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 srx-autovpn-full-tunnelgit 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/srx-autovpn-full-tunnel)<a href="https://agentmods.dev/skills/fastrevmd-lab/fwskillsshare/srx-autovpn-full-tunnel"><img src="https://agentmods.dev/badge/skills/fastrevmd-lab/fwskillsshare/srx-autovpn-full-tunnel/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/srx-autovpn-full-tunnel"><img src="https://agentmods.dev/badge/skills/fastrevmd-lab/fwskillsshare/srx-autovpn-full-tunnel.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 | $0.00099 | $0.07559 |
| Opus 5 | $0.00049 | $0.03779 |
| Sonnet 5 | $0.00020 | $0.01512 |
| Haiku 4.5 | $0.00010 | $0.00756 |
Grade A, and why
srx-autovpn-full-tunnel 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 — 472 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SRX AutoVPN Full-Tunnel Backhaul
Overview
AutoVPN lets one hub gateway accept IPsec connections from any number of spokes with no per-spoke hub configuration. Full-tunnel backhaul is the design choice to send everything a spoke does not own locally up the tunnel to the hub, instead of the conventional split tunnel (only hub-LAN traffic in the tunnel, internet broken out locally, no spoke-to-spoke).
Core principle: if traffic is not local to a spoke, it goes to the hub. The hub then source-NATs internet-bound traffic out its WAN and hairpins spoke-to-spoke traffic back out the tunnel un-NAT'd. The motivation is centralized egress — all internet traffic can be inspected, filtered, and logged at one point (UTM/IDP on the hub).
The full-tunnel changes are confined to four things: the traffic selector scope, spoke routing, hub egress routing/NAT, and two added hub security policies. Everything else — IKE/IPsec parameters and the AutoVPN dynamic-gateway mechanics — is standard AutoVPN.
Attribution. The reference topology, full-tunnel backhaul approach, and the validated
set-format configuration this skill summarizes come from Jason Anderson's labsrx-autovpn-backhaul-public(https://github.com/anderson-jason573/srx-autovpn-backhaul-public), built and validated on four vSRX (Junos OS 23.2R2.21) plus a Cisco IOS-XE WAN transit router. Seereferences/source-design-summary.md.
Runtime intake
Before starting the workflow, inspect the request, supplied artifacts, and
available approved read-only evidence. If unresolved facts could materially
change safety, scope, correctness, confidence, or the requested output, read
references/runtime-intake.md.
For each unresolved material fact whose catalog condition is true, invoke Claude AskUserQuestion or Codex request_user_input before continuing or issuing an open-ended request.
Ask at most three single-select catalog questions per round. After each response, ask another round whenever any unresolved material catalog condition remains true; continue only when none remain. Do not repeat answered questions or show the full catalog.
Without a native tool, present each selected catalog question with its 2-3 labeled choices and a free-text Other path in concise plain text; do not substitute a generic checklist.
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.
- 12d ago First seen · 472 lines · 99 tokens per session scan A b7c1b6b6e62f
srx-autovpn-full-tunnel is a skill published in the GitHub repository fastrevmd-lab/fwskillsshare (9 stars, last pushed today), licensed MIT. It adds 99 tokens to every session and 7,559 once invoked, about $0.0005 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.
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…
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…
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.
radkit-remote-access
Cisco RADKit — cloud-relayed remote device access, CLI execution, SNMP polling, device inventory discovery, attribute inspection. Use when accessing remote network devices through a cloud relay, running CLI on air-gapped devices, polling SNMP metrics remotely, or discovering device inventory via RADKit.