agentmods.dev

Biomedical-Agent-DB-Karpathy: Skill for Claude Code

.agents/skills/biomedical-database/SKILL.md

biomedical-database is a skill for Claude Code, Codex from stanveer/Biomedical-Agent-DB-Karpathy. It costs 59 tokens per session (337 once invoked), scanned A, original, MIT.

A set of rules for designing and updating databases that store biomedical information such as genes, proteins, diseases, chemicals, pathways, and research papers.

In plain words
What is it for?
Use it for biomedical schema design, importing source data, standardising terms, checking identifiers, mapping terms to ontologies, and linking claims to evidence.
Why use it?
It helps prevent made-up identifiers and lost source evidence while keeping uncertain or conflicting biomedical information visible.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; installed under .agents/ (shared by several agents).

This is stanveer/Biomedical-Agent-DB-Karpathy's own configuration. It tells Claude Code and Codex how to work on Biomedical-Agent-DB-Karpathy itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Biomedical-Agent-DB-Karpathy configures →

not rated 2repo 6mo ago A scan 59 tokens original MIT
View source ↗ stanveer/Biomedical-Agent-DB-Karpathy
Reuse

Borrowing it

Nothing to install: this file belongs to stanveer/Biomedical-Agent-DB-Karpathy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/stanveer/Biomedical-Agent-DB-Karpathy/master/.agents/skills/biomedical-database/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/stanveer/Biomedical-Agent-DB-Karpathy

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for biomedical-database

README.md
[![agentmods](https://agentmods.dev/badge/skills/stanveer/biomedical-agent-db-karpathy/biomedical-database/github.svg)](https://agentmods.dev/skills/stanveer/biomedical-agent-db-karpathy/biomedical-database)
Your own site
<a href="https://agentmods.dev/skills/stanveer/biomedical-agent-db-karpathy/biomedical-database"><img src="https://agentmods.dev/badge/skills/stanveer/biomedical-agent-db-karpathy/biomedical-database/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.

agentmods 80×15 button for biomedical-database

Your own site · 80×15
<a href="https://agentmods.dev/skills/stanveer/biomedical-agent-db-karpathy/biomedical-database"><img src="https://agentmods.dev/badge/skills/stanveer/biomedical-agent-db-karpathy/biomedical-database.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 337 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.00337
Opus 5.5 $0.00024 $0.00135
Sonnet 5.5 $0.00012 $0.00067
Haiku 4.5 $0.00006 $0.00034

Measured 2mo ago against content hash 6fea2e73f2ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

biomedical-database 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 2mo 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.

.agents/skills/biomedical-database/SKILL.md · 45 lines

What it actually says

Biomedical Database Skill

Purpose

This skill helps coding agents work safely on a biomedical knowledge database.

Core rules

  • Do not invent identifiers, ontology mappings, or unsupported relations.
  • Treat genes, proteins, variants, diseases, chemicals, pathways, and papers as distinct entity types.
  • Preserve source provenance for every nontrivial assertion.
  • Preserve disagreement across sources rather than overwriting it.
  • Keep observed text separate from normalized canonical values.
  • Preserve ambiguity when normalization is not justified.
  • Prefer minimal schema changes and explain them before making them.

Required reading before edits

  • docs/chat-context.md
  • docs/architecture.md
  • CLAUDE.md
  • schema/tables.sql
  • config/source_registry.yaml

Good implementation sequence

  1. Read the current schema and context files.
  2. Summarize the exact task in terms of entity types, namespaces, and provenance needs.
  3. Identify whether the change belongs in ingestion, normalization, validation, or schema.
  4. Prefer tests for ambiguity, conflicting evidence, and identifier handling.
  5. Verify that canonical IDs, source releases, and ingest metadata are not dropped.

Completion checklist

  • Canonical identifiers preserved
  • Entity types not collapsed
  • Source provenance retained
  • Ambiguity surfaced instead of guessed away
  • No speculative schema additions
Changes

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.

  1. 2mo ago First seen · 45 lines · 59 tokens per session scan A 6fea2e73f2ee

Subscribe to this mod's changes

biomedical-database is a skill published in the GitHub repository stanveer/Biomedical-Agent-DB-Karpathy (2 stars, last pushed 6mo ago), licensed MIT. It adds 59 tokens to every session and 337 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.

DatabasesScientific
Related

biomedical-database compared with skills from other repositories

biomedical-database next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
biomedical-databasestanveer/Biomedical-Agent-DB-KarpathySkill26mo agoMITA59Claude Code, Codex
tiledbvcfK-Dense-AI/scientific-agent-skillsSkill57kyesterdayMITA62Claude Code, Codex
lamindbK-Dense-AI/scientific-agent-skillsSkill57kyesterdayMITA58Claude Code, Codex
defining-cohort-phenotypesmaziyarpanahi/openmedSkill5.8kyesterdayApache-2.0A191Claude Code
benchling-integrationsynthetic-sciences/openscienceSkill4.4kyesterdayApache-2.0A44Claude Code, Codex
chembl-databasegoogle-deepmind/science-skillsSkill3.4k17d agoApache-2.0A53Claude Code, Codex
geospatial-data-pipelinecuriositech/some_claude_skillsSkill2644d agoMITA89Claude Code