chem-hazard-toxicity

chem-hazard-toxicity is a skill for Claude Code, Codex from learningmatter-mit/AtomisticSkills. It costs 34 tokens per session (755 once invoked), scanned A, original, MIT.

A tool for extracting chemical safety and toxicity information from PubChem, a public database of chemical information, using a compound's identifier. It reports hazard classifications and animal toxicity data such as LD50 or LC50 values.

In plain words
What is it for?
Use it to create a safety profile for a compound, review GHS hazard information, or perform the provided acute oral toxicity triage.
Why use it?
It gathers safety records and helps compare hazard statements with acute oral toxicity categories.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/learningmatter-mit/atomisticskills/chem-hazard-toxicity
Any agent
npx skills add learningmatter-mit/AtomisticSkills --skill chem-hazard-toxicity
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-hazard-toxicity

README.md
[![agentmods](https://agentmods.dev/badge/skills/learningmatter-mit/atomisticskills/chem-hazard-toxicity.svg)](https://agentmods.dev/skills/learningmatter-mit/atomisticskills/chem-hazard-toxicity)
Your own site
<a href="https://agentmods.dev/skills/learningmatter-mit/atomisticskills/chem-hazard-toxicity"><img src="https://agentmods.dev/badge/skills/learningmatter-mit/atomisticskills/chem-hazard-toxicity.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 755 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00034 $0.00755
Opus 5 $0.00017 $0.00378
Sonnet 5 $0.00007 $0.00151
Haiku 4.5 $0.00003 $0.00076

Measured 6d ago against content hash 268541dc69fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

chem-hazard-toxicity 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 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/get_safety_data.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-hazard-toxicity/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chemical Hazard and Toxicity Profiling

Goal

To programmatically extract critical safety information from the PubChem PUG-VIEW API. This skill pulls GHS Classifications, Hazard Classes, and Toxicological properties (like LD50/LC50 experimental animal records) for a given compound based on its CID, and performs GHS Acute Toxicity Category assignment and hazard statement consistency analysis.

Instructions

1. Extract Safety Profile by CID

Provide the precise CID of the molecule to query safety metadata.

# Env: base-agent
python .agents/skills/chem-hazard-toxicity/scripts/get_safety_data.py \
  --cid 2519 \
  --outdir research/caffeine_safety \
  --output safety_caffeine.json

2. GHS Acute Oral Toxicity Triage Helper

Use --triage to extract consensus GHS statements ($\ge 50%$), lowest rat oral LD50, GHS acute oral category (1–5 or unclassified), and check oral hazard code consistency:

# Env: base-agent
python .agents/skills/chem-hazard-toxicity/scripts/get_safety_data.py \
  --cid 2519 \
  --triage \
  --outdir research/caffeine_safety \
  --output triage_caffeine.json

Python API Integration

Import helper functions directly into python scripts:

from scripts.get_safety_data import (
    extract_consensus_ghs_codes,
    extract_lowest_rat_oral_ld50,
    assign_acute_oral_category,
    check_oral_code_consistency,
    profile_compound,
)

profile = profile_compound(2519, threshold_percent=50.0)
# Returns dict with cid, consensus_ghs_codes, oral_rat_ld50_mg_kg, oral_rat_ld50_evidence, acute_oral_category, ghs_oral_code_consistent

GHS Category & Code Consistency Rule:

  • Category 1 ($\le 5\text{ mg/kg}$) & Category 2 ($5 < \text{LD}_{50} \le 50\text{ mg/kg}$) $\rightarrow$ expected GHS oral code H300 (Fatal if swallowed).
  • Category 3 ($50 < \text{LD}_{50} \le 300\text{ mg/kg}$) $\rightarrow$ H301 (Toxic if swallowed).
  • Category 4 ($300 < \text{LD}_{50} \le 2000\text{ mg/kg}$) $\rightarrow$ H302 (Harmful if swallowed).
  • Category 5 ($2000 < \text{LD}_{50} \le 5000\text{ mg/kg}$) $\rightarrow$ H303 (May be harmful if swallowed).
  • unclassified ($> 5000\text{ mg/kg}$) $\rightarrow$ empty set ({}).

Read the full file on GitHub · 69 lines

Files

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.

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. 6d ago First seen · 69 lines · 34 tokens per session scan A 268541dc69fd

Subscribe to this mod's changes

chem-hazard-toxicity is a skill published in the GitHub repository learningmatter-mit/AtomisticSkills (160 stars, last pushed 2d ago), licensed MIT. It adds 34 tokens to every session and 755 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

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

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.

synthetic-sciences/openscience · 44 tokens

binding-affinity

Hybrid ML + physics binding affinity prediction. Empirical scoring, MM/GBSA rescoring, multi-method consensus, and batch virtual screening for protein-ligand complexes.

synthetic-sciences/openscience · 38 tokens

molecular-optimization

Iterative lead optimization with analyze-reason-generate-verify-evaluate loop. Paper-backed (MT-Mol, DrugR, MultiMol).

synthetic-sciences/openscience · 34 tokens