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.
npx skills add magnus919/agent-skills --skill privacy-engineeringgit clone --depth 1 https://github.com/magnus919/agent-skillsWrote 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.
[](https://agentmods.dev/skills/magnus919/agent-skills/privacy-engineering)<a href="https://agentmods.dev/skills/magnus919/agent-skills/privacy-engineering"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/privacy-engineering/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.
<a href="https://agentmods.dev/skills/magnus919/agent-skills/privacy-engineering"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/privacy-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00098 | $0.03335 |
| Opus 5 | $0.00049 | $0.01667 |
| Sonnet 5 | $0.00020 | $0.00667 |
| Haiku 4.5 | $0.00010 | $0.00333 |
Grade A, and why
privacy-engineering 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Privacy Engineering
Translate privacy principles into engineering artifacts that are observable, testable, and verifiable. This skill does not provide legal advice and does not substitute for jurisdiction-specific regulatory interpretation; those belong to qualified legal counsel and to legal-strategy.
Disclaimer
This skill does not provide legal advice. It provides an engineering method for translating privacy requirements (whether derived from GDPR, CCPA, HIPAA, internal policy, or contractual obligations) into verifiable technical artifacts. Jurisdiction-specific regulatory interpretation must be escalated to qualified legal counsel. Do not use this skill to determine whether a specific regulatory regime applies or to interpret the legal scope of a privacy obligation.
When to use
Load this skill when the task involves engineering privacy into a system, feature, or data flow:
- Map data classification, purpose, processing activities, access patterns, retention periods, deletion workflows, residency constraints, and consent flows.
- Define privacy acceptance criteria that are testable and verifiable — not policy prose alone.
- Produce a data-lifecycle record that traces data from collection through deletion across all stores and backups.
- Design a retention/deletion verification plan with measurable success conditions (e.g., "data for user X deleted from all primary stores within Y hours of verified account closure").
- Map data flows across service boundaries, tenant boundaries, and geographic regions, identifying where PII transits or resides.
- Review a change (feature, schema, integration, AI pipeline) for privacy impact and produce a privacy change review.
- Address privacy implications of agent traces (LLM conversation logs, tool-call history) and product analytics telemetry.
- Integrate consent and revocation signals into system behavior.
- Apply data minimization and purpose limitation at the engineering level.
- Define tenant-boundary isolation requirements for multi-tenant data.
What ships with it
8 files 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.
- evals/evals.json 18 KB
- README.md 4.7 KB
- references/discovery-brief.md 18 KB
- templates/data-flow-and-access-map.md 1.8 KB
- templates/data-lifecycle-record.md 2.3 KB
- templates/privacy-acceptance-criteria.md 3.2 KB
- templates/privacy-change-review.md 3.2 KB
- templates/retention-deletion-verification-plan.md 5.6 KB
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.
- 9d ago First seen · 285 lines · 98 tokens per session scan A cafdc626caaf
privacy-engineering is a skill published in the GitHub repository magnus919/agent-skills (76 stars, last pushed yesterday), licensed MIT. It adds 98 tokens to every session and 3,335 once invoked, about $0.0005 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.
Other skills, from other repositories
cocoaudit
View and export the append-only session audit trail for regulated environments.
audit-add
Add a clearly marked manual CocoAudit event. Usage: $audit add " ".
audit-export
Export the full CocoAudit trail as a stakeholder-ready compliance document.
audit-verify
Verify CocoAudit event integrity and contract evidence for local CocoPlus artifacts.
audit-ci
V2-native deterministic contract for the owning CocoPlus feature. Executes the behavior formerly delegated to audit-ci skill without registered runtime scripts.
official-doc
Produce a 31C official document (board resolution, formal notice, letter of position, certificate of authority) using the locked corporate template. Authoritative voice, declarative language, reference numbering, and official seal block. Renders to PDF + DOCX. Trigger when the user says "board resolution", "formal…