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 mutation-design-gfpgit 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/mutation-design-gfp)<a href="https://agentmods.dev/skills/pharmolix/openbiomed/mutation-design-gfp"><img src="https://agentmods.dev/badge/skills/pharmolix/openbiomed/mutation-design-gfp/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/mutation-design-gfp"><img src="https://agentmods.dev/badge/skills/pharmolix/openbiomed/mutation-design-gfp.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 | $0.00935 |
| Opus 5 | $0.00017 | $0.00467 |
| Sonnet 5 | $0.00007 | $0.00187 |
| Haiku 4.5 | $0.00003 | $0.00093 |
Grade A, and why
mutation-design-gfp 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
High-Fluorescence GFP Mutant Proposal
A skill performs automated multi-round optimization of Green Fluorescent Protein (GFP) to discover mutants with higher fluorescence intensity and higher diversity.
When to Use This Skill
- Design novel GFP mutants with improved fluorescence intensity.
- Run computational iterative directed evolution.
- Perform fast mutation search guided by an oracle model.
Example prompts:
- “Design GFP mutants with higher fluorescence.”
- “Run multi-round mutation optimization for GFP.”
- “Generate 96 GFP variants with improved fluorescence.”
Prerequisites
- Python 3.9+
- PyTorch
- NumPy / Pandas
- Protein sequence analysis tools
- Protein language model tools (ESM2)
Core Capabilities
This skill can:
- Download initial GFP sequences if they were not provided by users.
- Download and execute an in-silico oracle GFP prediction model.
- Generate controllable mutants within 4 point mutations for each round.
- Use ESM2 embeddings to represent GFP sequences.
- Optimize mutation proposals based on oracle feedback.
- Maintain population diversity using average pairwise Hamming distance.
- Perform multi-round optimization and return the best mutants.
Workflow
-
Download initial GFP sequences from
https://cloud.tsinghua.edu.cn/f/5e673c1db710466b828f/?dl=1and use them as the starting pool. -
Download the oracle GFP prediction model from
https://cloud.tsinghua.edu.cn/f/f655f79d7bb04a98a0bb/?dl=1, and the configuration file fromhttps://cloud.tsinghua.edu.cn/f/8a894bb4b41f4074b9b0/?dl=1. -
Execute code for oracle loading and scoring:
import torch
from omegaconf import OmegaConf
# ===== ORACLE MODEL LOADING =====
def load_oracle_model(ckpt_path, cfg_path):
with open(cfg_path, 'r') as fp:
cfg = OmegaConf.load(fp.name)
oracle = BaseCNN(**cfg.model.predictor)
state_dict = torch.load(ckpt_path)
oracle.load_state_dict(torch.load(ckpt_path))
oracle.eval()
# ===== ORACLE SCORING FUNCTION =====
def score_sequence(oracle, sequence: str) -> float:
results = oracle(sequence).detach()
return results.cpu().numpy()
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 · 110 lines · 34 tokens per session scan A 165bcdec834a
mutation-design-gfp is a skill published in the GitHub repository PharMolix/OpenBioMed (1,105 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 935 once invoked, about $0.0002 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
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…
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…