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 skills/kdevos12/alkyl/openbabelnpx skills add Kdevos12/ALKYL --skill openbabelgit clone --depth 1 https://github.com/Kdevos12/ALKYLWhat 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 | $0.00048 | $0.00937 |
| Opus 5 | $0.00024 | $0.00468 |
| Sonnet 5 | $0.00010 | $0.00187 |
| Haiku 4.5 | $0.00005 | $0.00094 |
Grade A, and why
openbabel 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 2d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenBabel — Chemical Format Conversion & Manipulation
OpenBabel 3.1.1. Two interfaces: pybel (Python API, high-level) and obabel (CLI, batch processing). Supports 146 formats, MMFF94/UFF/GAFF force fields.
When to Use This Skill
- Converting between molecular formats: SMILES ↔ SDF ↔ MOL2 ↔ PDB ↔ InChI ↔ CIF ↔ XYZ ↔ 100+ others
- Generating 3D coordinates from SMILES (quick alternative to RDKit ETKDGv3)
- Conformer searching with force field scoring
- Protonation state at given pH
- Computing molecular descriptors (LogP, TPSA, MR) and fingerprints
- SMARTS substructure filtering of large libraries
- Batch library processing (split, deduplicate, filter)
- Converting formats unsupported by RDKit (CIF, VASP POSCAR, XYZ, etc.)
Quick Start
from openbabel import pybel
# Read SMILES → generate 3D → write SDF
mol = pybel.readstring('smi', 'CC(=O)Oc1ccccc1C(=O)O') # aspirin
mol.make3D(forcefield='mmff94', steps=500)
mol.write('sdf', 'aspirin.sdf', overwrite=True)
# Read SDF → SMILES
for mol in pybel.readfile('sdf', 'library.sdf'):
print(mol.write('can').strip()) # canonical SMILES
Router — What to Read
| Task | Reference |
|---|---|
| pybel Python API: read, write, 3D, descriptors, fingerprints, SMARTS | references/pybel-python.md |
| obabel CLI: conversion, --gen3d, --conformer, filtering, pH, split | references/obabel-cli.md |
| Format codes, fingerprint types, descriptors, Tanimoto | references/formats-fingerprints.md |
Two Interfaces
| pybel | obabel CLI | |
|---|---|---|
| Use case | Scripted workflows, per-molecule logic | Batch conversion, library filtering |
| Import | from openbabel import pybel |
subprocess or shell |
| Speed | Moderate | Fast (C++ core) |
| Flexibility | High (per-atom access) | Moderate (flags) |
Installation
conda install -c conda-forge openbabel # recommended (includes C++ libs)
pip install openbabel # Linux/macOS only
# Verify
python -c "from openbabel import pybel; print(pybel.readstring('smi','C').molwt)"
obabel --version
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.
- 2d ago First seen · 92 lines · 48 tokens per session scan A a75518a7beec
openbabel is a skill published in the GitHub repository Kdevos12/ALKYL (6 stars, last pushed 5mo ago), licensed MIT. It adds 48 tokens to every session and 937 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 2026-08-31.
Other skills, from other repositories
design-mcp-server
Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.
add-tool
Scaffold a new MCP tool definition. Use when the user asks to add a tool, create a new tool, or implement a new capability for the server.
api-linter
MCP definition linter rules reference. Use when bun run lint:mcp or bun run devcheck reports a lint error or warning (format-parity, schema-is-object, name-format, server-json-, etc.) and you need to understand the rule, its severity, and how to fix it. Every rule ID the linter emits has an entry in this doc.
api-context
Canonical reference for the unified Context object passed to every tool and resource handler in @cyanheads/mcp-ts-core. Covers the full interface, its RequestContext base, all sub-APIs (ctx.log, ctx.state, ctx.requestInput, ctx.inputs, ctx.enrich, ctx.content), and when to use each.
api-canvas
DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…
api-errors
McpError constructor, JsonRpcErrorCode reference, and error handling patterns for @cyanheads/mcp-ts-core. Use when looking up error codes, understanding where errors should be thrown vs. caught, or using ErrorHandler.tryCatch in services.