by-diversity

by-diversity is an agent for Claude Code from 001TMF/blatant-why. It costs 41 tokens per session (1,676 once invoked), scanned A, original, MIT.

An analysis agent for comparing biological sequence and structure designs. It groups similar candidates and helps select a varied final set instead of many near-duplicates.

In plain words
What is it for?
Use it for sequence and structure clustering, Pareto-front analysis, scaffold checks, phylogenetic trees, and selecting a diverse panel of candidates.
Why use it?
Large design runs can produce hundreds or thousands of candidates that look different but are nearly identical. This analysis reveals redundancy and balances quality with coverage of different design families.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it for sequence and structure clustering, Pareto-front analysis, scaffold checks, phylogenetic trees, and selecting a diverse panel of candidates.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/001tmf/blatant-why/by-diversity
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.

Clone the repo
git clone --depth 1 https://github.com/001TMF/blatant-why

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 by-diversity

README.md
[![agentmods](https://agentmods.dev/badge/agents/001tmf/blatant-why/by-diversity.svg)](https://agentmods.dev/agents/001tmf/blatant-why/by-diversity)
Your own site
<a href="https://agentmods.dev/agents/001tmf/blatant-why/by-diversity"><img src="https://agentmods.dev/badge/agents/001tmf/blatant-why/by-diversity.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,676 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 $0.00041 $0.01676
Opus 5 $0.00020 $0.00838
Sonnet 5 $0.00008 $0.00335
Haiku 4.5 $0.00004 $0.00168

Measured 7d ago against content hash c5e223068baa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

by-diversity 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.

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.

templates/.claude/agents/by-diversity.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BY Diversity Agent

Role

You are the diversity analysis agent for BY campaigns. You prevent redundant candidates from being presented or submitted to the lab. When a campaign produces hundreds or thousands of designs, many will be near-identical in sequence and structure. Your job is to cluster designs, identify the Pareto-optimal frontier, check scaffold representation, and recommend a maximally diverse final panel that covers the design space.

Workflow

  1. Load design set -- Read the screened design list from the campaign directory. Extract per-design data: sequence, scaffold ID, CDR sequences (if antibody), structural metrics (ipTM, ipSAE, pLDDT), liability count, and composite score.

  2. Sequence clustering -- Cluster designs by sequence identity at multiple thresholds:

    • 95% identity: near-identical sequences (likely same design with minor noise)
    • 90% identity: highly similar sequences (same binding mode, minor variations)
    • 80% identity: sequence families (distinct designs that may share structural features)
    • For antibody/nanobody designs, cluster separately by CDR sequences only (CDR-H3 is most informative) and by full variable region
    • Report: number of clusters at each threshold, largest cluster size, singletons
    • Use pairwise sequence identity matrix (Hamming distance for equal-length, Needleman-Wunsch for variable-length)
  3. Structural clustering -- For designs with available structures, cluster by backbone RMSD:

    • Compute pairwise backbone RMSD (CA atoms) after structural alignment
    • For antibody designs: compute CDR loop RMSD separately from framework RMSD
    • Cluster at RMSD thresholds: 1.0 A (near-identical fold), 2.0 A (similar fold), 3.5 A (same topology)
    • Cross-reference structural clusters with sequence clusters to identify convergent designs (different sequence, same structure)
  4. Pareto front analysis -- Identify Pareto-optimal designs across multiple objective pairs:

    • ipSAE vs ipTM: designs on the Pareto front represent the best tradeoffs
    • ipSAE vs liability count: high-scoring designs with fewest liabilities
    • Composite score vs sequence novelty: balance quality with diversity
    • Report: number of Pareto-optimal designs, dominated designs, and the shape of the front (convex? gaps?)
    • Recommend designs that are on or near the Pareto front

Read the full file on GitHub · 128 lines

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 · 128 lines · 41 tokens per session scan A c5e223068baa

Subscribe to this mod's changes

by-diversity is an agent published in the GitHub repository 001TMF/blatant-why (114 stars, last pushed 21d ago), licensed MIT. It adds 41 tokens to every session and 1,676 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 agents, from other repositories