binding-site-analysis

binding-site-analysis is a skill for Claude Code from K-Dense-AI/drug-discovery-agent-skills. It costs 128 tokens per session (1,878 once invoked), scanned A, original, MIT.

A protein-structure analysis guide for finding cavities, or pockets, where a drug-like molecule might bind. It checks whether a pocket is large and suitable enough for further docking or design work.

In plain words
What is it for?
Use it to detect and rank protein cavities, choose docking-box coordinates, and compare structures with and without a bound molecule to find induced-fit, allosteric, or cryptic pockets.
Why use it?
It helps avoid spending computing time screening against a cavity that is unlikely to bind a molecule. It also distinguishes ordinary pockets from hidden or shape-changing sites.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: built for openclaw.

Good fit Use it to detect and rank protein cavities, choose docking-box coordinates, and compare structures with and without a bound molecule to find induced-fit, allosteric, or cryptic pockets.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/k-dense-ai/drug-discovery-agent-skills/binding-site-analysis
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 K-Dense-AI/drug-discovery-agent-skills --skill binding-site-analysis
Clone the repo
git clone --depth 1 https://github.com/K-Dense-AI/drug-discovery-agent-skills

Made for: Claude Code.

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 binding-site-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/k-dense-ai/drug-discovery-agent-skills/binding-site-analysis/github.svg)](https://agentmods.dev/skills/k-dense-ai/drug-discovery-agent-skills/binding-site-analysis)
Your own site
<a href="https://agentmods.dev/skills/k-dense-ai/drug-discovery-agent-skills/binding-site-analysis"><img src="https://agentmods.dev/badge/skills/k-dense-ai/drug-discovery-agent-skills/binding-site-analysis/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 binding-site-analysis

Your own site · 80×15
<a href="https://agentmods.dev/skills/k-dense-ai/drug-discovery-agent-skills/binding-site-analysis"><img src="https://agentmods.dev/badge/skills/k-dense-ai/drug-discovery-agent-skills/binding-site-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 128 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,878 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 $0.00128 $0.01878
Opus 5 $0.00064 $0.00939
Sonnet 5 $0.00026 $0.00376
Haiku 4.5 $0.00013 $0.00188

Measured 12d ago against content hash 81990055c40e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

binding-site-analysis 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 12d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/pocket_box.py, scripts/pocket_report.py, scripts/site_compare.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/binding-site-analysis/SKILL.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Binding Site Analysis

The step before docking. Every docking skill in this bundle assumes you already know where the ligand goes and that the site is worth the compute — this is where those two assumptions get checked. fpocket runs in seconds and can save a month of screening against a pocket that was never going to bind anything.

Tool: fpocket, MIT, conda install -c conda-forge fpocket. Alpha-sphere cavity detection by Voronoi tessellation. Checked against: fpocket 4.x output format.

Read references/fpocket-output.md before parsing a run, references/druggability.md before calling a site druggable or not, and references/cryptic-and-allosteric.md when the answer is "no pocket" — that one is judgement, not syntax.

The three scripts

Script Answers
pocket_report.py Which cavities are there, and is any of them worth targeting?
pocket_box.py Where exactly does the docking box go?
site_compare.py Does a pocket appear only when something is bound?

Score and Druggability Score are different, and pocket1 is not the answer

This is the thing to get right. fpocket reports two numbers per cavity and they measure different things. Score ranks cavities geometrically, and pocket numbering follows it. Druggability Score is a logistic model trained to separate sites with known drug-like ligands from sites without — it is the one that answers "worth a campaign".

They disagree often:

python skills/binding-site-analysis/scripts/pocket_report.py rank --out-dir receptor_out
# fpocket ranks pocket 1 first by Score, but pocket 2 is the most druggable.
pocket  druggability  score  volume  apolar_fraction  verdict     reason
2       0.871         0.31   720.5   0.7143           druggable   resembles sites with known drug-like ligands
1       0.183         0.412  980.4   0.3172           poor        does not resemble a small-molecule binding site

Read the full file on GitHub · 151 lines

Files

What ships with it

6 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. 12d ago First seen · 151 lines · 128 tokens per session scan A 81990055c40e

Subscribe to this mod's changes

binding-site-analysis is a skill published in the GitHub repository K-Dense-AI/drug-discovery-agent-skills (28 stars, last pushed 5d ago), licensed MIT. It adds 128 tokens to every session and 1,878 once invoked, about $0.0006 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.