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 skills add K-Dense-AI/drug-discovery-agent-skills --skill antibody-engineeringgit clone --depth 1 https://github.com/K-Dense-AI/drug-discovery-agent-skillsWrote 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/skills/k-dense-ai/drug-discovery-agent-skills/antibody-engineering)<a href="https://agentmods.dev/skills/k-dense-ai/drug-discovery-agent-skills/antibody-engineering"><img src="https://agentmods.dev/badge/skills/k-dense-ai/drug-discovery-agent-skills/antibody-engineering/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/skills/k-dense-ai/drug-discovery-agent-skills/antibody-engineering"><img src="https://agentmods.dev/badge/skills/k-dense-ai/drug-discovery-agent-skills/antibody-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00165 | $0.01970 |
| Opus 5 | $0.00082 | $0.00985 |
| Sonnet 5 | $0.00033 | $0.00394 |
| Haiku 4.5 | $0.00016 | $0.00197 |
Grade A, and why
antibody-engineering 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 12d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Antibody engineering
Sequence-level analysis for antibodies, nanobodies, and other variable-domain formats: numbering, CDR annotation, chemical liabilities, and physicochemical properties. All of it runs in seconds and rules out a surprising fraction of problems before a model or a wet-lab week is spent.
Read references/numbering-schemes.md before quoting any residue position, references/developability.md before acting on a liability, references/humanization-and-design.md for grafting and humanness, and references/tools.md for the wider ecosystem.
A residue number means nothing without its scheme
"Residue 52" is a different residue in IMGT, Kabat, and Chothia numbering, and the CDRs they define overlap only partially. The same trastuzumab heavy chain:
IMGT CDRH1 GFNIKDTY (8) CDRH2 IYPTNGYT (8) CDRH3 SRWGGDGFYAMDY (13)
Kabat CDRH1 DTYIH (5) CDRH2 RIYPTNGYTRYADSVKG (17) CDRH3 WGGDGFYAMDY (11)
Neither is wrong. Use IMGT by default — one definition for both chains, structurally principled gaps, and the germline database is IMGT-numbered — and convert to Kabat when matching legacy literature. State the scheme every time.
python skills/antibody-engineering/scripts/number_antibody.py antibody.fasta
python skills/antibody-engineering/scripts/number_antibody.py antibody.fasta --scheme kabat
python skills/antibody-engineering/scripts/number_antibody.py antibody.fasta \
--format regions --out regions.tsv
# trastuzumab_VH: chain H, closest germline human_H (human), E=3e-60
# variable domain spans input residues 1-120
CDRH1 8 GFNIKDTY
CDRH2 8 IYPTNGYT
CDRH3 13 SRWGGDGFYAMDY
Needs pip install anarci plus HMMER (hmmscan on PATH). Note that ANARCI's species call is
the closest germline, not an annotation — a humanised antibody reports human because its
frameworks are human, which says nothing about its CDRs.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 149 lines · 165 tokens per session scan A d7e6ea55ebc7
antibody-engineering is a skill published in the GitHub repository K-Dense-AI/drug-discovery-agent-skills (28 stars, last pushed 5d ago), licensed MIT. It adds 165 tokens to every session and 1,970 once invoked, about $0.0008 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 skills, from other repositories
patsnap-biological-modality
Biological sequence and modality intelligence via Patsnap MCP.
patsnap-chemical-molecular
Patsnap Chemical Molecular MCP for AI agents. Search 160M+ chemical structures, synthetic routes, and bioactivity data via specialized chemistry tools.
patsnap-scientific-translational-evidence
Patsnap Scientific & Translational Evidence MCP for AI agents. Retrieval platform focusing on scientific literature and translational outcomes, covering academic publication queries and translational medicine record tracking.
patsnap-target-disease
Patsnap Target & Disease MCP for AI agents. Target and disease profiling tool, covering target characterization, disease profiling, and epidemiology evidence retrieval.
patsnap-solution-engine
Patsnap TRIZ Concept Solution Engine MCP for AI agents. Generates innovation or product cost-reduction concepts through asynchronous TRIZ and TRIZ/DFMA workflows. Use for engineering problem solving, concept alternatives, cost-reduction analysis, task-progress retrieval, and selected-solution details.
patsnap-clinical-trials
Patsnap Clinical Trials MCP for AI agents. Intelligent clinical trial retrieval system, covering registered trial tracking, trial details and results analysis, and supporting clinical semantic search.