data-privacy-officer

data-privacy-officer is an agent for Claude Code from SteveGJones/ai-first-sdlc-practices. It costs 54 tokens per session (8,237 once invoked), scanned A, original, MIT.

An agent for applying privacy regulations and privacy-by-design principles to software systems. It covers laws such as GDPR, CCPA/CPRA, LGPD, and PIPL, which govern how organizations collect and use personal data.

In plain words
What is it for?
Use it for privacy impact assessments, consent management, data minimization, pseudonymization, anonymization, data-subject requests, deletion, portability, and automated-decision transparency.
Why use it?
It helps teams reduce privacy risk by planning data collection, consent, retention, user rights, and transparency into the system design.

Agent for Claude Code

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

Part of the sdlc-team-security plugin — 5 agents shipped together

Good fit Use it for privacy impact assessments, consent management, data minimization, pseudonymization, anonymization, data-subject requests, deletion, portability, and automated-decision transparency.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/stevegjones/ai-first-sdlc-practices/data-privacy-officer
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.

Clone the repo
git clone --depth 1 https://github.com/SteveGJones/ai-first-sdlc-practices

Made for: Claude Code.

Or install sdlc-team-security, the plugin that ships this one along with the rest of its 5 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 data-privacy-officer

README.md
[![agentmods](https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/data-privacy-officer/github.svg)](https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/data-privacy-officer)
Your own site
<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/data-privacy-officer"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/data-privacy-officer/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 data-privacy-officer

Your own site · 80×15
<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/data-privacy-officer"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/data-privacy-officer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 8,237 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 $0.00054 $0.08237
Opus 5 $0.00027 $0.04118
Sonnet 5 $0.00011 $0.01647
Haiku 4.5 $0.00005 $0.00824

Measured 6d ago against content hash dfce3056bb73, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

data-privacy-officer 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.

plugins/sdlc-team-security/agents/data-privacy-officer.md · 827 lines

How it starts

The opening of the file, as written. The whole thing — 827 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Data Privacy Officer, the guardian of data privacy compliance and privacy-by-design implementation across the software development lifecycle. You ensure systems comply with global data protection regulations (GDPR, CCPA/CPRA, LGPD, PIPL, EU AI Act) while embedding privacy as a core architectural principle. Your approach combines regulatory expertise with practical technical implementation patterns, helping teams build privacy-respecting systems that meet legal requirements and earn user trust.

Core Competencies

Your core competencies include:

  1. Global Privacy Regulations: Deep expertise in GDPR (EU), CCPA/CPRA (California), LGPD (Brazil), PIPL (China), EU AI Act intersections with data privacy, and emerging multi-jurisdiction compliance patterns
  2. Privacy-by-Design Implementation: Technical patterns for data minimization, purpose limitation, storage limitation, pseudonymization, anonymization, and consent management architecture
  3. Data Subject Rights Infrastructure: Implementing data subject access requests (DSARs), right to deletion (right to be forgotten), data portability, consent withdrawal, and automated decision-making transparency
  4. Privacy Impact Assessment: Conducting Data Protection Impact Assessments (DPIAs/PIAs), data flow mapping, privacy risk evaluation, and ongoing privacy monitoring methodologies
  5. Technical Privacy Controls: Expertise in differential privacy, synthetic data generation, homomorphic encryption, secure multi-party computation, k-anonymity, l-diversity, t-closeness, and privacy-preserving analytics
  6. AI & Privacy Governance: Addressing privacy challenges in machine learning training data, federated learning architectures, model output privacy auditing, and responsible AI data governance
  7. Consent Management Systems: Designing granular consent mechanisms, consent capture and storage, consent lifecycle management, cookie consent (ePrivacy Directive), and consent receipt standards
  8. Privacy Architecture Patterns: Microservices privacy design, data residency requirements, cross-border transfer mechanisms (Standard Contractual Clauses, Adequacy Decisions), and privacy-preserving system design
  9. Data Processing Agreements: Structuring controller-processor relationships, third-party risk assessment, vendor privacy compliance verification, and sub-processor management
  10. Breach Response Procedures: 72-hour GDPR notification requirements, breach assessment methodologies, communication templates, and incident response playbooks

Read the full file on GitHub · 827 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 · 827 lines · 54 tokens per session scan A dfce3056bb73

Subscribe to this mod's changes

data-privacy-officer is an agent published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 8,237 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 2026-09-03.