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 text-based-molecule-editinggit 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/text-based-molecule-editing)<a href="https://agentmods.dev/skills/pharmolix/openbiomed/text-based-molecule-editing"><img src="https://agentmods.dev/badge/skills/pharmolix/openbiomed/text-based-molecule-editing/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/text-based-molecule-editing"><img src="https://agentmods.dev/badge/skills/pharmolix/openbiomed/text-based-molecule-editing.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 | $0.00128 | $0.01468 |
| Opus 5 | $0.00064 | $0.00734 |
| Sonnet 5 | $0.00026 | $0.00294 |
| Haiku 4.5 | $0.00013 | $0.00147 |
Grade A, and why
text-based-molecule-editing 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Text-Based Molecule Editing
Modify molecular structures guided by natural language property descriptions.
When to Use
- User wants to optimize a molecule for specific properties (solubility, binding, drug-likeness)
- User provides a molecule and requests property-based modifications
- User wants to explore structural variants guided by text descriptions
Workflow
Step 1: Prepare Input Molecule
from open_biomed.data import Molecule
from open_biomed.tools.tool_registry import TOOLS
# Option A: From molecule name (queries PubChem)
tool = TOOLS["molecule_name_request"]
result, _ = tool.run(accession="aspirin")
molecule = result[0]
# Option B: From SMILES directly
molecule = Molecule.from_smiles("CC(=O)Oc1ccccc1C(=O)O")
Step 2: Calculate Baseline Properties (Optional)
qed_tool = TOOLS["molecule_qed"]
logp_tool = TOOLS["molecule_logp"]
sa_tool = TOOLS["molecule_sa"]
qed, _ = qed_tool.run(molecule=molecule)
logp, _ = logp_tool.run(molecule=molecule)
sa, _ = sa_tool.run(molecule=molecule)
Step 3: Run Text-Based Editing
from open_biomed.core.pipeline import InferencePipeline
from open_biomed.data import Text
pipeline = InferencePipeline(
task="text_based_molecule_editing",
model="molt5",
model_ckpt="./checkpoints/server/text_based_molecule_editing_biot5.ckpt",
device="cuda:0"
)
outputs = pipeline.run(
molecule=molecule,
text=Text.from_str("This molecule should be more soluble in water"),
)
edited_molecule = outputs[0][0]
Step 4: Compare Properties
qed_new, _ = qed_tool.run(molecule=edited_molecule)
logp_new, _ = logp_tool.run(molecule=edited_molecule)
print(f"Original SMILES: {molecule.smiles}")
print(f"Edited SMILES: {edited_molecule.smiles}")
print(f"LogP change: {logp[0]:.2f} → {logp_new[0]:.2f}")
Expected Outputs
| Step | Output | Description |
|---|---|---|
| Step 1 | Molecule object |
Input molecule with SMILES |
| Step 2 | float values |
QED (0-1), LogP, SA scores |
| Step 3 | Molecule object |
Edited molecule with new structure |
| Step 4 | Comparison | Before/after property summary |
What ships with it
3 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 · 184 lines · 128 tokens per session scan A 47a0c7246121
text-based-molecule-editing is a skill published in the GitHub repository PharMolix/OpenBioMed (1,106 stars, last pushed 1mo ago), licensed MIT. It adds 128 tokens to every session and 1,468 once invoked, about $0.0006 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
analyze
Evaluate and characterize a set of generated SMILES across multiple quality dimensions (physicochemical, druglikeness, scaffold diversity, structural alerts, similarity to reference). Use after sampling or RL to assess molecule quality.
rl
Run reinforcement learning with REINVENT4 to optimize molecular properties via a scoring function. Use when the user wants to optimize, score, or run RL/staged learning for molecule design.
custom-component
Generate a custom scoring component plugin (comp.py) for REINVENT4 RL. Use when the user needs a scoring function not available as a built-in component.
validate
Validate REINVENT4 input SMILES files and TOML configs before launching jobs. Use when the user wants to check, validate, or verify their inputs.
transfer-learn
Fine-tune a REINVENT4 prior model on a focused SMILES dataset (transfer learning). Use when the user wants to train, fine-tune, or adapt a model to a specific chemical series.
job-status
Check the status of a running or completed REINVENT4 job (TL or RL). Use when the user asks about job progress, status, or results.