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/commands/hermeticormus/libresecops-claude-code/privacy-review)<a href="https://agentmods.dev/commands/hermeticormus/libresecops-claude-code/privacy-review"><img src="https://agentmods.dev/badge/commands/hermeticormus/libresecops-claude-code/privacy-review/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/commands/hermeticormus/libresecops-claude-code/privacy-review"><img src="https://agentmods.dev/badge/commands/hermeticormus/libresecops-claude-code/privacy-review.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 | $0.00031 | $0.01080 |
| Opus 5.5 | $0.00012 | $0.00432 |
| Sonnet 5.5 | $0.00006 | $0.00216 |
| Haiku 4.5 | $0.00003 | $0.00108 |
Grade A, and why
privacy-review 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/privacy-review
Review a system, feature, or architecture for privacy concerns, producing a structured assessment with findings categorized by privacy principle and regulatory requirement.
Trigger
Use when evaluating the privacy posture of a system or feature. Appropriate for:
- New feature design review (before development)
- Architecture review for privacy implications
- Pre-launch privacy assessment
- Code review focused on personal data handling
- Third-party integration privacy assessment
- Post-incident privacy evaluation
Input
- System/feature description: What the system does and what data it processes
- Architecture details: System components, data stores, external services, APIs
- Data categories: Types of personal data collected or processed (if known)
- Code or configuration (optional): Relevant code handling personal data
- Regulatory context: Applicable privacy regulations (GDPR, CCPA, HIPAA, etc.)
- Intended users: Who the system serves (consumers, employees, patients, children, etc.)
Process
-
Personal data identification -- Identify all personal data in the system:
- Direct identifiers (name, email, phone, SSN, IP address)
- Indirect identifiers (location, device fingerprint, behavioral patterns)
- Sensitive data (health, biometric, racial/ethnic origin, political opinions, religious beliefs)
- Derived data (inferences, profiles, scores, predictions)
-
Purpose assessment -- For each data element, evaluate:
- What is the stated purpose of collection?
- Is the data necessary for that purpose (data minimization)?
- Could the purpose be achieved with less data or anonymized data?
- Are there secondary uses beyond the stated purpose (function creep)?
-
Legal basis evaluation -- For each processing activity:
- What is the legal basis (consent, contract, legitimate interest, legal obligation)?
- Is the legal basis appropriate for this type of processing?
- If consent, is it freely given, specific, informed, and unambiguous?
- If legitimate interest, has a balancing test been conducted?
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 · +5 lines · +31 tokens per session 2bd38c24fbfe
- 1mo ago First seen · 105 lines · 0 tokens per session scan A 0620819bc246
privacy-review is a command published in the GitHub repository HermeticOrmus/LibreSecOps-Claude-Code (4 stars, last pushed 9d ago), licensed MIT. It adds 31 tokens to every session and 1,080 once invoked, about $0.0001 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 commands, from other repositories
dc-review
Two-stage code review orchestrator. Stage 1 (spec compliance, binary) → Stage 2 (code quality, severity-tagged). Stage 2 skipped if Stage 1 fails. Lane-aware (trivial = Stage 2 only).
review-epo-claims
Analyze patent claims for EPO Art. 84 EPC compliance - clarity, conciseness, support by description.
CLAUDE_CODE_F033_IOSS_OSS
A code-review command for IOSS and OSS compliance. IOSS and OSS are European Union VAT schemes for reporting tax on cross-border sales.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.