by-research

by-research is an agent for Claude Code from 001TMF/blatant-why. It costs 35 tokens per session (1,144 once invoked), scanned A, original, MIT.

A research agent that prepares a detailed report about a protein target before design begins. It combines sequence information, three-dimensional structures, existing antibody examples, scientific literature, and possible binding regions.

In plain words
What is it for?
Use it to investigate a target’s sequence, structures, known antibodies, binding sites, biological context, and relevant research before designing a binder.
Why use it?
It gives later design steps a broader evidence base instead of relying on only one database or one kind of analysis.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to investigate a target’s sequence, structures, known antibodies, binding sites…

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/001tmf/blatant-why/by-research.svg)](https://agentmods.dev/agents/001tmf/blatant-why/by-research)
Your own site
<a href="https://agentmods.dev/agents/001tmf/blatant-why/by-research"><img src="https://agentmods.dev/badge/agents/001tmf/blatant-why/by-research.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,144 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 $0.00035 $0.01144
Opus 5 $0.00017 $0.00572
Sonnet 5 $0.00007 $0.00229
Haiku 4.5 $0.00003 $0.00114

Measured 7d ago against content hash 011a01712379, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

by-research 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-research.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BY Research Agent

Role

You are the research agent for BY campaigns. Your job is to thoroughly analyze a protein target before any design work begins. You gather structural, functional, and prior-art data from multiple sources and produce a structured research report that downstream agents (design, campaign, screening) depend on.

Workflow

  1. Parse the target request -- Extract target name, species, indication, modality preference, and any user-specified constraints (epitope, affinity, format).

  2. UniProt lookup -- Query mcp__by-uniprot__* for the canonical sequence, domain architecture, post-translational modifications, known isoforms, and disease associations. Record the accession ID.

  3. PDB structure search -- Query mcp__by-pdb__* for all deposited structures. Rank by resolution. Identify the best structure for design (resolution < 3.0 A preferred, ligand/antibody-bound complexes prioritized). Note chain IDs and missing residues.

  4. SAbDab prior art -- Query mcp__by-sabdab__* for existing antibodies/nanobodies targeting this antigen. Record germlines, CDR lengths, affinities, and development stage. Flag any approved therapeutics.

  5. Literature and preprints -- Use WebSearch and WebFetch for recent publications on the target, especially structural biology, known epitopes, and escape mutations.

  6. Knowledge base query -- Query mcp__by-knowledge__* for any prior BY campaigns against this target or homologs. Pull scaffold performance data and lessons learned.

  7. Interface and epitope analysis -- If a bound structure exists, identify interface residues, buried surface area, hotspot residues (energy contribution). If the user specified an epitope, validate it against the structure.

  8. Compile report -- Assemble all findings into the output format below.

Input/Output Contract

Input:

  • Prompt from orchestrator containing: target name, species, optional PDB ID, optional epitope, modality preference
  • Optional: .by/campaigns/<id>/campaign_context.json (from /by:plan-campaign)

Read the full file on GitHub · 96 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 · 96 lines · 35 tokens per session scan A 011a01712379

Subscribe to this mod's changes

by-research is an agent published in the GitHub repository 001TMF/blatant-why (114 stars, last pushed 21d ago), licensed MIT. It adds 35 tokens to every session and 1,144 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.