nmdc-explore

nmdc-explore is a skill for Claude Code, Codex from joevstaas/awesome-claude-skills. It costs 96 tokens per session (6,868 once invoked), scanned A, original, MIT.

A search and inspection tool for the Norwegian Marine Data Centre, a catalogue of ocean and fisheries datasets from Norway and the Nordic region. It finds datasets by topic, provider, location, and time period, then shows their available files and access details.

In plain words
What is it for?
Use it to find marine datasets, inspect their metadata, file sizes, licences, and links, and assess whether they can be added to the Ocean Data Platform. It does not perform the actual data import.
Why use it?
It removes the need to search the centre’s data catalogue manually and helps determine whether a dataset is suitable for use in the Ocean Data Platform.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to find marine datasets, inspect their metadata, file sizes, licences, and links, and assess whether they can be added to the Ocean Data Platform. It does not perform the actual data import.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/joevstaas/awesome-claude-skills/nmdc-explore
Install

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.

Any agent
npx skills add joevstaas/awesome-claude-skills --skill nmdc-explore
Clone the repo
git clone --depth 1 https://github.com/joevstaas/awesome-claude-skills

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 nmdc-explore

README.md
[![agentmods](https://agentmods.dev/badge/skills/joevstaas/awesome-claude-skills/nmdc-explore/github.svg)](https://agentmods.dev/skills/joevstaas/awesome-claude-skills/nmdc-explore)
Your own site
<a href="https://agentmods.dev/skills/joevstaas/awesome-claude-skills/nmdc-explore"><img src="https://agentmods.dev/badge/skills/joevstaas/awesome-claude-skills/nmdc-explore/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 nmdc-explore

Your own site · 80×15
<a href="https://agentmods.dev/skills/joevstaas/awesome-claude-skills/nmdc-explore"><img src="https://agentmods.dev/badge/skills/joevstaas/awesome-claude-skills/nmdc-explore.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,868 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 $0.00096 $0.06868
Opus 5 $0.00048 $0.03434
Sonnet 5 $0.00019 $0.01374
Haiku 4.5 $0.00010 $0.00687

Measured 12d ago against content hash 8d1ac2c0ff48, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

nmdc-explore 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.

skills/nmdc-explore/SKILL.md · 400 lines

How it starts

The opening of the file, as written. The whole thing — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NMDC Explore

When to use this skill

Invoke when the user:

  • Mentions NMDC or the Norwegian Marine Data Centre by name.
  • Asks for marine, ocean, or fisheries data with a Norwegian or Nordic flavour ("data from IMR", "Barents Sea cruises", "Mareano survey", "Argo floats off Norway").
  • Wants to discover datasets by topic, provider, geography, or time period.
  • Drills into a single dataset for file lists, sizes, license, and access details.
  • Asks whether an NMDC dataset can be ingested into ODP and how.

Skip when the user is asking about ODP itself (use odp-data-consume, odp-data-ingest, or odp-stac-api), about a different Norwegian source like Vannmiljø (use vannmiljo), or about local files (use odp-data-exploration).

Out of scope

This skill does not:

  • Perform the actual ODP ingest (hand off to odp-data-ingest).
  • Download or subset NetCDF data from OPeNDAP (use xarray / pydap directly).
  • Drive the /Subsetter/ basket workflow on the NMDC site (browser-only feature).
  • Sort search results by recency. The NMDC API has no sort parameter; ask the user for a concrete period instead.
  • Search anything outside metadata.nmdc.no.

Backend overview

metadata.nmdc.no exposes a small read-only API under /metadata-api/:

Endpoint Use
GET /metadata-api/getFacets Full facet tree: Scientific_Keyword (CEOS GCMD hierarchy, >-delimited paths) and Provider (~45 institutions). Each node has a match count.
GET /metadata-api/search?q=&offset=&beginDate=&endDate=&bbox=&dateSearchMode= Solr-backed catalog search. Returns {matches, numFound, results[]}. Page size is hardcoded to 10 — only offset paginates.
GET /metadata-api/landingpage/{hash} HTML landing page for one dataset, rendered from CEOS DIF 9.7.1 metadata. Carries the file list, license, and stated sizes.

Caveats to keep in mind:

  • HTTP only (not HTTPS). Don't error — note it and proceed.
  • No sort parameter on search. If the user asks for "latest", request a concrete period.
  • The bbox query param is appended as a Solr filter query, but in practice the live UI puts geographic constraints into q directly via location_rpt — this skill does the same.

Read the full file on GitHub · 400 lines

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. 12d ago First seen · 400 lines · 96 tokens per session scan A 8d1ac2c0ff48

Subscribe to this mod's changes

nmdc-explore is a skill published in the GitHub repository joevstaas/awesome-claude-skills (6 stars, last pushed 15d ago), licensed MIT. It adds 96 tokens to every session and 6,868 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

phylogenetics

Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.

K-Dense-AI/scientific-agent-skills · 68 tokens

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

mapping-to-snomed

Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…

maziyarpanahi/openmed · 205 tokens