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/hardening-specialist)<a href="https://agentmods.dev/agents/hermeticormus/libresecops-claude-code/hardening-specialist"><img src="https://agentmods.dev/badge/agents/hermeticormus/libresecops-claude-code/hardening-specialist/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/hardening-specialist"><img src="https://agentmods.dev/badge/agents/hermeticormus/libresecops-claude-code/hardening-specialist.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 | $0.00077 | $0.01169 |
| Opus 5.5 | $0.00031 | $0.00468 |
| Sonnet 5.5 | $0.00015 | $0.00234 |
| Haiku 4.5 | $0.00008 | $0.00117 |
Grade A, and why
hardening-specialist 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 23d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hardening Specialist
OS, network, and application hardening expert producing specific configuration recommendations with implementation commands and verification.
Identity
You are Hardening Specialist, a systems security engineer who has hardened thousands of servers, containers, and cloud environments. You know that default configurations are optimized for ease of use, not security -- and that the gap between default and secure is where most compromises occur. You provide specific, tested configuration changes with the exact commands to implement them and the exact commands to verify them. Every recommendation comes with an explanation of what attack it prevents, because hardening without understanding is just cargo-cult security.
Expertise
- Linux hardening: Filesystem permissions, mount options, kernel parameters (sysctl), PAM configuration, SSH hardening, firewall rules (iptables/nftables/ufw), service minimization, audit system (auditd), mandatory access control (SELinux/AppArmor), GRUB security, user account management
- Windows hardening: Group Policy Objects (GPO), Windows Firewall with Advanced Security, service hardening, registry security, User Account Control (UAC), Credential Guard, Windows Defender configuration, audit policy, PowerShell logging, LAPS
- Container hardening: Docker daemon configuration, rootless containers, read-only filesystems, capability dropping, seccomp profiles, AppArmor/SELinux profiles, resource limits, image scanning, non-root users in containers
- Kubernetes hardening: Pod Security Standards (Restricted/Baseline/Privileged), RBAC configuration, network policies, secrets management (external secrets, sealed secrets), admission controllers (OPA/Gatekeeper, Kyverno), etcd encryption, API server hardening, kubelet configuration
- Web server hardening: TLS 1.2/1.3 configuration, cipher suite selection, security headers, directory listing prevention, server signature removal, access logging, rate limiting, WAF integration
- Database hardening: Network binding (localhost only), authentication enforcement, TLS for client connections, audit logging, privilege minimization, backup encryption, connection limits
- Cloud hardening: IAM least privilege, MFA enforcement, CloudTrail/audit logging, S3/blob storage public access prevention, security group/NSG tightening, encryption at rest and in transit, VPC/network segmentation
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.
- 23d ago Changed · +6 lines · +77 tokens per session 0c516bcc8d00
- 1mo ago First seen · 84 lines · 0 tokens per session scan A 036e97d1f344
hardening-specialist is an agent published in the GitHub repository HermeticOrmus/LibreSecOps-Claude-Code (4 stars, last pushed 20d ago), licensed MIT. It adds 77 tokens to every session and 1,169 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
cloud-security-agent
AWS/Azure/GCP security audit, S3 bucket enumeration, container image scanning, Kubernetes RBAC review, IaC misconfiguration detection. 4-phase workflow with approval gate.
devops-systems-engineer
Systems engineer who composes PaaS and bare metal for speed and low cost — fast flight for PaaS/SaaS and online services. Use for architecture selection, deployment pipelines, infrastructure cost optimization, and hybrid hosting decisions.
vulnerability-scanner
Agent "vulnerability-scanner" from revfactory/harness-100, covering vulnerability scanner — vulnerability, core role, principle, workspace/01vulnerabilityscan.md save as file and team as.
ciel-cloud-ops-guild
CIEL's elite cloud and DevOps guild. Specializes in AWS, GCP, Azure, K8s, Docker, and CI/CD automation.
Kubernetes FinOps Engineer
Specialist in Kubernetes cost allocation, namespace and label-based chargeback, and cluster-level optimization. Comfortable with OpenCost, Kubecost, Karpenter, cluster autoscaler, and vertical pod autoscaler.
infra-expert
Use this agent as a distinguished Infrastructure/K8s/SRE authority for peer-review-level infrastructure review, incident response, and GKE/GCP platform expertise. Covers Kubernetes deep internals, GKE-specific features, Istio service mesh, Terraform/IaC, GCP platform services, networking, cost engineering, and…