A three-layer review method for checking DNV document drafts: field checks, an independent re-derivation, and substantive review by an experienced user’s perspective.

Use it to inspect prepared drafts against the case profile, form registry, controlled values, and practical requirements.

It catches both obvious field errors and values that look plausible but are wrong.

How acogood/spain-dnv-consultant configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to acogood/spain-dnv-consultant. 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/acogood/spain-dnv-consultant/main/.claude/skills/dnv-review/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/acogood/spain-dnv-consultant

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/acogood/spain-dnv-consultant/dnv-review/github.svg)](https://agentmods.dev/skills/acogood/spain-dnv-consultant/dnv-review)

Your own site

<a href="https://agentmods.dev/skills/acogood/spain-dnv-consultant/dnv-review"><img src="https://agentmods.dev/badge/skills/acogood/spain-dnv-consultant/dnv-review/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/acogood/spain-dnv-consultant/dnv-review"><img src="https://agentmods.dev/badge/skills/acogood/spain-dnv-consultant/dnv-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,157 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00087	$0.01157
Opus 5.5	$0.00035	$0.00463
Sonnet 5.5	$0.00017	$0.00231
Haiku 4.5	$0.00009	$0.00116

Measured 2mo ago against content hash 21ac3994207e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dnv-review 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.

.claude/skills/dnv-review/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ревью пакета — трёхслойная методология

Когда нужно проверить черновики из user/drafts/, используй три независимых слоя. Вывод — для черновика, требующего экспертной/официальной проверки.

Для работы нужны user/case-profile.json и user/drafts/drafts.json. Если чего-то не хватает — сгенерируй недостающее (см. навык по заполнению форм) или сообщи пользователю, чего не хватает.

Слой 1A. Механический baseline (детерминированный, исчерпывающий)

python engine/scripts/field_qa.py user/case-profile.json knowledge_base/forms/registry.json user/drafts/drafts.json --out-dir user/drafts --allowed-root user

Гарантии: вердикт на КАЖДОЕ поле реестра (count==полей; молчание = бага), корректность не правдоподобие, контролируемые словари (ловит sexo=indefinido), галлюцинации (профиль пуст, а в черновике значение → WRONG). Отчёт: user/drafts/field_qa_report.md. Ненулевой выход = есть WRONG.

Читая «Причину»: до · реестр: — вывод механики, после — подсказка из реестра (common_errors), то есть контекст, а не находка. Поэтому MISSING ≠ автоматически пробел пакета: у части полей пусто — это корректное состояние кейса. Канонический случай — N.I.E. на первичной подаче: требования предъявить NIE норма не ставит, а подачу подписывает представитель (art. 5 Ley 39/2015 — представительство доказывается cualquier medio válido en Derecho; norms/solicitud-inicial.md §5). Тогда четыре MISSING по N.I.E. (MI-T, MI-F, tasa-790-038, tasa-790-038-familiar) — не пропуски. В сводке разделяй такие MISSING от настоящих и не предлагай заполнить: выдумывать значение нельзя ни в каком случае.

Слой 1B. Независимая ре-деривация (two-process)

Механический baseline сравнивает строки. Ре-деривация добавляет смысловой слой и доказуемо не видит черновик:

Вызови субагента field-qa-reviewer, передав в делегирующем сообщении только содержимое user/case-profile.json и knowledge_base/forms/registry.json. Путь черновика НЕ передавай. Он вернёт ожидаемые значения по каждому полю (вслепую) + межполевые замечания.
Затем сам прочитай user/drafts/drafts.json и сдиффай ожидаемые значения с фактическими. Расхождение → WRONG/UNCERTAIN.
Изоляция проверяема: ожидаемые значения сгенерированы ДО того, как черновик попал в контекст диффа. Если field-qa-reviewer запросил черновик — это нарушение, переспроси без него.

Read the full file on GitHub · 73 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.

2mo ago First seen · 73 lines · 87 tokens per session scan A 21ac3994207e

Subscribe to this mod's changes

dnv-review is a skill published in the GitHub repository acogood/spain-dnv-consultant (83 stars, last pushed 3mo ago), licensed MIT. It adds 87 tokens to every session and 1,157 once invoked, about $0.0003 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 2026-08-30.

Documents

dnv-review next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
dnv-reviewacogood/spain-dnv-consultant	Skill	83	3mo ago	MIT	A	87	Claude Code
orbit-notionnexu-io/open-design	Skill	106k	yesterday	Apache-2.0	A	117	Claude Code, Codex
instrument-data-to-allotropeanthropics/knowledge-work-plugins	Skill	35k	2d ago	Apache-2.0	A	123	Claude Code
apify-youtube-transcript-scrapersickn33/agentic-awesome-skills	Skill	49k	yesterday	MIT	A	48	Claude Code
legal-holdanthropics/claude-for-legal	Skill	9.9k	3d ago	Apache-2.0	A	68	Claude Code
ppt-reviewOrkas-AI/Orkas	Skill	9.0k	yesterday	MIT	A	2	Claude Code, Codex
feishuHmbown/CodeWhale	Skill	41k	5d ago	MIT	A	33	Claude Code, Codex

spain-dnv-consultant: Skill for Claude Code