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 skills add fastrevmd-lab/fwskillsshare --skill sd-onprem-proxmox-deploygit clone --depth 1 https://github.com/fastrevmd-lab/fwskillsshareWrote 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/skills/fastrevmd-lab/fwskillsshare/sd-onprem-proxmox-deploy)<a href="https://agentmods.dev/skills/fastrevmd-lab/fwskillsshare/sd-onprem-proxmox-deploy"><img src="https://agentmods.dev/badge/skills/fastrevmd-lab/fwskillsshare/sd-onprem-proxmox-deploy/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/skills/fastrevmd-lab/fwskillsshare/sd-onprem-proxmox-deploy"><img src="https://agentmods.dev/badge/skills/fastrevmd-lab/fwskillsshare/sd-onprem-proxmox-deploy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00071 | $0.09487 |
| Opus 5 | $0.00036 | $0.04744 |
| Sonnet 5 | $0.00014 | $0.01897 |
| Haiku 4.5 | $0.00007 | $0.00949 |
Grade A, and why
sd-onprem-proxmox-deploy 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 10d 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 — 566 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deploying Security Director On-Prem on Proxmox VE
STATUS: stable (v1.0.0). Procedure below was executed end-to-end on SD On-Prem 26.2.1-5348 on Proxmox VE 9.2, and has since been run to completion three times by the maintainer — the repeat runs the draft label was waiting on. Values in
<angle brackets>are site-specific.
Full step-by-step how-to: references/HOWTO-deploy-sd-onprem-proxmox.md
(complete deployment + log-path + operations guide; this SKILL.md is the summary).
Overview
This is Security Director On-Prem 25/26 — a NEW ATOM-based appliance on single-node RKE2 Kubernetes, NOT Junos Space Security Director. Ignore Space-era guidance: there is no device "schema install", no Space fabric. Version parity (device 26.x + SD 26.x) is not a schema concern. Log analytics ("All Security Events") is gated by an assigned subscription, not a schema. Ingest path =
secmgt/jingestpod →kafka-la→logging/opensearch.
SD On-Prem ships as a KVM appliance: an OS boot disk (qcow2) + two data disks
- a seed ISO carrying first-boot config. Juniper's supported flow targets a
libvirt/virsh host, but Proxmox VE does not run
libvirtd. So we run the vendor.binin extract-only mode (--no-run) to generate the qcow2s + ISO (no KVM needed), then import them into aqm-native VM and skip the vendorlaunch-vm.sh. The VM stays fully Proxmox-managed (snapshots, HA, API).
Artifacts (both files are needed for a fresh install)
| File | Role |
|---|---|
Juniper-Security-Director-<ver>-<build>-kvm.bin (~6 GB) |
Embeds disk-0 (OS qcow2, sha256-verified). Run normally it deploys/upgrades via libvirt; run --no-run it ONLY extracts artifacts (disk-0 + builds disk-1/2 + seed ISO) — no KVM. This is the fresh-install extractor on Proxmox. |
Juniper-Security-Director-<ver>-<build>.tgz (~8 GB) |
The encrypted software bundle the appliance pulls + decrypts at first boot. It is tgz → metadata.json + *-software.zip.psig + *-software.zip → sd_onprem_software.zip (ENCRYPTED). You cannot hand-extract qcow2s from it — it is not the disk source; the .bin is. |
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 566 lines · 71 tokens per session scan A ab0f1f3a1691
sd-onprem-proxmox-deploy is a skill published in the GitHub repository fastrevmd-lab/fwskillsshare (8 stars, last pushed 13d ago), licensed MIT. It adds 71 tokens to every session and 9,487 once invoked, about $0.0004 per session on Opus 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 2026-08-31.
Other skills, from other repositories
fmc-firewall-ops
Cisco Secure Firewall FMC — access policy search, rule inspection, FTD device targeting, multi-FMC profile management. Use when searching firewall rules by IP or FQDN, checking if host A can reach host B through the firewall, auditing FMC access policies, or reviewing SGT-based segmentation rules.
fortimanager-ops
FortiManager policy operations — ADOM inventory, policy package review, recursive object resolution, revision history, install preview, and gated package install. Use when auditing FortiGate firewall policy at the MANAGER level (intent), reviewing ADOM policy packages, or planning a package install with rollback…
fortianalyzer-ops
FortiAnalyzer log operations — policy-filtered traffic log query within a bounded time window, offset pagination, per-policy activity checks, and logging-device inventory. Use when asking whether traffic actually matched a firewall rule, investigating what hit a policy, or determining whether a rule is genuinely…
fortigate-ops
FortiGate device operations — system status, interfaces, routing, IPsec VPN tunnel state with phase 1 and phase 2 reported separately, HA member identification, per-VDOM scoping, and manager-vs-device drift detection. Use when asking what a FortiGate is ACTUALLY doing right now, whether a tunnel is up, or whether the…
meraki-security-appliance
Cisco Meraki MX security appliance (read-only) — L3/L7 firewall rules, content filtering, IDS/IPS and AMP settings, site-to-site VPN, traffic shaping via Cisco's official Meraki MCP. Use when auditing Meraki firewall rules, reviewing content filtering, or inspecting MX VPN configuration.
azure-network-ops
Azure cloud networking -- VNets, NSGs, ExpressRoute, VPN Gateways, Azure Firewalls, Load Balancers, Application Gateways, Route Tables, Network Watcher, Private Endpoints, DNS zones. Use when auditing Azure VNets, troubleshooting hybrid connectivity (ExpressRoute/VPN), checking NSG rules, inspecting firewall policies…