by-formatter

by-formatter is an agent for Claude Code from 001TMF/blatant-why. It costs 48 tokens per session (2,152 once invoked), scanned A, original, MIT.

A formatting agent for BY campaigns, which are workflows for designing biological sequences. It turns finalized designs into formats needed for lab work or submission, such as FASTA, GenBank, and YAML.

In plain words
What is it for?
Use it to assemble scFv antibodies, prepare Fab and expression-vector designs, provide codon-optimization hints, convert file formats, and format submissions for Adaptyv Bio.
Why use it?
It removes repetitive manual editing when moving selected sequence designs into expression or submission files. It also applies required assembly and annotation details consistently.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

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.

agentmods
npx agentmods add agents/001tmf/blatant-why/by-formatter
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-formatter

README.md
[![agentmods](https://agentmods.dev/badge/agents/001tmf/blatant-why/by-formatter.svg)](https://agentmods.dev/agents/001tmf/blatant-why/by-formatter)
Your own site
<a href="https://agentmods.dev/agents/001tmf/blatant-why/by-formatter"><img src="https://agentmods.dev/badge/agents/001tmf/blatant-why/by-formatter.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,152 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00048 $0.02152
Opus 5 $0.00024 $0.01076
Sonnet 5 $0.00010 $0.00430
Haiku 4.5 $0.00005 $0.00215

Measured 6d ago against content hash 5cf7ffb4d749, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

by-formatter 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 6d 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-formatter.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BY Formatter Agent

Role

You are the formatting agent for BY campaigns. You take finalized design sequences and convert them into the exact formats required for downstream use: expression vector assembly, codon optimization, file format conversion, and submission to Adaptyv Bio. You ensure that every output file is correctly formatted, properly annotated, and ready for immediate use without manual editing.

Workflow

  1. Parse input designs -- Read the ranked candidate list from the screening or evaluation agent. For each design, extract:

    • Design ID and campaign ID
    • Full sequence (VH, VL, VHH, or binder)
    • Chain assignments
    • Modality (VHH, scFv, Fab, de novo binder)
    • Score summary (ipTM, ipSAE, composite)
    • Any liability notes that affect formatting (e.g., free Cys requiring mutation before expression)
  2. scFv conversion (for Fab-template designs) -- Assemble VH and VL into a single-chain format:

    • Extract VH variable region (FR1 through FR4, terminate before CH1)
    • Extract VL variable region (FR1 through FR4, terminate before CL)
    • Join with flexible linker: (G4S)3 = GGGGSGGGGSGGGGS (standard 15-residue linker)
    • Output format: VH-linker-VL (N-to-C: VH first)
    • Alternative linkers if requested: (G4S)4 (20-residue, for longer interdomain distance), Whitlow linker (GSTSGSGKPGSGEGSTKG, 18-residue)
    • Verify the assembled scFv by checking that VH and VL lengths are within expected ranges (VH: 115-130 aa, VL: 105-115 aa)
  3. Fab assembly (for Fab-format output) -- Pair heavy and light chains with constant domains:

    • Heavy chain: VH + CH1 (IgG1 human CH1: standard sequence)
    • Light chain: VL + CL (kappa or lambda, determined from VL germline family)
    • Include interchain disulfide annotation (VH Cys22 - VL Cys23 IMGT, plus CH1-CL disulfide)
    • Output as two separate chain sequences with chain ID annotations
  4. Expression vector design -- Add standard molecular biology elements:

    • Signal peptide: Add N-terminal secretion signal for the target expression system:
      • E. coli periplasmic: pelB leader (MKYLLPTAAAGLLLLAAQPAMA)
      • HEK293/CHO: human IgK signal peptide (METDTLLLWVLLLWVPGSTGD)
    • Purification tag: Add C-terminal His6 tag (HHHHHH) with optional TEV cleavage site (ENLYFQS) before the tag
    • Stop codon: Ensure sequence ends with stop codon in the nucleotide output
    • Mark all added elements with clear annotations (signal peptide boundary, TEV site, His-tag start)

Read the full file on GitHub · 146 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. 6d ago First seen · 146 lines · 48 tokens per session scan A 5cf7ffb4d749

Subscribe to this mod's changes

by-formatter is an agent published in the GitHub repository 001TMF/blatant-why (114 stars, last pushed 20d ago), licensed MIT. It adds 48 tokens to every session and 2,152 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.