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.
npx agentmods add commands/001tmf/blatant-why/welcomegit clone --depth 1 https://github.com/001TMF/blatant-whyWrote 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.
[](https://agentmods.dev/commands/001tmf/blatant-why/welcome)<a href="https://agentmods.dev/commands/001tmf/blatant-why/welcome"><img src="https://agentmods.dev/badge/commands/001tmf/blatant-why/welcome.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00016 | $0.00739 |
| Opus 5 | $0.00008 | $0.00369 |
| Sonnet 5 | $0.00003 | $0.00148 |
| Haiku 4.5 | $0.00002 | $0.00074 |
Grade A, and why
by:welcome 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.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/welcome — First-Run Orientation
Introduce BY to a new user and surface the core workflows without overwhelming them with internal complexity.
Instructions
Step 1: Check if this is a first run
Read .by/environment.json. If it does not exist, this is likely a fresh install.
Note the result for Step 3 and Step 4.
Step 2: Display welcome message
Present the following orientation:
Welcome to BY (Blatant-Why)
BY is a protein design agent that helps you design nanobodies, antibodies, and protein binders. You describe a target, BY handles the computation.
Getting Started (pick one)
1. Design nanobodies against a target
Example: "Design VHH nanobodies against PD-L1"
BY will research your target, ask a few quick questions about your preferences, then run the full design-screen-rank pipeline. You get back a ranked table of candidates ready for lab testing.
2. Load and explore a target first
Example:
/by:load PD-L1or/by:load 5JDSResearch a protein target before committing to a design campaign. BY pulls structural data, known binders, and epitope information so you can make an informed decision.
3. Check your environment
Example:
/by:setupSee what compute providers are available and which API keys are configured. Useful if you want to confirm Tamarind Bio access or check for local GPU tools.
4. Resume an existing campaign
Example:
/by:statusthen/by:resultsCheck the state of a running campaign or view ranked designs from a completed one.
Key Commands
| Command | What it does |
|---|---|
/by:plan-campaign |
Quick discussion to capture your design preferences before launching |
/by:load |
Research a protein target (structure, known binders, epitopes) |
/by:status |
Check current campaign progress |
/by:results |
View ranked design candidates with scores |
/by:setup |
Configure compute providers and API keys |
What happens behind the scenes
BY uses specialized MCP tools to search protein databases (PDB, UniProt, SAbDab), run structure predictions and design computations via Tamarind Bio cloud (free tier available), and score candidates with custom metrics (ipSAE for interface quality, ipTM for global confidence). You do not need to manage any of this -- just describe what you want.
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.
- 5d ago First seen · 85 lines · 16 tokens per session scan A 5b03c2cbd9b1
by:welcome is a command published in the GitHub repository 001TMF/blatant-why (114 stars, last pushed 19d ago), licensed MIT. It adds 16 tokens to every session and 739 once invoked, about $0.0001 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.
Other commands, from other repositories
read
Accepts: local PDF path, DOI, journal URL, or a pasted abstract with basic metadata.
run-gencast
Guide the user through running GenCast end-to-end on an AMD cluster.
run-swinunetr
Guide the user through training or inference with SwinUNETR on AMD GPUs.
run-aurora
Guide the user through running Aurora (0.1° resolution) end-to-end on an AMD cluster.
run-reinvent4
Guide the user through running REINVENT4 transfer learning for molecular design on AMD GPUs.
run-semlaflow
Guide the user through generating 3D molecular structures with SemlaFlow on AMD GPUs.