chem-bond-dissociation

chem-bond-dissociation is a skill for Claude Code, Codex from learningmatter-mit/AtomisticSkills. It costs 39 tokens per session (2,996 once invoked), scanned A, original, MIT.

A tool for estimating the energy needed to break every single bond in a molecule, using machine-learning models and fragmented molecular structures. It can calculate homolytic breaking into radicals and heterolytic breaking into charged fragments.

In plain words
What is it for?
Use it to identify weaker bonds and estimate homolytic or heterolytic bond dissociation energies for studies of metabolism, fuel oxidation, electrolyte stability, or polymer breakdown.
Why use it?
It avoids calculating each bond-breaking case by hand and compares the stability of the intact molecule with its fragments.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to identify weaker bonds and estimate homolytic or heterolytic bond…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/learningmatter-mit/atomisticskills/chem-bond-dissociation
Install

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.

Any agent
npx skills add learningmatter-mit/AtomisticSkills --skill chem-bond-dissociation
Clone the repo
git clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for chem-bond-dissociation

README.md
[![agentmods](https://agentmods.dev/badge/skills/learningmatter-mit/atomisticskills/chem-bond-dissociation.svg)](https://agentmods.dev/skills/learningmatter-mit/atomisticskills/chem-bond-dissociation)
Your own site
<a href="https://agentmods.dev/skills/learningmatter-mit/atomisticskills/chem-bond-dissociation"><img src="https://agentmods.dev/badge/skills/learningmatter-mit/atomisticskills/chem-bond-dissociation.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,996 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00039 $0.02996
Opus 5 $0.00019 $0.01498
Sonnet 5 $0.00008 $0.00599
Haiku 4.5 $0.00004 $0.00300

Measured 7d ago against content hash 62bf91e0756f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

chem-bond-dissociation 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.

The scan reads SKILL.md. This mod also ships 2 executable files (examples/methanol_uma_omol_both/plot.py, scripts/calculate_bde.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/chem-bond-dissociation/SKILL.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bond Dissociation Energy Skill

Goal

Calculate the homolytic and/or heterolytic bond dissociation energy (BDE) for each single bond in a molecule using Machine Learning Interatomic Potentials (MLIPs).

Homolytic BDE (radical fragments): $$\text{BDE}_\text{homo}(A{-}B) = E(A\bullet) + E(B\bullet) - E(A{-}B)$$

Heterolytic BDE (ionic fragments, minimum over both polarity variants): $$\text{BDE}_\text{hetero}(A{-}B) = \min!\bigl(E(A^+)+E(B^-),; E(A^-)+E(B^+)\bigr) - E(A{-}B)$$

[!IMPORTANT] This skill computes BDEs by relaxing both the intact molecule and fragments with an MLIP. For purpose-trained GNN models that predict BDE directly from SMILES (MAE ~0.6 kcal/mol), consider ALFABET or BonDNet instead.

Background

BDE is a fundamental thermodynamic quantity that determines:

  • Drug metabolism: CYP450 enzymes abstract H from the weakest C–H bond
  • Electrolyte stability: Which bonds break first under electrochemical voltage
  • Combustion chemistry: Rate-determining bond-breaking steps in fuel oxidation
  • Polymer degradation: Weakest links in polymer backbone chains

A 2024 study (Zubatyuk et al., JCTC) demonstrated that MACE potentials achieve BDE RMSE of 1.37 kcal/mol for aliphatic C–H bonds in drug-like molecules, outperforming semi-empirical methods and ALFABET for BDE ranking.

1. Prerequisites

  • Conda Environment: mace-agent (includes RDKit, ASE, and MACE)
  • Input: SMILES string or structure file (.sdf, .mol2)
  • RDKit: Required for bond identification and molecular fragmentation

2. Choosing a Foundation Potential

Refer to the foundation-potentials skill for model selection.

[!IMPORTANT] Model requirements by cleavage mode:

Mode Recommended model supports_charge_spin Validated?
homolytic MACE-OFF23-small/medium/large Not required
heterolytic or both MACE-OMOL-extra-large (env: mace-agent) ✅ Required
heterolytic or both MACE-MH-1 with omol head (env: mace-agent) ✅ Required
heterolytic or both FairChem uma-s-1p1 with --task_name omol (env: fairchem-agent) ✅ Required

Setting charge/spin on MACE models: use atoms.info["charge"] and atoms.info["spin"] (the calculator's default info_keys maps "charge"total_charge / "spin"total_spin). Both MACE-OMOL and MACE-MH use joint_embedding to condition the network on these scalars.

If you request --cleavage both with a model that does not support charge/spin, the skill will log a warning and silently fall back to homolytic-only. Using --cleavage heterolytic with an unsupported model raises an error.

Note on single-atom fragments: When a bond produces a bare H (or other single atom), heterolytic BDE is automatically skipped — neither MACE nor FairChem UMA has signed single-atom energies (only neutral H, C, N, O… are in the reference tables).

Read the full file on GitHub · 228 lines

Files

What ships with it

57 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.

Changes

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.

  1. 7d ago First seen · 228 lines · 39 tokens per session scan A 62bf91e0756f

Subscribe to this mod's changes

chem-bond-dissociation is a skill published in the GitHub repository learningmatter-mit/AtomisticSkills (161 stars, last pushed 3d ago), licensed MIT. It adds 39 tokens to every session and 2,996 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.

Related

Other skills, from other repositories

hypogenic

Automated LLM-driven hypothesis generation and testing on tabular datasets. Use when you want to systematically explore hypotheses about patterns in empirical data (e.g., deception detection, content analysis). Combines literature insights with data-driven hypothesis testing. For manual hypothesis formulation use…

synthetic-sciences/openscience · 69 tokens

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…

synthetic-sciences/openscience · 67 tokens

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…

synthetic-sciences/openscience · 78 tokens

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…

synthetic-sciences/openscience · 80 tokens

molfeat

Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.

synthetic-sciences/openscience · 47 tokens

pytdc

Therapeutics Data Commons. AI-ready drug discovery datasets (ADME, toxicity, DTI), benchmarks, scaffold splits, molecular oracles, for therapeutic ML and pharmacological prediction.

synthetic-sciences/openscience · 41 tokens