redaction-and-disclosure

redaction-and-disclosure is a skill for Claude Code, Codex from sergeionlyart/minius_codex_lab. It costs 75 tokens per session (783 once invoked), scanned A, original, Apache-2.0.

A data-safety checklist for removing sensitive information before material is searched, shared, or sent outside the project. It also records what was removed and whether approval is needed.

In plain words
What is it for?
Use it to make a minimized copy of a document, inspect its metadata and attachments, log redactions, assess remaining risks, and identify required human approval before external disclosure.
Why use it?
It helps prevent secrets, personal details, hidden metadata, and other restricted information from being disclosed accidentally. It keeps the original unchanged and stops when the purpose, permission, or remaining risk is unclear.

Skill for Claude CodeCodex

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

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/check_repo_safety.py --staged.

Good fit Use it to make a minimized copy of a document, inspect its metadata and attachments, log redactions, assess remaining risks, and identify required human approval before external disclosure.

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/redaction-and-disclosure

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 redaction-and-disclosure

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/sergeionlyart/minius_codex_lab/redaction-and-disclosure"><img src="https://agentmods.dev/badge/skills/sergeionlyart/minius_codex_lab/redaction-and-disclosure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 783 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 $0.00075 $0.00783
Opus 5 $0.00037 $0.00392
Sonnet 5 $0.00015 $0.00157
Haiku 4.5 $0.00007 $0.00078

Measured 12d ago against content hash 64548c6680e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

redaction-and-disclosure 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 12d 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/redaction-and-disclosure/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Redaction и допустимость раскрытия

Contract

  • Job-to-be-done: создать минимизированную копию и обоснованное решение о допустимости конкретного раскрытия.
  • Inputs: материал, цель/получатель, data classification, правовые и организационные правила.
  • Outputs: redacted copy, redaction log, residual-risk findings и требуемое human approval.
  • Evidence and safety: оригинал не изменяй; учитывай текст, metadata, вложения, скрытые слои и косвенную идентификацию.
  • Stop conditions: останови раскрытие при неизвестной цели, полномочиях, классе, неудаляемом риске или отсутствии approval.
  • Acceptance test: вручную проверь копию поиском удаленных значений и просмотром metadata/рендера отдельным reviewer.

Цель

Снизить объем раскрываемых данных до минимально необходимого и сделать решение о раскрытии проверяемым. Этот skill не заменяет решение уполномоченного подразделения по безопасности/защите данных.

Процедура

  1. Определи target action: web query, remote push, external email/export, public release, subagent/MCP.
  2. Определи data class по SECURITY.md и внутренней политике. Не понижай класс.
  3. Создай inventory чувствительных элементов:
    • personal identifiers;
    • case/party names;
    • addresses/contact/bank/health data;
    • secrets/tokens/keys;
    • official-use/restricted markings;
    • investigation/sealed/professional secrets;
    • local paths/usernames;
    • hidden metadata/comments/tracked changes;
    • embedded files/macros.
  4. Проверь necessity каждого элемента. Удали, обобщи, псевдонимизируй или замени surrogate ID.
  5. Для веб-запроса сформируй sanitized query, не позволяющий восстановить конкретное дело.
  6. Для Git проверь staged set, а не только working tree:
python3 scripts/check_repo_safety.py --staged
  1. Для DOCX/PDF проверь metadata, comments, hidden text и attachments; после redaction повторно извлеки текст/metadata для контроля.
  2. Создай disclosure log:
    • action/date/actor;
    • files/fields;
    • class;
    • redactions;
    • legal/organizational basis;
    • recipient/system;
    • approval;
    • residual risk.
  3. Если безопасная минимизация невозможна, запрети внешнее действие и предложи локальный/offline путь.

Read the full file on GitHub · 74 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. 12d ago First seen · 74 lines · 75 tokens per session scan A 64548c6680e5

Subscribe to this mod's changes

redaction-and-disclosure is a skill published in the GitHub repository sergeionlyart/minius_codex_lab (6 stars, last pushed 10d ago), licensed Apache-2.0. It adds 75 tokens to every session and 783 once invoked, about $0.0004 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

contract-guardian

A contract-review workflow that checks agreements for risks, links important findings to relevant laws, and produces a written review. It covers common agreements such as sales, leases, loans, services, contracting, and intellectual property.

lawyerllsx-dotcom/Legal-Workflow-Chain · 245 tokens

法律周报

A legal-news briefing workflow that finds recent court and legal-practice articles, scores them against selected criteria, and archives chosen items in a local Obsidian notes folder. Obsidian is a local note-taking application.

lawyerllsx-dotcom/Legal-Workflow-Chain · 242 tokens

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