arwp-dataset-publication

arwp-dataset-publication is a skill for Claude Code, Codex from dkharlanau/agent-ready-web-profile. It costs 38 tokens per session (740 once invoked), scanned A, original, Apache-2.0.

A workflow for publishing a genuine reusable website collection as a versioned dataset with an archive citation, provenance, and machine-readable descriptions. A dataset is a structured collection of information intended for reuse or analysis.

In plain words
What is it for?
It is for auditing a site's corpus, preparing dataset metadata and documentation, and publishing a reproducible release when the material has independent reuse value.
Why use it?
It helps turn an informal or changing collection into a documented release with clear scope, history, limitations, and reuse rights.

Skill for Claude CodeCodex

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

Good fit It is for auditing a site's corpus, preparing dataset metadata and documentation, and publishing a reproducible release when the material has independent reuse value.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dkharlanau/agent-ready-web-profile/arwp-dataset-publication
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 dkharlanau/agent-ready-web-profile --skill arwp-dataset-publication
Clone the repo
git clone --depth 1 https://github.com/dkharlanau/agent-ready-web-profile

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 arwp-dataset-publication

README.md
[![agentmods](https://agentmods.dev/badge/skills/dkharlanau/agent-ready-web-profile/arwp-dataset-publication/github.svg)](https://agentmods.dev/skills/dkharlanau/agent-ready-web-profile/arwp-dataset-publication)
Your own site
<a href="https://agentmods.dev/skills/dkharlanau/agent-ready-web-profile/arwp-dataset-publication"><img src="https://agentmods.dev/badge/skills/dkharlanau/agent-ready-web-profile/arwp-dataset-publication/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 arwp-dataset-publication

Your own site · 80×15
<a href="https://agentmods.dev/skills/dkharlanau/agent-ready-web-profile/arwp-dataset-publication"><img src="https://agentmods.dev/badge/skills/dkharlanau/agent-ready-web-profile/arwp-dataset-publication.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 740 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 $0.00038 $0.00740
Opus 5 $0.00019 $0.00370
Sonnet 5 $0.00008 $0.00148
Haiku 4.5 $0.00004 $0.00074

Measured 2d ago against content hash f24fbd1bfd7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

arwp-dataset-publication 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 2d 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/arwp-dataset-publication/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ARWP Dataset Publication

Use this skill when a target website contains a substantial reusable corpus: knowledge records, cards, annotations, research observations, evaluation cases, exercises, benchmarks or other structured data with independent reuse value.

Do not activate this workflow merely to create an SEO artifact.

Outcome

Turn an existing mutable website corpus into a deliberately scoped, versioned, reproducible and externally citable dataset release.

Workflow

  1. Inspect the repository and public site before creating files.
  2. Decide whether a genuine reusable dataset exists. If not, mark the module not applicable and stop.
  3. Identify the canonical corpus and exclude private, operational, generated-noise and unsafe-to-release files.
  4. Run node bin/arwp-dataset.mjs <canonical-site-url> --json when the public site is available.
  5. Ensure a human dataset/research landing surface exists.
  6. Publish canonical Schema.org Dataset metadata. Use Croissant/DCAT in addition only when the dataset shape/catalog justifies them.
  7. Publish methodology, provenance, limitations, schema/data dictionary and explicit reuse rights.
  8. Choose a dataset release version and freeze the distributions intended for citation.
  9. Compute SHA-256 checksums for the exact release bytes.
  10. Prepare accurate CITATION.cff metadata for the dataset release.
  11. Publish the frozen release through Zenodo or another appropriate external persistent archive using owner-authorized access.
  12. Only after the archive issues the identifier, verify that the DOI resolves to the intended release and then add the exact DOI to Dataset metadata, CITATION.cff, the human citation surface and relevant trust metadata.
  13. Preserve prior version DOI identity when a later corpus release changes cited bytes.
  14. Re-run the ARWP dataset audit and keep missing or externally blocked work explicit.

Required state model

Before external archival issuance, use an explicit state such as:

{
  "publicationState": "doi-not-issued",
  "persistentIdentifier": {
    "type": "DOI",
    "state": "not-issued",
    "value": null
  }
}

Read the full file on GitHub · 70 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. 2d ago Changed · +2 lines f24fbd1bfd7c
  2. 3d ago First seen · 68 lines · 38 tokens per session scan A 46ec463ed6d7

Subscribe to this mod's changes

arwp-dataset-publication is a skill published in the GitHub repository dkharlanau/agent-ready-web-profile (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 38 tokens to every session and 740 once invoked, about $0.0002 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 2026-09-08.