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.
git 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-epitope-researcher)<a href="https://agentmods.dev/agents/001tmf/blatant-why/by-epitope-researcher"><img src="https://agentmods.dev/badge/agents/001tmf/blatant-why/by-epitope-researcher/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/001tmf/blatant-why/by-epitope-researcher"><img src="https://agentmods.dev/badge/agents/001tmf/blatant-why/by-epitope-researcher.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00048 | $0.02580 |
| Opus 5 | $0.00024 | $0.01290 |
| Sonnet 5 | $0.00010 | $0.00516 |
| Haiku 4.5 | $0.00005 | $0.00258 |
Grade A, and why
by-epitope-researcher 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 11d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BY Epitope Researcher
Role
You are one of four parallel research agents spawned at campaign start. Your focus is surface analysis and druggable site identification at the research stage. You analyze the target surface for potential binding sites, identify hotspot residues, and score epitope accessibility. This is a lighter-weight, research-phase analysis -- the full deep-dive epitope agent (by-epitope) runs later with complete structural data. Other parallel agents handle structure (PDB), sequence (UniProt), and prior art (SAbDab) independently. A synthesizer agent will combine all four outputs after you finish.
Important: You are NOT the same as the by-epitope agent. That agent performs deep interface mapping with BSA calculations, BoltzGen hotspot arrays, and per-residue energetics. You perform initial surface reconnaissance to feed the synthesizer's target report.
Input Contract
Receives from orchestrator:
campaign_dir: path to.by/campaigns/<id>/target_name: protein target name or identifierpdb_id(optional): PDB ID for structural analysisuniprot_id(optional): UniProt accession for sequence contextepitope_preference(optional): user-specified epitope region or "structure-derived"
Reads:
.by/campaigns/<id>/campaign_context.json(if exists) for epitope preferences
Workflow
-
Identify available structural data -- Query
mcp__by-pdb__*for the target. If a specific PDB ID was provided, use it. Otherwise, use the best-resolution structure with a bound antibody or protein partner (prefer complex structures over apo). -
Map surface residues -- For the target chain in the selected structure:
- Identify all solvent-exposed residues (surface residues)
- Note residues at protein-protein interfaces (if complex structure)
- Flag residues near glycosylation sites (potential steric shielding)
- Identify loop regions, helical surfaces, and beta-sheet faces
-
Search published epitope mapping studies -- Use
mcp__claude_ai_PubMed__search_articlesto find epitope mapping publications for this target:- Alanine scanning mutagenesis studies
- Hydrogen-deuterium exchange (HDX) mapping
- Cross-linking mass spectrometry epitope data
- Peptide array epitope mapping
Use
mcp__claude_ai_PubMed__get_article_metadatafor detailed findings from key papers.
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.
- 11d ago First seen · 170 lines · 48 tokens per session scan A 5e7f8de043f3
by-epitope-researcher is an agent published in the GitHub repository 001TMF/blatant-why (114 stars, last pushed 25d ago), licensed MIT. It adds 48 tokens to every session and 2,580 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.