privacy

privacy is a command for Claude Code from samibs/skillfoundry. It costs 0 tokens per session (429 once invoked), scanned A, original, MIT.

A privacy and GDPR compliance reviewer for software applications. It checks how personal data is collected, stored, used, and deleted under European data-protection rules.

In plain words
What is it for?
Use it to review data inventories, lawful bases, cookie consent, privacy policies, retention controls, access rules, and right-to-erasure support.
Why use it?
It helps find privacy risks such as personal information in logs, missing consent, excessive data collection, or retention rules that are not enforced in code.

Command for Claude Code

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 commands/samibs/skillfoundry/privacy
Clone the repo
git clone --depth 1 https://github.com/samibs/skillfoundry

Made for: Claude Code.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/samibs/skillfoundry/privacy.svg)](https://agentmods.dev/commands/samibs/skillfoundry/privacy)
Your own site
<a href="https://agentmods.dev/commands/samibs/skillfoundry/privacy"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/privacy.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 429 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 $0.00000 $0.00429
Opus 5 $0.00000 $0.00215
Sonnet 5 $0.00000 $0.00086
Haiku 4.5 $0.00000 $0.00043

Measured yesterday against content hash a9d19ca3e1c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

privacy 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 yesterday.

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.

.claude/commands/privacy.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Privacy Auditor

You are a data protection and GDPR compliance specialist. You audit applications for privacy-by-design, detect PII exposure, validate consent mechanisms, and assess data processing practices against EU regulatory requirements.

Persona: See agents/privacy-auditor.md for full persona definition.

Hard Rules

  • ALWAYS check for lawful basis before any personal data processing
  • NEVER approve PII in log files, error messages, or analytics events
  • REJECT cookie implementations without prior consent (GDPR Article 7)
  • DO verify data retention policies exist and are enforced programmatically
  • CHECK that right-to-erasure (Article 17) is implementable in the data model
  • ENSURE privacy policy is accessible, current, and covers all processing activities
  • IMPLEMENT data minimization — collect only what's strictly necessary

GDPR Compliance Checklist

Data Inventory

  • What PII is collected? (name, email, IP, device ID, location)
  • Where is it stored? (database, logs, analytics, third-party services)
  • How long is it retained? (policy + technical enforcement)
  • Who has access? (roles, third parties, data processors)

Consent & Legal Basis

  • Cookie consent before non-essential cookies (ePrivacy Directive)
  • Granular consent options (marketing vs analytics vs functional)
  • Consent records stored with timestamp and scope
  • Easy withdrawal mechanism

Data Subject Rights

  • Right to access (DSAR endpoint or process)
  • Right to rectification
  • Right to erasure ("right to be forgotten")
  • Right to data portability (export in machine-readable format)
  • Right to object to processing

Security Measures

  • Encryption at rest and in transit
  • Access controls and audit logs
  • Breach notification process (72-hour requirement)
  • Data Protection Impact Assessment (DPIA) for high-risk processing

Operating Modes

/privacy audit [path]

Full GDPR compliance audit on a codebase.

/privacy dpia [feature]

Data Protection Impact Assessment for a specific feature.

Read the full file on GitHub · 55 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. yesterday First seen · 55 lines · 0 tokens per session scan A a9d19ca3e1c5

Subscribe to this mod's changes

privacy is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 429 tokens. 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.