A method for checking claims in case documents against their sources. It extracts individual claims, assigns verification results, and uses a devil’s-advocate review to test whether each claim is supported, contradicted, outdated, or unverifiable.

Use it to verify claims in specifications, written submissions, and related documents, with checks against stored sources, practice notes, and the web.

It helps find statements that lack traceable evidence or use an unsuitable confidence label. This separates source-checking from deciding whether the underlying legal position is correct.

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-verify/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-verify/github.svg)](https://agentmods.dev/skills/acogood/spain-dnv-consultant/dnv-verify)

Your own site

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

Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 772 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	$0.00060	$0.00772
Opus 5.5	$0.00024	$0.00309
Sonnet 5.5	$0.00012	$0.00154
Haiku 4.5	$0.00006	$0.00077

Measured 2mo ago against content hash 477f6f733eb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dnv-verify 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-verify/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Верификация claim'ов — методология (devils-advocate)

Когда нужно проверить утверждения в документе (spec, memoria, escrito) на трассируемость и достоверность, используй эту методологию. Верификация покрывает трассируемость claim'ов и механику полей, не юридическую правильность.

Извлечение claim'ов

python engine/scripts/extract_claims.py user/spec.md user/claims.json

user/claims.json — тегированные claim'ы (с уровнем достоверности, ссылками, секцией). Идемпотентно перегенерируется при изменении документа. Можно указать любой другой файл вместо spec.md.

Запуск devils-advocate

Вызови субагента devils-advocate (.claude/agents/devils-advocate.md). Он:

сам пре-загружает источники (knowledge_base/norms|sources|practice), локальные user/slices/ (Grep-only, не Read целиком), и web;
проверяет по стратегии на тег: [норма]→BOE/WebSearch; [практика — Telegram] → Grep дайджеста/slices, счёт РАЗНЫХ псевдонимов (один человек ×5 ≠ 5); [не подтверждено] → UNVERIFIABLE + конкретная внешняя проверка;
выдаёт вердикты (CONFIRMED / WEAKLY SUPPORTED / CONTRADICTED / UNVERIFIABLE / OUTDATED / TAG TOO HIGH/LOW) и пишет user/verification_report.md.

Если запускаешь частично — передай агенту номер секции (он поддерживает partial).

Ключевые инварианты верификации

Агент их держит; проверь на выходе:

[практика — Telegram] никогда не апгрейдится до [норма] количеством сообщений — только текст закона/офиц. разъяснение меняет уровень.
Приватные консультантские чаты — не источник ни в каком виде.
Claim без найденного источника → UNVERIFIABLE + пункт в «список внешних проверок», не «похоже на правду».
as-of: источник старше текущего года на процедурном → OUTDATED + живая сверка.

Полнота практики

Если user/slices/ есть — они войдут в проверку практики (Grep). Если нет — практика проверяется только по опубликованному дайджесту; пометь сниженную полноту практики в отчёте.

Формат отчёта

Read the full file on GitHub · 63 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 · 63 lines · 60 tokens per session scan A 477f6f733eb8

Subscribe to this mod's changes

dnv-verify is a skill published in the GitHub repository acogood/spain-dnv-consultant (83 stars, last pushed 3mo ago), licensed MIT. It adds 60 tokens to every session and 772 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 2026-08-30.

Legal and compliance Research

dnv-verify next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
dnv-verifyacogood/spain-dnv-consultant	Skill	83	3mo ago	MIT	A	60	Claude Code
fto-triageanthropics/claude-for-legal	Skill	9.9k	3d ago	Apache-2.0	A	81	Claude Code
legal-holdanthropics/claude-for-legal	Skill	9.9k	3d ago	Apache-2.0	A	68	Claude Code
specification-writingwanshuiyin/Auto-claude-code-research-in-sleep	Skill	19k	3d ago	MIT	A	49	Claude Code
terms-of-servicegenspark-ai/genoffice	Skill	12k	yesterday	Apache-2.0	A	32	Claude Code, Codex
x-scorecardx-cmd/x-cmd	Skill	4.7k	6d ago	Apache-2.0	A	57	Claude Code, Codex
gesellschaftsrechtliche-satzungen-agbKlotzkette/claude-fuer-deutsches-recht	Skill	1.8k	yesterday	Apache-2.0	A	69	Claude Code

spain-dnv-consultant: Skill for Claude Code