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 degradersgit 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/degraders)<a href="https://agentmods.dev/skills/k-dense-ai/drug-discovery-agent-skills/degraders"><img src="https://agentmods.dev/badge/skills/k-dense-ai/drug-discovery-agent-skills/degraders/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/degraders"><img src="https://agentmods.dev/badge/skills/k-dense-ai/drug-discovery-agent-skills/degraders.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 | $0.00145 | $0.02033 |
| Opus 5 | $0.00072 | $0.01017 |
| Sonnet 5 | $0.00029 | $0.00407 |
| Haiku 4.5 | $0.00015 | $0.00203 |
Grade A, and why
degraders 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Targeted Protein Degradation
A degrader does not inhibit a protein — it recruits an E3 ligase to it, the protein is destroyed, and the degrader is released to do it again. That single change makes an "undruggable" target tractable, because a degrader needs only a binding site, not a functional pocket. It is the largest expansion of small-molecule target space in the last decade, and almost every developability heuristic you know is calibrated for something else.
No installation, no network, no key for the bundled scripts — they implement the property rules, linker arithmetic, and dose-response analysis. Ternary complex prediction needs an external tool (PRosettaC, DeepTernary, AlphaFold3) with its own licence and usually a GPU.
Read references/degrader-modalities.md for how this pharmacology differs, references/ternary-complex.md before modelling or designing a linker, and references/degrader-developability.md before judging a molecule — that one is judgement, not syntax.
The three scripts
| Script | Answers |
|---|---|
protac_properties.py |
Is this molecule inside the bRo5 habitable band? |
ternary_setup.py |
What do the prediction tools need, and what linker lengths do I make? |
degrader_triage.py |
What do DC50, Dmax, and the curve shape actually say? |
Occupancy versus event
| Inhibitor | Degrader | |
|---|---|---|
| Requires | continuous occupancy | a transient encounter |
| Stoichiometry | 1:1 | catalytic |
| Removes | one function | the whole protein, scaffolding included |
| Duration | drug half-life | protein resynthesis rate |
| Needs | a functional pocket | any ligandable surface |
The last row is the point. No catalytic site, no allosteric mechanism, no functional consequence
of binding required — which is why binding-site-analysis names degradation first when a target
scores undruggable.
What ships with it
6 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 · 161 lines · 145 tokens per session scan A 6d317418e82f
degraders 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 145 tokens to every session and 2,033 once invoked, about $0.0007 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.