chembl-query

chembl-query is a skill for Claude Code, Codex from PharMolix/OpenBioMed. It costs 69 tokens per session (1,277 once invoked), scanned A, original, MIT.

A query tool for ChEMBL, a public database of drug-like molecules and their measured biological effects. It searches for compounds that affect a protein, activity data for a molecule, or drugs linked to a disease.

In plain words
What is it for?
Use it to find compounds acting on targets such as EGFR, review a molecule's known biological targets, or search for compounds associated with a disease indication.
Why use it?
It avoids manually combining scattered drug-discovery records when looking for known molecule activity. Results can be narrowed by identifiers such as a protein's UniProt ID, a molecule's SMILES structure, or activity measurements.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to find compounds acting on targets such as EGFR, review a molecule's known biological targets, or search for compounds associated with a disease indication.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pharmolix/openbiomed/chembl-query
About the project

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.

PharMolix/OpenBioMed · 1,106 stars · on GitHub

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 PharMolix/OpenBioMed --skill chembl-query
Clone the repo
git clone --depth 1 https://github.com/PharMolix/OpenBioMed

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 chembl-query

README.md
[![agentmods](https://agentmods.dev/badge/skills/pharmolix/openbiomed/chembl-query/github.svg)](https://agentmods.dev/skills/pharmolix/openbiomed/chembl-query)
Your own site
<a href="https://agentmods.dev/skills/pharmolix/openbiomed/chembl-query"><img src="https://agentmods.dev/badge/skills/pharmolix/openbiomed/chembl-query/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for chembl-query

Your own site · 80×15
<a href="https://agentmods.dev/skills/pharmolix/openbiomed/chembl-query"><img src="https://agentmods.dev/badge/skills/pharmolix/openbiomed/chembl-query.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,277 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00069 $0.01277
Opus 5 $0.00034 $0.00639
Sonnet 5 $0.00014 $0.00255
Haiku 4.5 $0.00007 $0.00128

Measured 11d ago against content hash aff17526a3c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

chembl-query 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 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (examples/basic_example.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.

skills/chembl-query/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ChEMBL Query

Query ChEMBL database for bioactivity data on drug-like compounds.

When to Use

  • Find compounds active against a protein target (target-based search)
  • Get bioactivity profile for a molecule (molecule-based search)
  • Find drugs for a disease indication (indication-based search)

Workflow

Use Case 1: Target-Based Compound Search

Find compounds with activity against a protein target.

from open_biomed.tools.tool_registry import TOOLS

tool = TOOLS["chembl_query"]

# Search by target name
results, _ = tool.run(
    query_type="target",
    target_name="EGFR",
    standard_type="IC50",
    standard_value_lte=100,  # nM
    limit=20
)

# Or search by UniProt ID
results, _ = tool.run(
    query_type="target",
    uniprot_id="P00533",
    standard_type="IC50",
    limit=20
)

Use Case 2: Molecule Bioactivity Profile

Get all known targets and activity data for a compound.

# Search by molecule name
results, _ = tool.run(
    query_type="molecule",
    molecule_name="imatinib",
    limit=50
)

# Or search by SMILES
results, _ = tool.run(
    query_type="molecule",
    smiles="CC(=O)Oc1ccccc1C(=O)O",
    limit=20
)

# Or search by ChEMBL ID
results, _ = tool.run(
    query_type="molecule",
    chembl_id="CHEMBL25",
    limit=20
)

Use Case 3: Disease/Indication-Based Drug Search

Find drugs studied for a specific disease.

# Find all drugs for diabetes
results, _ = tool.run(
    query_type="indication",
    disease="diabetes",
    limit=50
)

# Filter for approved drugs only (max_phase=4)
results, _ = tool.run(
    query_type="indication",
    disease="diabetes",
    max_phase=4,  # Approved drugs only
    limit=20
)

Expected Outputs

Query Type Output Fields
Target molecule_chembl_id, molecule_name, target_chembl_id, target_name, standard_type, standard_value, standard_units, pchembl_value
Molecule molecule_chembl_id, molecule_name, target_chembl_id, target_name, target_organism, standard_type, standard_value, standard_units, pchembl_value
Indication molecule_chembl_id, molecule_name, indication, max_phase_for_ind, phase_description

Read the full file on GitHub · 164 lines

Files

What ships with it

2 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. 11d ago First seen · 164 lines · 69 tokens per session scan A aff17526a3c1

Subscribe to this mod's changes

chembl-query is a skill published in the GitHub repository PharMolix/OpenBioMed (1,106 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 1,277 once invoked, about $0.0003 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.