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/loadgit clone --depth 1 https://github.com/001TMF/blatant-whyWhat 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 | $0.00013 | $0.00834 |
| Opus 5 | $0.00006 | $0.00417 |
| Sonnet 5 | $0.00003 | $0.00167 |
| Haiku 4.5 | $0.00001 | $0.00083 |
Grade A, and why
by:load scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/load — Load and Analyze a Protein Target
Load a protein target by name, PDB ID, or UniProt accession and run initial research analysis to prepare for a design campaign.
Instructions
Step 0: Show BY banner and read model profile
Display the BY session banner first:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
BY ► LOADING TARGET
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Then read model profile:
MODEL_PROFILE=$(cat .by/config.json 2>/dev/null | grep -o '"model_profile"[[:space:]]*:[[:space:]]*"[^"]*"' | grep -o '"[^"]*"$' | tr -d '"' || echo "balanced")
Model lookup for this command:
| Agent | quality | balanced | budget |
|---|---|---|---|
| by-research | opus | sonnet | sonnet |
Step 1: Parse input
Determine the input type:
- PDB ID: 4-character alphanumeric (e.g.,
1ABC,7XYZ) - UniProt accession: alphanumeric with pattern like
P12345orQ9UHD2 - Free text: treat as a target name or description for search
Step 2: Create campaign directory
CAMPAIGN_ID="campaign_$(date +%Y%m%d_%H%M%S)"
mkdir -p .by/campaigns/$CAMPAIGN_ID/{designs,screening,logs,research}
echo ".by/campaigns/$CAMPAIGN_ID" > .by/active_campaign
Initialize state.json with phase=RESEARCH, round=1, target info.
Step 3: Spawn by-research agent
Delegate to a by-research agent via Task() (model per profile table above).
Use MCP research tools (PDB, UniProt, SAbDab) -- NOT web search. The by-research agent has access to all structured databases via MCP servers.
Analyze target:
{user_argument}Tasks:
- Resolve the target to a PDB structure and UniProt entry using MCP tools
- Identify chains, domains, and key binding interfaces
- Search SAbDab for existing antibodies against this target
- Identify known epitopes and druggable sites
- Assess target difficulty (structured/disordered, glycosylation, flexibility)
- Recommend design strategy: binder vs antibody vs nanobody
- Suggest initial parameters (scaffold, CDR lengths, seed count)
Write analysis to
{campaign_dir}/research/target_analysis.json. Write human-readable summary to{campaign_dir}/research/summary.md.
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.
- 3d ago First seen · 113 lines · 13 tokens per session scan A 7d546d95c535
by:load is a command published in the GitHub repository 001TMF/blatant-why (114 stars, last pushed 17d ago), licensed MIT. It adds 13 tokens to every session and 834 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
run-archesweather
Guide the user through running ArchesWeather end-to-end on an AMD cluster.
run-mattergen
Guide the user through running MatterGen end-to-end on an AMD cluster via SLURM or Docker.
run-matey
Guide the user through training or inference with MATEY on AMD GPUs.
run-aurora
Guide the user through running Aurora (0.1° resolution) end-to-end on an AMD cluster.
run-semlaflow
Guide the user through generating 3D molecular structures with SemlaFlow on AMD GPUs.
add-recipe
Create or improve a recipe (inference, fine-tune, eval, etc.) for a model already in AI4Science Studio.