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 uniprot-rcsbgit 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/uniprot-rcsb)<a href="https://agentmods.dev/skills/k-dense-ai/drug-discovery-agent-skills/uniprot-rcsb"><img src="https://agentmods.dev/badge/skills/k-dense-ai/drug-discovery-agent-skills/uniprot-rcsb/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/uniprot-rcsb"><img src="https://agentmods.dev/badge/skills/k-dense-ai/drug-discovery-agent-skills/uniprot-rcsb.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 | $0.00162 | $0.02467 |
| Opus 5 | $0.00081 | $0.01234 |
| Sonnet 5 | $0.00032 | $0.00493 |
| Haiku 4.5 | $0.00016 | $0.00247 |
Grade A, and why
uniprot-rcsb 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UniProt, RCSB PDB, and AlphaFold DB
The retrieval layer under every structure-based workflow: sequence in, annotation and coordinates out, plus the checks that decide whether those coordinates are worth using.
Services: rest.uniprot.org · search.rcsb.org · data.rcsb.org · files.rcsb.org · alphafold.ebi.ac.uk. All unauthenticated.
Read references/uniprot-api.md for query and field syntax, references/rcsb-search.md for search attributes and the data API, and references/choosing-a-structure.md before committing to a structure — that one is judgement, not syntax.
The four scripts
| Script | Answers |
|---|---|
uniprot_fetch.py |
What is this protein, what is its sequence, where are its sites, what ids does it map to |
rcsb_search.py |
Which structures exist, and which are worth downloading |
fetch_structure.py |
Get the coordinates — experimental, assembly, predicted, or ligand |
structure_report.py |
Is this file actually usable, and what is missing from it |
Sequence and annotation
python skills/uniprot-rcsb/scripts/uniprot_fetch.py entry P00533
python skills/uniprot-rcsb/scripts/uniprot_fetch.py search "gene:EGFR AND organism_id:9606 AND reviewed:true"
python skills/uniprot-rcsb/scripts/uniprot_fetch.py fasta P00533 --isoforms
python skills/uniprot-rcsb/scripts/uniprot_fetch.py features P00533 --types Binding,Active,Mutagenesis
python skills/uniprot-rcsb/scripts/uniprot_fetch.py map P00533 P04637 --to PDB
Put reviewed:true in almost every search. UniProtKB is ~0.5 % Swiss-Prot (curated) and
~99.5 % TrEMBL (automatic); without the flag a gene-name search returns fragments and predicted
isoforms above the entry you wanted. The script reports the reviewed/unreviewed split and warns
when nothing reviewed matched.
What ships with it
8 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.
- references/choosing-a-structure.md 7.2 KB
- references/rcsb-search.md 7.4 KB
- references/uniprot-api.md 6.7 KB
- scripts/_common.py 8.5 KB runs code
- scripts/fetch_structure.py 9.0 KB runs code
- scripts/rcsb_search.py 15 KB runs code
- scripts/structure_report.py 21 KB runs code
- scripts/uniprot_fetch.py 15 KB runs code
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 · 178 lines · 162 tokens per session scan A de3632ab102b
uniprot-rcsb 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 162 tokens to every session and 2,467 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.