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 pubchem-querygit 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/pubchem-query)<a href="https://agentmods.dev/skills/pharmolix/openbiomed/pubchem-query"><img src="https://agentmods.dev/badge/skills/pharmolix/openbiomed/pubchem-query/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/pubchem-query"><img src="https://agentmods.dev/badge/skills/pharmolix/openbiomed/pubchem-query.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 | $0.00074 | $0.00761 |
| Opus 5 | $0.00037 | $0.00380 |
| Sonnet 5 | $0.00015 | $0.00152 |
| Haiku 4.5 | $0.00007 | $0.00076 |
Grade A, and why
pubchem-query 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 10d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PubChem Query
Query PubChem database for drug discovery and chemistry applications.
When to Use
- Convert drug name to molecular structure (SMILES, SDF)
- Find similar compounds for lead optimization
- Query bioactivity data against protein targets
- Get compounds active in specific assays
Workflow
Use Case 1: Name/ID to Structure
from open_biomed.tools.tool_registry import TOOLS
tool = TOOLS["molecule_name_request"]
molecules, _ = tool.run("aspirin")
mol = molecules[0]
print(f"SMILES: {mol.smiles}")
Use Case 2: Similarity Search
from open_biomed.data import Molecule
query = Molecule.from_smiles("CC(=O)Oc1ccccc1C(=O)O") # aspirin
tool = TOOLS["molecule_structure_request"]
molecules, _ = tool.run(molecule=query, threshold=0.85, max_records=10)
for mol in molecules:
print(mol.smiles)
Use Case 3: Bioactivity Query
tool = TOOLS["pubchem_bioactivity"]
# Query 1: Get assays where compound was active
results, _ = tool.run(query_type="compound", cid=2244, aids_type="active")
# Query 2: Get compounds active in an assay
results, _ = tool.run(query_type="assay", aid=1195, cids_type="active")
# Query 3: Get assays targeting a gene
results, _ = tool.run(query_type="target", gene_symbol="PTGS2")
Expected Outputs
| Query Type | Output |
|---|---|
| Name to Structure | Molecule object with SMILES, SDF file saved |
| Similarity Search | List of similar Molecule objects |
| Bioactivity (compound) | List of AIDs where compound was active/inactive |
| Bioactivity (assay) | List of CIDs active/inactive in the assay |
| Bioactivity (target) | List of AIDs targeting the gene |
Score Interpretation
| Similarity Threshold | Interpretation |
|---|---|
| > 0.90 | Very similar, likely same scaffold |
| 0.80-0.90 | Similar, potential analogs |
| 0.70-0.80 | Moderately similar, scaffold hops possible |
Error Handling
| Error | Solution |
|---|---|
| Compound not found | Try alternative names or SMILES |
| No similar compounds | Lower threshold (min 0.70) |
| No bioactivity data | Compound may not be tested; try related compounds |
| Timeout | Reduce max_records or retry |
What ships with it
2 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.
- 10d ago First seen · 102 lines · 74 tokens per session scan A ff761be39a45
pubchem-query is a skill published in the GitHub repository PharMolix/OpenBioMed (1,106 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 761 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 2026-08-30.
Other skills, from other repositories
chembl-bioactivity
Use this Skill to query ChEMBL for bioactivity data: target lookup, IC50/Ki retrieval, activity cliffs, SAR tables, and pChEMBL-normalized values.
librosa-audio
Music information retrieval with librosa: tempo, chroma, MFCCs, spectral features, onset detection, harmonic-percussive separation, pitch, and k-NN similarity search.
compound-profile
Generate comprehensive compound profiles including structure, properties, bioactivity, and development status. Use for drug analysis, SAR studies, and competitive profiling. Keywords: compound, drug, molecule, structure, SMILES, bioactivity, IC50.
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…