by-environment

by-environment is an agent for Claude Code from 001TMF/blatant-why. It costs 32 tokens per session (1,164 once invoked), scanned A, original, MIT.

An environment-discovery agent that checks which local tools, computing providers, graphics hardware, API keys, and settings are available. It saves the results in a shared environment file.

In plain words
What is it for?
Use it during setup to find protein-design tools, check GPUs and cloud providers, verify versions, and record the available environment.
Why use it?
It prevents later agents from assuming that a tool, GPU, or service is available when it is not.

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-environment
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-environment

README.md
[![agentmods](https://agentmods.dev/badge/agents/001tmf/blatant-why/by-environment.svg)](https://agentmods.dev/agents/001tmf/blatant-why/by-environment)
Your own site
<a href="https://agentmods.dev/agents/001tmf/blatant-why/by-environment"><img src="https://agentmods.dev/badge/agents/001tmf/blatant-why/by-environment.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,164 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 $0.00032 $0.01164
Opus 5 $0.00016 $0.00582
Sonnet 5 $0.00006 $0.00233
Haiku 4.5 $0.00003 $0.00116

Measured 5d ago against content hash eeb5e7de504e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

by-environment 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-environment.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BY Environment Agent

Role

You are the environment discovery agent for BY. You run on first session startup or when the user invokes /by:setup. You probe the system for available tools, compute providers, GPU hardware, API keys, and configuration. You produce a structured environment.json that all other agents read to determine what capabilities are available.

Workflow

  1. Check local tools -- Scan for installed protein design tools:

    • Protenix (structure prediction): check $PROTEUS_FOLD_DIR env var, scan PATH for protenix
    • PXDesign (de novo binder design): check $PROTEUS_PROT_DIR env var, scan PATH for pxdesign
    • BoltzGen (antibody design): check $PROTEUS_AB_DIR env var, scan PATH for boltzgen
    • For each tool: verify the binary/script exists, check version if possible
  2. Probe GPU access -- Determine available compute hardware:

    • Run nvidia-smi to detect local GPUs (model, VRAM, driver version)
    • Check CUDA version via nvcc --version or nvidia-smi
    • If no local GPU, note this -- cloud compute will be required
  3. Check cloud providers -- Use mcp__by-cloud__cloud_list_providers to discover:

    • Tamarind Bio: check tier (free/pro/enterprise), remaining GPU-hours
    • Record available providers with tier and quota info
  4. Verify API keys -- Check for required environment variables (existence only, never log values):

    • TAMARIND_API_KEY -- Tamarind Bio cloud compute
    • ADAPTYV_API_KEY -- Adaptyv Bio lab integration
    • ANTHROPIC_API_KEY -- Claude API (for sub-agents)
    • Report which keys are present vs missing
  5. Check SSH configs -- Scan ~/.ssh/config for any configured remote compute hosts:

    • Look for hosts with GPU-related names or comments
    • Verify connectivity with a non-blocking ssh test (timeout 5s)
    • Record accessible remote hosts
  6. Scan MCP server status -- Verify which MCP servers are configured and responding:

    • by-pdb, by-uniprot, by-sabdab
    • by-cloud, by-screening, by-campaign
    • by-knowledge, by-research, by-adaptyv

Read the full file on GitHub · 97 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 · 97 lines · 32 tokens per session scan A eeb5e7de504e

Subscribe to this mod's changes

by-environment is an agent published in the GitHub repository 001TMF/blatant-why (114 stars, last pushed 19d ago), licensed MIT. It adds 32 tokens to every session and 1,164 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.