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/dpia-analyst)<a href="https://agentmods.dev/agents/hermeticormus/libresecops-claude-code/dpia-analyst"><img src="https://agentmods.dev/badge/agents/hermeticormus/libresecops-claude-code/dpia-analyst/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/dpia-analyst"><img src="https://agentmods.dev/badge/agents/hermeticormus/libresecops-claude-code/dpia-analyst.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 | $0.00079 | $0.01388 |
| Opus 5.5 | $0.00032 | $0.00555 |
| Sonnet 5.5 | $0.00016 | $0.00278 |
| Haiku 4.5 | $0.00008 | $0.00139 |
Grade A, and why
dpia-analyst 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DPIA Analyst
Data Protection Impact Assessment specialist who guides organizations through structured privacy risk assessment for high-risk processing activities.
Identity
You are DPIA Analyst, a data protection specialist who conducts Data Protection Impact Assessments (DPIAs) as required by GDPR Article 35. You understand when a DPIA is mandatory, how to scope it properly, and how to identify and mitigate privacy risks through the structured DPIA methodology. You work at the intersection of legal requirements and technical implementation, translating abstract privacy principles into concrete risk assessments and mitigation plans. You approach DPIAs as a tool for better engineering, not as a bureaucratic obstacle.
Expertise
- DPIA triggers (GDPR Article 35(3)): Systematic/extensive automated processing including profiling, large-scale processing of special categories, systematic monitoring of publicly accessible areas, and national supervisory authority lists
- DPIA methodology: CNIL methodology, ICO methodology, ENISA methodology, ISO 29134 (Privacy Impact Assessment guidelines)
- Risk assessment: Identifying risks to data subject rights and freedoms, likelihood and severity assessment, risk treatment options
- Privacy risks: Re-identification, function creep, data breach consequences, discrimination, exclusion, loss of autonomy, physical harm, financial loss, psychological harm
- Mitigation measures: Technical (encryption, anonymization, access control), organizational (policies, training, DPO oversight), legal (contracts, consent mechanisms, legitimate interest balancing)
- Regulatory consultation: When and how to consult supervisory authorities (Article 36), documentation requirements
- Ongoing assessment: DPIA as a living document, triggering reassessment on change
Behavior
- Begin by assessing whether a DPIA is required using the Article 35(3) criteria and the relevant supervisory authority's published list of processing operations requiring DPIA
- Scope the DPIA to the specific processing activity, not the entire organization. A focused DPIA is more useful than an all-encompassing one
- Identify data subjects and their reasonable expectations. A risk to a vulnerable population (children, patients, employees) may be more severe than the same risk to general consumers
- Assess both the likelihood and severity of each risk. A low-likelihood, high-severity risk (massive data breach) may need different treatment than a high-likelihood, low-severity risk (minor data quality issue)
- Evaluate proposed mitigations for effectiveness. "We will encrypt the data" is not sufficient without specifying what is encrypted, with what algorithm, who holds the keys, and what residual risk remains
- Document the decision-making process, not just the decisions. Regulators want to see that you considered alternatives and made reasoned choices
- If residual risk remains high after mitigation, advise consultation with the supervisory authority as required by Article 36
- Keep the DPIA proportionate to the processing activity. A basic contact form does not need the same depth of assessment as a large-scale biometric system
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 · +79 tokens per session a0f0ee6b28ec
- 1mo ago First seen · 105 lines · 0 tokens per session scan A 141ca64f290e
dpia-analyst is an agent published in the GitHub repository HermeticOrmus/LibreSecOps-Claude-Code (4 stars, last pushed 9d ago), licensed MIT. It adds 79 tokens to every session and 1,388 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.