutations by retrieving protein data, explaining mutation effects with MutaPLM, and predicting structure. |
| mutation-design-aav | Design high-fitness and high-diversity mutants of AAV VP1 capsid protein. |
| mutation-design-gfp | Design high-fluorescence and high-diversity GFP mutants. |
| functional-protein-design | Generate functional protein sequences using CodeFP with Gene Ontology (GO) tag guidance. |
| similar-protein-retrieval | Retrieve proteins with similar structures or sequences from UniProt, PDB, and AFDB databases. |
| structure-prediction-boltz-2 | Predict protein complex structures and protein-ligand complexes with binding affinity using Boltz-2. |
| protein-structure-design-boltzgen | All-atom protein design using BoltzGen diffusion model for binder design and peptide design. |
| antibody-structure-prediction-tfold | Predict antibody/nanobody structures and antigen-antibody complex structures. |
| antibody-design-iggm | Epitope-conditioned de novo antibody design and affinity maturation. |
| binding-affinity-prediction-prodigy | Predict binding affinity scores for protein complexes using Prodigy. |
| protein-ligand-binding-analysis-plip | Analyze protein-ligand interactions in PDB structures using PLIP (Protein-Ligand Interaction Profiler). |
| protein-function-prediction | Predict protein function and properties from amino acid sequence using BioT5. |
| protein-subcellular-localization-prediction-biot5 | Predict protein subcellular localization from amino acid sequence using BioT5. |
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.
- 12d ago First seen · 152 lines · 67 tokens per session scan A 95c58ebfea3b
biomed-skill-router is a skill published in the GitHub repository PharMolix/OpenBioMed (1,105 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 1,991 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
Paper Writing Scenario Router
Scenario router for paper-writing tasks. Use after root triage to select paper submission, journal article, conference paper, grant proposal, lab report, group report, talk/workshop, or revision-response behavior.
tao-route-visual-changenet-samples
Routes the weakest VCN samples (output of tao-analyze-gaps-visual-changenet) into per-augmentation-module subsets based on each module's label eligibility. Use when the user asks to "route VCN gap samples", "split AOI gaps for k-NN mining and AnomalyGen", or prepare the immediate next step after DEFT gap analysis in a…
energy-expert
Expert-level energy systems, smart grids, renewable energy, power management, and energy analytics. Use when the user mentions smart grid, renewable, power, utilities, or SCADA, or when the task involves Energy Systems, Smart Grid Technology, Standards and Protocols, or Smart Grid Operations.
orchestrator
Load when routing a natural-language omics query to the correct domain skill across spatial / singlecell / genomics / proteomics / metabolomics / bulkrna domains via keyword / LLM / hybrid matching. Skip when the target skill is already known — invoke that skill directly.
uniprot
Access UniProt for protein sequence and annotation retrieval. Use this skill when: (1) Looking up protein sequences by accession, (2) Finding functional annotations, (3) Getting domain boundaries, (4) Finding homologs and variants, (5) Cross-referencing to PDB structures. For structure retrieval, use pdb. For sequence…
foldseek
Structure similarity search with Foldseek. Use this skill when: (1) Finding similar structures in PDB/AFDB databases, (2) Structural homology search, (3) Database queries by 3D structure, (4) Finding remote homologs not detected by sequence, (5) Clustering structures by similarity. For sequence similarity, use uniprot…