privacy-doc-generator

privacy-doc-generator is an agent for Claude Code from acaprino/daodan. It costs 116 tokens per session (4,197 once invoked), scanned A, original, MIT.

An agent that drafts and audits privacy documents from a ROPA-driven model. A ROPA, or Record of Processing Activities, records how an organization uses personal data.

In plain words
What is it for?
Use it for Privacy Policies, Cookie Policies, data-processing agreements, consent notices, and data-protection impact assessments under the listed privacy laws and frameworks.
Why use it?
It organizes the underlying data-processing details before writing, helping expose missing information and unsupported assumptions in privacy documents.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the business plugin — 1 skill, 3 agents shipped together

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.

agentmods
npx agentmods add agents/acaprino/daodan/privacy-doc-generator
Clone the repo
git clone --depth 1 https://github.com/acaprino/daodan

Made for: Claude Code.

Or install business, the plugin that ships this one along with the rest of its 1 skill, 3 agents.

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 privacy-doc-generator

README.md
[![agentmods](https://agentmods.dev/badge/agents/acaprino/daodan/privacy-doc-generator.svg)](https://agentmods.dev/agents/acaprino/daodan/privacy-doc-generator)
Your own site
<a href="https://agentmods.dev/agents/acaprino/daodan/privacy-doc-generator"><img src="https://agentmods.dev/badge/agents/acaprino/daodan/privacy-doc-generator.svg" alt="Measured on agentmods" height="20"></a>
Per session 116 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,197 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00116 $0.04197
Opus 5 $0.00058 $0.02099
Sonnet 5 $0.00023 $0.00839
Haiku 4.5 $0.00012 $0.00420

Measured 6d ago against content hash dcbc758215b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

privacy-doc-generator 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 6d 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.

exports/claude/plugins/business/agents/privacy-doc-generator.md · 419 lines

How it starts

The opening of the file, as written. The whole thing — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GOLDEN RULES

  • NEVER generate legal text without gathering context first -- questionnaire before drafting
  • Every clause must link to its normative basis (article, guideline, recital)
  • Output is NEVER a substitute for licensed attorney review -- flag this prominently
  • Mark assumptions and gaps as "NON SPECIFICATO" so the user knows what needs human review
  • Use plain language -- avoid legalese unless legal precision requires it

INTERNAL MODEL: ROPA-DRIVEN GENERATION

Build an internal simplified ROPA (Record of Processing Activities, Art. 30 GDPR) before generating any document. The policy text derives from this structured model -- not the other way around.

ROPA nodes:

  • ProcessingActivity, Purpose, LegalBasis, DataCategory, DataSubject
  • Recipient, TransferMechanism, RetentionRule, SecurityMeasure

Why: policies built from structured data are auditable, consistent, and updatable. Free-text-first generation produces "beautiful but technically false" documents.


PHASE 0: REGULATORY DELTA CHECK

Trigger: This phase activates when the user passes an existing compliance document to review, update, audit, check, or assess. If the interaction is a brand-new document generation with no existing file, skip to PHASE 1.

Step 0.1 -- Extract normative context from document:

  • Read the file and identify: jurisdictions covered, normative sources cited (GDPR articles, EDPB guidelines, Garante provvedimenti, etc.), generation date or last-update date from metadata block
  • Build a list of "normative dependencies" -- the specific regulations, guidelines, and rulings the document relies on
  • If the document lacks a metadata block with date, ask the user when it was last generated/updated

Step 0.2 -- Targeted regulatory search:

  • For each normative dependency, run WebSearch queries using year-based terms covering the years from document date to today (e.g. guidelines 2025 2026) as proxy for date filtering:
    • site:edpb.europa.eu guidelines {topic} {year} for new EDPB guidelines
    • site:garanteprivacy.it provvedimenti {topic} {year} for new Garante provvedimenti
    • site:eur-lex.europa.eu {regulation} {year} for legislative amendments
    • site:curia.europa.eu {topic} {year} for relevant new CJEU rulings
  • Cap at 4-6 targeted queries, prioritizing jurisdictions and sources most central to the document. If many jurisdictions, focus on primary ones and note others as unchecked
  • If WebSearch returns no results for a source, note it as "unable to verify" in the output. If all queries fail, report the delta check as inconclusive and proceed to PHASE 1

Read the full file on GitHub · 419 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. 6d ago First seen · 419 lines · 116 tokens per session scan A dcbc758215b1

Subscribe to this mod's changes

privacy-doc-generator is an agent published in the GitHub repository acaprino/daodan (8 stars, last pushed 2d ago), licensed MIT. It adds 116 tokens to every session and 4,197 once invoked, about $0.0006 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 agents, from other repositories

brief

Draft and redline contracts and policies — NDAs, MSAs, employment agreements, vendor contracts — with stage-appropriate risk framing. Use when a contract needs to be written from scratch or reviewed for risk. Trigger with "draft an NDA", "redline this contract".

jeremylongshore/tons-of-skills-marketplace · 57 tokens

terms

Drafts GDPR-compliant privacy policies, Terms of Service, cookie notices, and DPAs sized to company stage. Use when you need a privacy policy, ToS, or data processing agreement written or audited. Trigger with "draft my privacy policy", "review my terms of service".

jeremylongshore/tons-of-skills-marketplace · 59 tokens

patent-creator

Drafts complete patent applications autonomously through 6-phase workflow (estimated 55-80 min). Produces markdown + SVG output requiring DOCX/PDF conversion before USPTO filing.

RobThePCGuy/Claude-Patent-Creator · 42 tokens

healthit-information-manager

Use for Health Information Manager work in Health IT & Informatics including HIM, ROI, retention, legal health record, chart integrity.

ajhcs/healthcare-agents · 31 tokens

governance-enforcer

Interactive assistant for setting up and enforcing document governance in a trestle workspace. Set up governance templates. Validate documents against them. Identify violations. Help fix non-compliant documents. Use when users need help with document governance, template enforcement, or fixing governance validation…

oscal-compass-lab/compliance-trestle-skills · 94 tokens

chronology-builder

Isolated worker that reads case documents iteratively and extracts sourced timeline events (date, neutral fact, mandatory document+locus provenance, undisputed/alleged/contested status, party attribution). Deduplicates and cross-references across documents and languages. Emits events.json for the legal-chronology…

fedec65/bettercallclaude · 103 tokens