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 learningmatter-mit/AtomisticSkills --skill drug-retrosynthesisgit clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkillsWrote 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/learningmatter-mit/atomisticskills/drug-retrosynthesis)<a href="https://agentmods.dev/skills/learningmatter-mit/atomisticskills/drug-retrosynthesis"><img src="https://agentmods.dev/badge/skills/learningmatter-mit/atomisticskills/drug-retrosynthesis.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 5.1 | $0.00022 | $0.00639 |
| Opus 5 | $0.00011 | $0.00319 |
| Sonnet 5 | $0.00004 | $0.00128 |
| Haiku 4.5 | $0.00002 | $0.00064 |
Grade A, and why
drug-retrosynthesis 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 7d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
drug-retrosynthesis
Goal
To predict the retrosynthetic pathways and synthetic accessibility of novel small molecules (such as undocumented fluorinated gases) using the state-of-the-art transformer models provided by IBM RXN for Chemistry.
Instructions
1. Identify Target Molecule
Ensure you have the valid canonical SMILES string for the target material or chemical you wish to synthesize.
2. Set Up the IBM RXN Environment
Because IBM RXN is a cloud-hosted API, you must have an API Key.
- Sign up for a free IBM RXN account at https://rxn.res.ibm.com/
- Generate an API Key in your user profile.
- Export the key in your terminal session before running the skill script:
export RXN_API_KEY="your-api-key-here"
3. Run Retrosynthesis Evaluation
Use the wrapper script to submit the SMILES string to the IBM RXN API. The script will poll the server and return the predicted pathway and a confidence score for synthetic feasibility.
# Env: drugdisc-agent
python .agents/skills/drug-retrosynthesis/scripts/evaluate_ibm_rxn.py "target_smiles" --steps 3
Examples
Evaluating the synthetic pathway for a fluorinated gas analog (e.g., 2,3,3,3-tetrafluoropropene: FC(F)(F)C(F)=C):
# Env: drugdisc-agent
export RXN_API_KEY="api-key-here"
python .agents/skills/drug-retrosynthesis/scripts/evaluate_ibm_rxn.py "FC(F)(F)C(F)=C" --steps 3
Constraints
- Environments: Requires the
drugdisc-agentconda environment. - Dependencies: The script relies on the
rxn4chemistrypython library (pip install rxn4chemistry). If not installed, the script will gracefully exit with instructions. - Rate Limits: The IBM RXN free tier has API limits. Do not use this in a high-throughput loop for thousands of molecules without a premium tier.
- Sourcing Constraints: This tool does not directly check commercial availability of the proposed precursors. You must manually verify if the starting materials proposed by IBM RXN are commercially available.
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.
- 7d ago First seen · 58 lines · 22 tokens per session scan A 056f47af559e
drug-retrosynthesis is a skill published in the GitHub repository learningmatter-mit/AtomisticSkills (161 stars, last pushed 3d ago), licensed MIT. It adds 22 tokens to every session and 639 once invoked, about $0.0001 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
datamol
Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters…
deepchem
Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first…
rdkit
Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions. For standard workflows with simpler interface, use datamol (wrapper around RDKit). Use rdkit for advanced control, custom…
binding-affinity
Hybrid ML + physics binding affinity prediction. Empirical scoring, MM/GBSA rescoring, multi-method consensus, and batch virtual screening for protein-ligand complexes.
drug-design
End-to-end drug discovery pipeline orchestration. Deterministic Python script that auto-chains structure prediction, pocket detection, de novo design, docking, scoring, and ADMET filtering into reproducible workflows.
molecular-optimization
Iterative lead optimization with analyze-reason-generate-verify-evaluate loop. Paper-backed (MT-Mol, DrugR, MultiMol).