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-policygit 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-policy)<a href="https://agentmods.dev/skills/fastrevmd-lab/fwskillsshare/srx-policy"><img src="https://agentmods.dev/badge/skills/fastrevmd-lab/fwskillsshare/srx-policy/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-policy"><img src="https://agentmods.dev/badge/skills/fastrevmd-lab/fwskillsshare/srx-policy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 413 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
- medium Output Handling · line 118 Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.Fix: Set explicit limits on output length, generation count, and rate. Use max_tokens and truncation to prevent unbounded output.
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 | $0.00084 | $0.07285 |
| Opus 5 | $0.00042 | $0.03642 |
| Sonnet 5 | $0.00017 | $0.01457 |
| Haiku 4.5 | $0.00008 | $0.00728 |
Grade A, and why
srx-policy 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 9d 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 — 473 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SRX Security Policy
Overview
Use this skill for Juniper SRX security policy design on Junos 23.x and newer non-Branch SRX platforms. It focuses on the policy layer that decides whether traffic is permitted, denied, logged, counted, or passed into security services such as AppID/AppFW, NextGen Web Filtering (NGWF), Enhanced Web Filtering (EWF), SecIntel, and ATP-backed protections.
Enforced Global-Policy Output Contract
For greenfield, migration, and onboarding work, generated policy MUST use security policies global; express zones only as match from-zone and match to-zone fields inside each global policy. Do not preserve zone-pair structure merely because it appears in the input.
Use zone-to-zone output only after the caller explicitly opts into one of these exceptions and record the exception and affected rules in the result:
- existing-estate compatibility where structural change is outside scope;
- an isolated exception that is clearer and safer as a zone-pair policy;
- a customer standard or toolchain that requires zone-pair contexts.
Day-one SRX onboarding MUST detect set security policies from-zone ... to-zone ... contexts and rewrite them under security policies global by default. Preserve each source context's rule order, move its zones into match fields, verify semantic parity, and only remove or deactivate the legacy contexts with explicit approval and rollback protection. Read references/zone-pair-to-global-example.md for the complete detect-and-rewrite example.
Why global policy is the enforced generation target:
- Most vendor rulebases already behave like one ordered policy table with source zone, destination zone, source, destination, service/application, action, logging, and profiles as fields.
- Junos global policy lets a rule match one or more
from-zoneandto-zonevalues inside the policy itself. - A global policy table avoids duplicating the same logical rule across every zone pair.
- It pairs naturally with the global address book and application/application-set objects.
- It is easier to review, diff, reorder, and migrate than many separate zone-pair contexts.
- It keeps AppFW, UTM/web-filtering, SecIntel, and ATP attachment decisions close to the logical rule instead of scattering equivalent controls across zone pairs.
What ships with it
22 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.
- agents/openai.yaml 220 B
- references/ngwf-vs-ewf-research.md 3.5 KB
- references/runtime-intake.md 6.4 KB
- references/service-discovery.md 1.6 KB
- references/source-add-a-web-filtering-profile-j-web-for-srx-series-23-2.md 1.1 KB
- references/source-configure-application-firewalling-on-a-juniper-srx.md 973 B
- references/source-configuring-security-policies-junos-os.md 1.1 KB
- references/source-getting-started-with-atp-appliance-and-the-srx-series.md 977 B
- references/source-how-to-use-secintel.md 625 B
- references/source-index.md 1.7 KB
- references/source-jncip-sec-configuring-juniper-enhanced-web-filtering.md 912 B
- references/source-juniper-advanced-threat-prevention-datasheet.md 975 B
- references/source-juniper-secintel-datasheet.md 945 B
- references/source-juniper-srx-enhanced-web-filtering-configuration.md 930 B
- references/source-juniper-srx-policy-configuration.md 882 B
- references/source-secintel-feeds-overview-and-benefits.md 976 B
- references/source-security-global-policies.md 1.3 KB
- references/source-security-policy-applications-and-application-sets-junos-os.md 1022 B
- references/source-srx-configuring-next-generation-web-filtering-on-srx-devices.md 959 B
- references/source-understanding-application-firewall-policies.md 1.0 KB
- references/web-filtering-ngwf-ewf-patterns.md 5.2 KB
- references/zone-pair-to-global-example.md 7.3 KB
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.
- 9d ago First seen · 473 lines · 84 tokens per session scan A 37078c4cf9f0
srx-policy is a skill published in the GitHub repository fastrevmd-lab/fwskillsshare (8 stars, last pushed 11d ago), licensed MIT. It adds 84 tokens to every session and 7,285 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.
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.