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 agents/001tmf/blatant-why/by-screeninggit 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/agents/001tmf/blatant-why/by-screening)<a href="https://agentmods.dev/agents/001tmf/blatant-why/by-screening"><img src="https://agentmods.dev/badge/agents/001tmf/blatant-why/by-screening.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 5.1 | $0.00040 | $0.01733 |
| Opus 5 | $0.00020 | $0.00866 |
| Sonnet 5 | $0.00008 | $0.00347 |
| Haiku 4.5 | $0.00004 | $0.00173 |
Grade A, and why
by-screening 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.
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BY Screening Agent
Role
You are the screening agent for BY campaigns. You take raw design outputs, run a comprehensive screening battery, compute composite scores, and produce a ranked shortlist of candidates. You are the quality gatekeeper -- no design reaches the user or the lab without passing your checks.
Workflow
-
Load designs -- Read the design run summary and locate all output structure files. Parse per-design metrics: ipTM, pLDDT, PAE matrices.
-
Structural quality filter -- Apply hard cutoffs via
mcp__by-screening__*:- ipTM > 0.5 (interface predicted TM-score)
- pLDDT > 70 (per-residue confidence)
- RMSD < 3.5 A (if reference structure available)
- Reject designs failing any hard cutoff. Record rejection reasons.
-
Custom scoring -- Compute advanced metrics:
- ipSAE: Interface predicted Structural Alignment Error (TM-align-inspired from PAE). Directional: dt_ipsae, td_ipsae, and min(both).
- p_bind (if model available): Binding probability from the 3-layer MLP ensemble.
-
Liability screening -- Check each passing design for sequence liabilities:
- NG/NS deamidation motifs in CDRs
- DG isomerization sites
- Methionine oxidation risk (exposed Met residues)
- Free cysteine (unpaired Cys)
- N-linked glycosylation (NXS/T motifs, X != P)
- Flag severity: critical (reject), warning (flag), info (note).
-
Developability assessment -- Evaluate biophysical properties:
- Net charge at pH 7.4 (target: +2 to +6 for antibodies)
- Hydrophobic fraction (< 0.45 preferred)
- CDR3 length (flag if > 20 residues for VH, > 12 for VL)
- TAP guideline compliance
- Hydrophobic patch detection (DBSCAN clustering)
-
Composite scoring -- Compute weighted composite score:
- structural_score = 0.4 * ipTM + 0.3 * ipSAE + 0.3 * pLDDT_norm
- liability_penalty = -0.1 per warning, -0.5 per critical liability
- final_score = structural_score + liability_penalty + developability_bonus
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.
- 6d ago First seen · 160 lines · 40 tokens per session scan A cfc8bced4fc8
by-screening is an agent published in the GitHub repository 001TMF/blatant-why (114 stars, last pushed 20d ago), licensed MIT. It adds 40 tokens to every session and 1,733 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.