verifiable-legal-document

verifiable-legal-document is a skill for Claude Code, Codex from sergeionlyart/minius_codex_lab. It costs 69 tokens per session (1,261 once invoked), scanned A, original, Apache-2.0.

A Russian-language workflow for producing legal documents with claim identifiers, linked supporting passages, hashes, and validation reports.

In plain words
What is it for?
Use it for evidence-backed HTML or DOCX legal documents and their source appendices.
Why use it?
It makes important statements traceable to exact evidence and can stop release when required checks fail.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); $skill-name invocation.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 tools/verifiable_document/ingest.py \.

Good fit Use it for evidence-backed HTML or DOCX legal documents and their source appendices.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/sergeionlyart/minius_codex_lab
agentmods
npx agentmods add skills/sergeionlyart/minius_codex_lab/verifiable-legal-document

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 verifiable-legal-document

README.md
[![agentmods](https://agentmods.dev/badge/skills/sergeionlyart/minius_codex_lab/verifiable-legal-document/github.svg)](https://agentmods.dev/skills/sergeionlyart/minius_codex_lab/verifiable-legal-document)
Your own site
<a href="https://agentmods.dev/skills/sergeionlyart/minius_codex_lab/verifiable-legal-document"><img src="https://agentmods.dev/badge/skills/sergeionlyart/minius_codex_lab/verifiable-legal-document/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 verifiable-legal-document

Your own site · 80×15
<a href="https://agentmods.dev/skills/sergeionlyart/minius_codex_lab/verifiable-legal-document"><img src="https://agentmods.dev/badge/skills/sergeionlyart/minius_codex_lab/verifiable-legal-document.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,261 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 $0.00069 $0.01261
Opus 5 $0.00034 $0.00630
Sonnet 5 $0.00014 $0.00252
Haiku 4.5 $0.00007 $0.00126

Measured 11d ago against content hash 681bc6d47c48, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

verifiable-legal-document 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 11d 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/verifiable-legal-document/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Проверяемый юридический документ

Contract

  • Job-to-be-done: собрать юридический документ, где существенные claims проверяются по внутренним ссылкам, evidence и hashes.
  • Inputs: approved structured spec, evidence ledger, source fragments, output format и validation policy.
  • Outputs: HTML/DOCX, evidence appendix, manifests/hashes и machine-readable validation report.
  • Evidence and safety: не добавляй содержание вне ledger; минимизируй source fragments и проверяй metadata перед распространением.
  • Stop conditions: останови build/release при missing evidence, broken anchors, hash mismatch, unsafe path или blocker validation.
  • Acceptance test: вручную открой три claim links/backlinks, сверь fragments с источником и повтори validator.

Цель

Сделать проверку тезиса быстрой и локальной: из основного текста пользователь кликает ссылку и попадает в том же HTML/DOCX на точное предложение/абзац приложения, подтверждающее тезис. Приложение хранит provenance, context, version и hash.

Канонический pipeline

источники → адресуемые evidence units → structured spec JSON → validator → self-contained HTML/DOCX → independent audit

Подробная спецификация: references/document-contract.md и docs/VERIFIABLE_DOCUMENT_SPEC.md.

Evidence model

  • claim_id — уникальный тезис в основном документе.
  • claim_type — fact/legal_proposition/numeric/quotation/interpretation/assumption/recommendation.
  • source_id — конкретный источник/редакция.
  • unit_id — точное адресуемое предложение или абзац.
  • evidence_refs — список unit_id, поддерживающих claim.
  • counterevidence_refs — фрагменты, ограничивающие/опровергающие claim.
  • source SHA-256 и unit SHA-256 защищают от незаметной подмены.

Режим приложения

  1. full — полный нормализованный текст источника разбит на units. Предпочтителен для нормативных актов/судебных решений, если объем, право на воспроизведение и политика позволяют.
  2. evidence-pack — точные cited units с достаточным контекстом, metadata, hash и ссылкой/путем к целому источнику. Используй, если полный документ нельзя законно/технически включить.
  3. page-image evidence — для скана: релевантная страница/область + OCR/extracted text + marker human-verified или needs-human-verification.

Read the full file on GitHub · 107 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 107 lines · 69 tokens per session scan A 681bc6d47c48

Subscribe to this mod's changes

verifiable-legal-document is a skill published in the GitHub repository sergeionlyart/minius_codex_lab (6 stars, last pushed 9d ago), licensed Apache-2.0. It adds 69 tokens to every session and 1,261 once invoked, about $0.0003 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

legal-research-export

A delivery tool for legal research that checks the work and formats it as Markdown or a Word document. It runs an audit before creating the final research report.

kingselyjoe/legal-research-dsh · 55 tokens

evidence-catalog-generator

Organize user-provided evidence materials into evidence catalog entries and fill them into a user-provided or generic DOCX template. The public version contains no real case template, parties, docket numbers, facts, amounts, addresses, or local file paths.

lawyerllsx-dotcom/Legal-Workflow-Chain · 56 tokens

cloud-service-agreement

Draft and fill SaaS agreement templates — cloud contract, MSA, order form, software license, pilot agreement, design partner agreement. Includes variants with SLAs and AI terms. Produces signable DOCX from Common Paper standard forms. Use when user says "SaaS agreement," "cloud contract," "MSA," "order form,"…

open-agreements/open-agreements · 103 tokens

data-privacy-agreement

Draft and fill data privacy contract and agreement templates — DPA, data processing contract, GDPR, HIPAA BAA, business associate agreement, AI addendum. Produces signable DOCX files from Common Paper standard forms. Use when user says "DPA," "data processing agreement," "HIPAA BAA," "business associate agreement," or…

open-agreements/open-agreements · 123 tokens

analyze-document

Forensically analyse a family court document using the 13-point protocol. Use when the user says "analyse this document", "review this affidavit", "what does this report say", "break down this letter", uploads a court document, affidavit, family report, solicitor letter, or any legal document related to their family…

odin33g/family-court-strategist · 71 tokens

case-setup

Set up a new family court case vault from scratch. Use when the user says "set up my case", "start my case vault", "I need to organise my family court case", "help me build a case", "create my evidence vault", or is beginning a new family court matter and needs structure.

odin33g/family-court-strategist · 67 tokens