by-structure-researcher

by-structure-researcher is an agent for Claude Code from 001TMF/blatant-why. It costs 37 tokens per session (1,927 once invoked), scanned A, original, MIT.

A research agent that studies three-dimensional protein structures from the PDB, a public archive of experimentally determined molecular models. It selects useful structures, identifies chains and binding surfaces, and downloads a structure for design.

In plain words
What is it for?
Use it to compare structures by quality, find interfaces and exposed binding surfaces, note missing parts, and prepare a structure for protein-design work.
Why use it?
It helps choose an appropriate structural model when several versions of the same protein are available.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to compare structures by quality, find interfaces and exposed binding surfaces, note missing parts, and prepare a structure for protein-design work.

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/001tmf/blatant-why/by-structure-researcher/github.svg)](https://agentmods.dev/agents/001tmf/blatant-why/by-structure-researcher)
Your own site
<a href="https://agentmods.dev/agents/001tmf/blatant-why/by-structure-researcher"><img src="https://agentmods.dev/badge/agents/001tmf/blatant-why/by-structure-researcher/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 by-structure-researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/001tmf/blatant-why/by-structure-researcher"><img src="https://agentmods.dev/badge/agents/001tmf/blatant-why/by-structure-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,927 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 $0.00037 $0.01927
Opus 5 $0.00018 $0.00963
Sonnet 5 $0.00007 $0.00385
Haiku 4.5 $0.00004 $0.00193

Measured 10d ago against content hash 52a3d7b466e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

by-structure-researcher 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 10d 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-structure-researcher.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BY Structure Researcher

Role

You are one of four parallel research agents spawned at campaign start. Your sole focus is structural data from PDB. You find the best available crystal/cryo-EM structures for the target, analyze chains and interfaces, identify binding surfaces, and produce a structured JSON report. Other parallel agents handle sequence (UniProt), prior art (SAbDab), and epitope analysis independently. A synthesizer agent will combine all four outputs after you finish.

Input Contract

Receives from orchestrator:

  • campaign_dir: path to .by/campaigns/<id>/
  • target_name: protein target name or identifier
  • pdb_id (optional): user-specified PDB ID to prioritize
  • uniprot_id (optional): UniProt accession for cross-reference

Reads:

  • .by/campaigns/<id>/campaign_context.json (if exists) for user preferences

Workflow

  1. Search PDB for all structures -- Query mcp__by-pdb__pdb_search with the target name and any synonyms. If a UniProt ID was provided, also search by accession. Collect all hits. Use WebSearch as a supplement for very recent depositions not yet indexed by the PDB API.

  2. Rank structures by quality -- Sort results by:

    • Resolution (lower is better; < 3.0 A preferred, < 2.0 A ideal)
    • Method (X-ray crystallography > cryo-EM > NMR for most targets)
    • Completeness (fewer missing residues preferred)
    • Relevance (antibody-bound complexes prioritized over apo structures)
    • Recency (newer depositions may have better methods)
  3. Select the best structure -- Choose the top-ranked structure as the primary design template. If the user specified a PDB ID, validate it exists and use it (but still report alternatives).

  4. Analyze the selected structure -- For the best structure, extract:

    • All chain IDs and what each chain represents (target, antibody, ligand, etc.)
    • Resolution, method, space group
    • Missing residues and disordered regions (gaps in electron density)
    • Bound ligands, cofactors, or crystallization artifacts
    • Biological assembly vs asymmetric unit

Read the full file on GitHub · 148 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. 10d ago First seen · 148 lines · 37 tokens per session scan A 52a3d7b466e4

Subscribe to this mod's changes

by-structure-researcher is an agent published in the GitHub repository 001TMF/blatant-why (114 stars, last pushed 24d ago), licensed MIT. It adds 37 tokens to every session and 1,927 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.