source-provenance

source-provenance is a skill for Claude Code, Codex from sergeionlyart/minius_codex_lab. It costs 62 tokens per session (1,017 once invoked), scanned A, original, Apache-2.0.

A source register and checking process that links each important piece of evidence to its origin, version, retrieval time, exact location, and handling conditions. Evidence provenance means being able to retrace a claim to the source material that supports it.

In plain words
What is it for?
Use it to record sources, publication and effective dates, identifiers, versions, hashes or snapshots where allowed, retrieval metadata, precise locators, evidence excerpts, and unresolved provenance gaps.
Why use it?
It makes research reproducible and exposes sources that cannot be reliably identified, located, or lawfully handled. This reduces the risk of citing the wrong version or losing the basis for a conclusion.

Skill for Claude CodeCodex

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

Good fit Use it to record sources, publication and effective dates, identifiers, versions, hashes or snapshots where allowed, retrieval metadata, precise locators, evidence excerpts, and unresolved provenance gaps.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sergeionlyart/minius_codex_lab/source-provenance
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 sergeionlyart/minius_codex_lab --skill source-provenance
Clone the repo
git clone --depth 1 https://github.com/sergeionlyart/minius_codex_lab

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 source-provenance

README.md
[![agentmods](https://agentmods.dev/badge/skills/sergeionlyart/minius_codex_lab/source-provenance.svg)](https://agentmods.dev/skills/sergeionlyart/minius_codex_lab/source-provenance)
Your own site
<a href="https://agentmods.dev/skills/sergeionlyart/minius_codex_lab/source-provenance"><img src="https://agentmods.dev/badge/skills/sergeionlyart/minius_codex_lab/source-provenance.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,017 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 $0.00062 $0.01017
Opus 5 $0.00031 $0.00508
Sonnet 5 $0.00012 $0.00203
Haiku 4.5 $0.00006 $0.00102

Measured 8d ago against content hash 9758e6dc251c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

source-provenance 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 8d 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/source-provenance/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Source provenance

Contract

  • Job-to-be-done: обеспечить проверяемую цепочку от каждого evidence unit до источника, версии и времени получения.
  • Inputs: локальный/веб-источник, origin, дата, версия, locator и условия доступа.
  • Outputs: source register rows, hashes/snapshots где допустимо, retrieval metadata и unresolved provenance gaps.
  • Evidence and safety: не сохраняй restricted content без разрешения; URL и metadata не должны содержать credentials/PII.
  • Stop conditions: останови использование источника, если origin, версия, locator или lawful handling нельзя установить.
  • Acceptance test: вручную восстанови один evidence unit по register row и сверь его hash/locator.

Цель

Сделать каждый существенный тезис воспроизводимо проверяемым: источник должен быть идентифицирован, сохранен/зафиксирован, оценен, адресуем и связан с точным доказательственным фрагментом.

Минимальная запись источника

Используй поля из references/source-register-fields.md и matters/_template/sources/REGISTER.csv. Обязательны:

  • source_id;
  • title, issuing body/author, type, jurisdiction;
  • identifier/requisites;
  • publication/adoption date;
  • version/as-of и effective dates;
  • official/current/draft/repealed status;
  • retrieval timestamp UTC;
  • official URL либо local path;
  • SHA-256 локальной копии, если файл сохраняется;
  • legal force/authority;
  • reliability и relevance;
  • locator scheme;
  • limitations.

Процедура

  1. Инвентаризация. Перечисли предоставленные и найденные материалы. Не анализируй все одинаково глубоко.
  2. Дедупликация. Сравни identifiers, URL canonicalization, file hashes и содержание. Не удаляй конфликтующие редакции как дубликаты.
  3. Классификация: primary, supporting, contextual, adverse/counterevidence, unreliable/needs verification, reviewed-not-used.
  4. Проверка происхождения. Установи официальный орган/издателя, chain of custody для локального файла и дату получения.
  5. Версионность. Для нормативного акта фиксируй нужную редакцию и период действия; для dataset — schema/methodology version; для веб-страницы — access date и при возможности archived/local snapshot.
  6. Хэширование. Для разрешенных локальных файлов:

Read the full file on GitHub · 80 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. 8d ago First seen · 80 lines · 62 tokens per session scan A 9758e6dc251c

Subscribe to this mod's changes

source-provenance is a skill published in the GitHub repository sergeionlyart/minius_codex_lab (6 stars, last pushed 6d ago), licensed Apache-2.0. It adds 62 tokens to every session and 1,017 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

A Chinese-language legal research workflow for finding laws, regulations, court cases, compensation standards, and legal grounds.

lawyerllsx-dotcom/Legal-Workflow-Chain · 87 tokens

legal-citation-comprehensive

A Chinese and foreign legal-citation tool for checking, completing, explaining, and formatting footnotes under the second edition of a legal citation manual. It handles laws, cases, legal documents, and academic sources when the relevant source material is provided.

lawyerllsx-dotcom/Legal-Workflow-Chain · 119 tokens

legal-fact-checker

A Chinese-language fact-checking guide for legal documents such as contracts, case analyses, legal opinions, and legal assignments. It checks provided drafts against factual and legal support without inventing laws, cases, or facts.

lawyerllsx-dotcom/Legal-Workflow-Chain · 143 tokens

workflow-overview

A workflow guide for handling complex legal matters through assessment, issue identification, source research, reasoning, fact checking, and document output.

lawyerllsx-dotcom/Legal-Workflow-Chain · 63 tokens

tw-legal-rag

A tool for finding real Taiwan court judgments and legal interpretations with verifiable citations before answering questions about Taiwan law.

aa0101181514/tw-legal-rag · 84 tokens

legal-research

A structured system for legal research involving laws, court decisions, academic sources, arguments, and evidence. It separates facts, legal claims, scholarly views, and the author's own analysis.

kingselyjoe/legal-research-dsh · 78 tokens