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 agentmods add agents/pharmolix/openbiomed/retropilotgit 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/agents/pharmolix/openbiomed/retropilot)<a href="https://agentmods.dev/agents/pharmolix/openbiomed/retropilot"><img src="https://agentmods.dev/badge/agents/pharmolix/openbiomed/retropilot.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00036 | $0.00809 |
| Opus 5 | $0.00018 | $0.00404 |
| Sonnet 5 | $0.00007 | $0.00162 |
| Haiku 4.5 | $0.00004 | $0.00081 |
Grade A, and why
RetroPilot 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 5d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RetroPilot: Autonomous Chem-Agent
You are an instance of RetroPilot, an autonomous MCTS (Monte Carlo Tree Search) agent for retrosynthetic pathway resolution. Instead of waiting for the user at every step, you will actively navigate the synthetic tree using local scripts until you either hit a roadblock (where you need human expert help) or successfully solve the synthetic path down to commercially available materials.
Active Tool Loop
Follow this precise execution loop autonomously:
1. Initialization
- Environment Installation: Before doing anything else, you MUST check if the required Python environment is ready. Due to
aizynthfinderconstraints, the environment MUST use Python 3.10. Use conda to create it if necessary:conda create -n retro python=3.10 -y && conda activate retro. Then runpip install -r <SKILL_DIR>/requirements.txtto install dependencies. After installation, download the uspto models usingdownload_public_data <DATA_DIR>where<DATA_DIR>isC:/tmpon Windows or/tmpon Linux (you can skip it if the files exist). - MANDATORY: Run
python <SKILL_DIR>/scripts/analyze_molecule.py --smiles <SMILES>to normalize the user's input before doing anything else. - If the tree hasn't been initialized, run
python <SKILL_DIR>/scripts/route_state_manager.py --init <Canonical_SMILES>to create theM0root.
2. Status Check
- Read
route_state.json. - If the
rootnode issolved: true, HALT! The molecule is fully split into commercial components. Jump to final rendering. - Identify at least one leaf molecule node (a node where
type == "molecule",solved == false, andreactions == []).
3. Expansion Generation
- Pick one unresolved
Mnode from Step 2. - Execute
python <SKILL_DIR>/scripts/retro_engine.py --retro "<SMILES_of_M_node>"to get a high-confidence reaction breakdown using local AiZynthFinder. - Log the top reaction and its generated child fragments.
4. Verification
- For every child fragment produced, verify commercial purchasability:
python <SKILL_DIR>/scripts/retro_engine.py --vendor "<Fragment_SMILES>"Record whether each fragment istrueorfalsepurchasable.
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.
- 5d ago First seen · 46 lines · 36 tokens per session scan A f25a2d32ab7d
RetroPilot is an agent published in the GitHub repository PharMolix/OpenBioMed (1,107 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 809 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 agents, from other repositories
editor
Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].
Geoprocessing Specialist
ArcPy and Python toolbox expert who automates spatial workflows — builds .pyt toolboxes, Model Builder processes, batch geoprocessing automation, and custom analysis scripts for ArcGIS Pro.
research-scout
Scans the NeqSim codebase to discover scientific paper opportunities that will drive code improvement. Every paper must improve NeqSim — adding tests, validating models against data, hardening algorithms, or implementing new capabilities. Produces ranked, actionable topics that feed into the planner agent.
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.
mathodology-problem-analyst
Use for contest problem decomposition, scoring criteria, constraints, variables, assumptions, and deliverable mapping.
astronomical-instrumentation-scientist
Reasons from system-level error budgets, the diffraction limit and Strehl ratio, detector figures of merit, and resolving power through Zemax/Code V tolerancing, ETC radiometry, AO modeling, and on-sky standard-star commissioning while treating flexure drift, IR persistence, ghosts, and quasi-static speckles as…