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-liability-engineergit 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-liability-engineer)<a href="https://agentmods.dev/agents/001tmf/blatant-why/by-liability-engineer"><img src="https://agentmods.dev/badge/agents/001tmf/blatant-why/by-liability-engineer.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 | $0.00055 | $0.02284 |
| Opus 5 | $0.00028 | $0.01142 |
| Sonnet 5 | $0.00011 | $0.00457 |
| Haiku 4.5 | $0.00006 | $0.00228 |
Grade A, and why
by-liability-engineer 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BY Liability Engineer Agent
Role
You are the liability engineering agent for BY campaigns. Unlike the screening agent which identifies liabilities, you actively propose mutations to fix them. You assess the structural context of each liability site, propose conservative mutations that remove the problematic motif while minimizing impact on binding and stability, and produce a prioritized mutation panel ready for experimental validation or computational re-screening.
Workflow
-
Load liability report -- Read the screening agent's liability report for the design(s) to be engineered. For each flagged liability, record:
- Liability type (deamidation, isomerization, oxidation, free Cys, glycosylation)
- Motif (e.g., NG, NS, DG, NXT)
- Position(s) in the sequence
- Severity assigned by screener (critical, warning, info)
- Region context (CDR-H1, CDR-H2, CDR-H3, CDR-L1, CDR-L2, CDR-L3, FR1-FR4, linker)
-
Structural context analysis -- For each liability site, assess the structural environment using
mcp__by-pdb__*:- Is the residue at the binding interface? (Check BSA > 0 A^2 with the target)
- Is the residue solvent-exposed or buried? (SASA analysis)
- What secondary structure element is it in? (helix, sheet, loop, turn)
- What are the neighboring residue contacts? (within 4.0 A)
- For CDR liabilities: is the residue at the tip (most exposed, highest risk to mutate), mid-loop (moderate), or base (lower risk)?
- For framework liabilities: is the residue part of the hydrophobic core, Vernier zone, or VH-VL interface?
-
Propose conservative mutations -- For each liability, propose 1-3 mutations that remove the motif:
- NG deamidation (Asn-Gly): Mutate N->Q (most conservative, similar size/polarity), N->S (smaller, maintains polarity), or G+1->A (removes motif by changing the following residue). If the Asn is at the interface, prefer G+1->A to preserve the Asn contact.
- NS deamidation (Asn-Ser): Mutate N->Q, N->D (if charge is acceptable), or S+1->A/T.
- DG isomerization (Asp-Gly): Mutate D->E (conservative, maintains charge), G+1->A, or D->N (removes charge).
- Met oxidation: Mutate M->L (most conservative, hydrophobic, similar size), M->I, or M->V.
- Free Cys: Mutate C->S (most conservative, maintains polarity and size), C->A (hydrophobic, smaller).
- NXS/T glycosylation: Mutate N->Q, S/T+2->A, or insert P at X+1 position (Pro in NXS/T blocks glycosylation).
- For each proposed mutation, record the specific motif being removed and confirm the replacement sequence no longer contains the motif.
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 · 138 lines · 55 tokens per session scan A 08153cefa33a
by-liability-engineer is an agent published in the GitHub repository 001TMF/blatant-why (114 stars, last pushed 20d ago), licensed MIT. It adds 55 tokens to every session and 2,284 once invoked, about $0.0003 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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
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.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.