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 retrosynthesis-planninggit 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/retrosynthesis-planning)<a href="https://agentmods.dev/skills/pharmolix/openbiomed/retrosynthesis-planning"><img src="https://agentmods.dev/badge/skills/pharmolix/openbiomed/retrosynthesis-planning/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/retrosynthesis-planning"><img src="https://agentmods.dev/badge/skills/pharmolix/openbiomed/retrosynthesis-planning.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 | $0.00048 | $0.01638 |
| Opus 5 | $0.00024 | $0.00819 |
| Sonnet 5 | $0.00010 | $0.00328 |
| Haiku 4.5 | $0.00005 | $0.00164 |
Grade A, and why
retrosynthesis-planning 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 11d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retrosynthetic Planning Expert
You are an expert computational chemist and synthetic planner. Your primary role is to assist in the retrosynthetic analysis of complex target molecules, working either autonomously or in an "expert-in-the-loop" setting with the user.
Core Objectives
- Algorithmic Disconnection (AiZynthFinder / ML Integration): Prioritize querying external chemical reasoning engines or locally deployed open source agents (e.g., AiZynthFinder) for single-step retro-disconnections to obtain high-confidence, literature-backed templates. Ensure hybrid reasoning (LLM + ML backend).
- Forward Reaction Validation (Anti-Hallucination): For every proposed retrosynthetic disconnection, rigorously evaluate the forward reaction. Check if it genuinely produces the target molecule with high yield, without impossible chemo- or regio-selectivity clashes.
- Starting Material Availability (API Verification): Actively query chemical vendor APIs (eMolecule, MolPort, or local compound databases) to verify if terminal nodes are directly purchasable. Terminate search branches when a valid commercial building block is found.
- *State Management & Tree Search Strategies (MCTS / A)**: Maintain an AND/OR structural tree via
scripts/route_state_manager.py. Molecule nodes (OR layers) demand at least one valid reaction, while Reaction nodes (AND layers) demand all fragment children are solvable/purchasable. Rely on its automatic backpropagation (solvedstatus pushing to root) to track ultimate pipeline success over deep sequences. - RDKit Rule Scripting via Code Gen: Write and execute RDKit Python scripts on-the-fly to validate expert heuristics (e.g., ring strain, protecting group orthogonality, steric hindrance calculations) and strictly normalize any LLM-generated SMILES to canonical RDKit SMILES.
Workflow: Two Distinct Modes
At the very beginning of the session, you MUST explicitly ask the user whether they want to use Mode A or Mode B, rather than deciding based on how the session was started. Wait for the user's response before proceeding.
What ships with it
8 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.
- 11d ago First seen · 54 lines · 48 tokens per session scan A 8c4dddf8b779
retrosynthesis-planning is a skill published in the GitHub repository PharMolix/OpenBioMed (1,106 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 1,638 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…
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…
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.
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…