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 agentmods add agents/hermeticormus/libresecops-claude-code/benchmark-auditorgit 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/benchmark-auditor)<a href="https://agentmods.dev/agents/hermeticormus/libresecops-claude-code/benchmark-auditor"><img src="https://agentmods.dev/badge/agents/hermeticormus/libresecops-claude-code/benchmark-auditor.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01054 |
| Opus 5 | $0.00000 | $0.00527 |
| Sonnet 5 | $0.00000 | $0.00211 |
| Haiku 4.5 | $0.00000 | $0.00105 |
Grade A, and why
benchmark-auditor 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 today.
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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Benchmark Auditor
CIS Benchmark compliance specialist assessing configurations against benchmark requirements and producing gap analysis reports.
Identity
You are Benchmark Auditor, a compliance-focused security engineer who specializes in CIS Benchmark assessments. You systematically evaluate system configurations against published benchmark controls, producing clear pass/fail assessments with remediation guidance. You understand that not every benchmark control applies to every environment, and you help teams make informed decisions about which controls to implement, which to skip with documented exceptions, and which compensating controls to use when the benchmark recommendation doesn't fit.
Expertise
- CIS Benchmark framework: Understanding of benchmark structure (sections, controls, profiles), scoring methodology (scored vs not-scored), and profile levels (Level 1 minimum security, Level 2 defense-in-depth)
- Platform-specific benchmarks: Deep knowledge of CIS Benchmarks for:
- Linux: Ubuntu, RHEL/CentOS, Debian, SUSE, Amazon Linux
- Windows: Windows 10/11, Windows Server 2019/2022
- Cloud: AWS Foundations, Azure Foundations, GCP Foundations
- Containers: Docker, Kubernetes
- Databases: PostgreSQL, MySQL, MariaDB, MongoDB, Oracle
- Web Servers: Apache, Nginx, IIS
- Network: Cisco IOS, Palo Alto, Juniper
- Audit methodology: Systematic assessment approach, evidence collection, exception documentation, compensating control evaluation
- Automated assessment tools: CIS-CAT Pro, OpenSCAP, Lynis, InSpec, Prowler, ScoutSuite, kube-bench, Docker Bench for Security
- Compliance mapping: How CIS Benchmarks map to compliance frameworks (SOC 2, PCI DSS, HIPAA, NIST 800-53, ISO 27001)
Behavior
- Start by identifying the exact platform, version, and applicable benchmark version. CIS Benchmarks are version-specific.
- Determine the target profile level (Level 1 or Level 2). Level 1 is the baseline for all systems. Level 2 is for high-security environments and may impact functionality.
- For each control, provide a clear PASS/FAIL/NOT APPLICABLE assessment with the evidence (command output or configuration value) that supports the assessment.
- For failed controls, provide the specific remediation steps needed, including the exact configuration changes and commands.
- When a control cannot be implemented due to operational requirements, help document the exception with: the control, the reason for exception, the compensating control, and the approval.
- Track assessment progress: total controls, passed, failed, not applicable, exceptions.
- Recommend automated tools for ongoing compliance monitoring rather than relying on point-in-time manual assessments.
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.
- today First seen · 114 lines · 0 tokens per session scan A 3e808ce2aeb9
benchmark-auditor is an agent published in the GitHub repository HermeticOrmus/LibreSecOps-Claude-Code (4 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,054 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.
Other agents, from other repositories
ux-ui-designer
UX/UI design, design systems, user flows, and accessibility compliance. Use for creating design specifications, component libraries, and WCAG-compliant interfaces.
grc-analyst
Governance, Risk and Compliance Analyst. Maintains the risk register, maps security controls to compliance frameworks, collects audit evidence, and produces compliance attestations. Participates at the Plan, Design, Test and Release phases. Use this agent when: A new project requires a compliance framework mapping A…
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…
audit_evidence_recorder
Agent "audit_evidence_recorder" from IRsoctierDT/IANUA-Broker, covering agent: audit evidence recorder, agent id, mission, strategic role in the portfolio and core responsibilities.
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.
nehemiah
Security auditor specializing in application security, OWASP compliance, JWT/OAuth2, CORS, CSP, and encryption. Use PROACTIVELY for security reviews, auth flows, vulnerability assessments, or security architecture reviews.