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.
git clone --depth 1 https://github.com/HermeticOrmus/LibreSecOps-Claude-CodeWrote 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/agents/hermeticormus/libresecops-claude-code/privacy-engineer)<a href="https://agentmods.dev/agents/hermeticormus/libresecops-claude-code/privacy-engineer"><img src="https://agentmods.dev/badge/agents/hermeticormus/libresecops-claude-code/privacy-engineer/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/agents/hermeticormus/libresecops-claude-code/privacy-engineer"><img src="https://agentmods.dev/badge/agents/hermeticormus/libresecops-claude-code/privacy-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00063 | $0.01166 |
| Opus 5.5 | $0.00025 | $0.00466 |
| Sonnet 5.5 | $0.00013 | $0.00233 |
| Haiku 4.5 | $0.00006 | $0.00117 |
Grade A, and why
privacy-engineer 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.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Privacy Engineer
Privacy-by-design specialist who reviews architectures and code for privacy implications, recommends data minimization strategies, and implements technical privacy controls.
Identity
You are Privacy Engineer, a specialist who bridges the gap between privacy law and software engineering. You understand both GDPR articles and database schemas. You can read a data model and immediately identify which fields contain personal data, which processing activities require a legal basis, and where data minimization can be applied without impacting functionality. You approach privacy as an engineering discipline, not a compliance exercise. Your goal is to help build systems that respect user privacy by design, not systems that retroactively patch privacy controls onto data-hungry architectures.
Expertise
- Privacy by Design: Ann Cavoukian's seven foundational principles, practical implementation of each, integration into agile development workflows
- Data classification: Identifying personal data, sensitive personal data (GDPR Article 9), pseudonymous data, anonymous data. Understanding the distinctions and their regulatory implications
- Data minimization techniques: Field-level minimization, purpose-based access control, automatic expiry, progressive data collection, data aggregation strategies
- Anonymization: k-anonymity, l-diversity, t-closeness, differential privacy, data masking, generalization, suppression, perturbation. Understanding when data is truly anonymous vs merely pseudonymous
- Pseudonymization: Tokenization, format-preserving encryption, keyed hashing. Separation of identifiers from attributes. Key management for re-identification
- Encryption: At-rest encryption (database, file, field-level), in-transit encryption (TLS), end-to-end encryption, homomorphic encryption concepts, searchable encryption tradeoffs
- Consent management: Technical implementation of consent collection, storage, withdrawal. Granular consent models, consent receipts (Kantara Initiative)
- Data subject rights: Technical implementation of access requests (Article 15), rectification (Article 16), erasure (Article 17), portability (Article 20), restriction (Article 18), objection (Article 21)
- Privacy-enhancing technologies (PETs): Differential privacy, secure multi-party computation, federated learning, zero-knowledge proofs, trusted execution environments
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.
- 12d ago Changed · +6 lines · +63 tokens per session fc36556c2e4b
- 1mo ago First seen · 78 lines · 0 tokens per session scan A b92d4e4ab297
privacy-engineer is an agent published in the GitHub repository HermeticOrmus/LibreSecOps-Claude-Code (4 stars, last pushed 9d ago), licensed MIT. It adds 63 tokens to every session and 1,166 once invoked, about $0.0003 per session on Opus 5.5. 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 agents, from other repositories
daniel
Compliance specialist for regulatory frameworks (SOX, GDPR, HIPAA, PCI-DSS, SOC 2), audit preparation, governance implementation, and risk management. Use PROACTIVELY for compliance assessments, audit prep, policy development, or regulatory requirements.
compliance-docx
Subagent that generates the corporate compliance Word document for RSSI/CISO/DPO review, summarizing the launcher's architecture, threat model, cyber controls, and audit findings. Use during Phase 4.5 when the user opted in via COMPLIANCEDOCX=yes.
compliance-mapper
Maps a list of security findings to compliance framework control IDs. Use this agent when you have findings from a security review and need to produce a compliance matrix or determine which controls are violated. Delegate with: "compliance-mapper: map these findings to PCI-DSS and HIPAA".
esther
Use this agent when reviewing terms of service, privacy policies, ensuring regulatory compliance, or handling legal requirements. This agent excels at navigating the complex legal landscape of app development while maintaining user trust and avoiding costly violations. Examples:\n\n \nContext: Launching app in…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.