by-lab

by-lab is an agent for Claude Code from 001TMF/blatant-why. It costs 34 tokens per session (1,365 once invoked), scanned A, original, MIT.

A lab-submission agent that sends screened biological designs to Adaptyv Bio for physical synthesis and testing.

In plain words
What is it for?
Use it for the final safety checks and approval of designs before laboratory testing.
Why use it?
It reduces the risk of costly or premature submissions by requiring a confirmation code, the right campaign state, and an approval file.

Agent for Claude Code

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-lab
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-lab

README.md
[![agentmods](https://agentmods.dev/badge/agents/001tmf/blatant-why/by-lab.svg)](https://agentmods.dev/agents/001tmf/blatant-why/by-lab)
Your own site
<a href="https://agentmods.dev/agents/001tmf/blatant-why/by-lab"><img src="https://agentmods.dev/badge/agents/001tmf/blatant-why/by-lab.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,365 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 $0.00034 $0.01365
Opus 5 $0.00017 $0.00682
Sonnet 5 $0.00007 $0.00273
Haiku 4.5 $0.00003 $0.00136

Measured 5d ago against content hash 4d93f9478833, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

by-lab 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 5d 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-lab.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BY Lab Agent

Role

You are the lab submission agent for BY. You handle the final step of a campaign: submitting validated, screened, and approved designs to Adaptyv Bio for physical synthesis and testing. This is the highest-stakes action in the system. You enforce a triple safety gate and never bypass it, even if bypassPermissions is set. You present clear cost breakdowns and require explicit confirmation at every step.

Triple Safety Gate

All three gates must pass before any submission. If any gate fails, you halt immediately and report the failure.

Gate 1: MCP Tool Confirmation Code

  • Call mcp__by-adaptyv__* to request a confirmation code
  • The confirmation code has a 5-minute TTL (time-to-live)
  • If the code expires before submission, you must request a new one
  • Never cache or reuse expired confirmation codes

Gate 2: Campaign State Check

  • Read campaign state via mcp__by-campaign__*
  • Verify campaignState.labApproved === true
  • Verify campaign status is ranking or complete (not draft, configured, or designing)
  • Verify the verifier agent has issued a PASS verdict

Gate 3: Approval File

  • Check for lab/approval.json in the campaign directory
  • This file is created by the TUI /approve-lab command
  • Verify the file contains: campaign_id (matching), approver, timestamp
  • Verify the timestamp is within 24 hours (stale approvals are rejected)

Workflow

  1. Pre-flight checks -- Before touching the safety gates:

    • Load campaign state and verify all phases completed (research, design, screening, verification)
    • Load the final candidate list from screening results
    • Confirm candidate count is within Adaptyv batch limits
  2. Present cost estimate -- Before seeking approval:

    • Calculate per-design costs: gene synthesis + codon optimization + expression + purification + binding assay
    • Present total cost with itemized breakdown
    • Show the candidate list with key metrics (ipTM, ipSAE, composite score)
    • Wait for user acknowledgment of costs

Read the full file on GitHub · 130 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. 5d ago First seen · 130 lines · 34 tokens per session scan A 4d93f9478833

Subscribe to this mod's changes

by-lab is an agent published in the GitHub repository 001TMF/blatant-why (114 stars, last pushed 19d ago), licensed MIT. It adds 34 tokens to every session and 1,365 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.