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 rsenna/rs-agent-plugin --skill opnsense-admingit clone --depth 1 https://github.com/rsenna/rs-agent-pluginWrote 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/rsenna/rs-agent-plugin/opnsense-admin)<a href="https://agentmods.dev/skills/rsenna/rs-agent-plugin/opnsense-admin"><img src="https://agentmods.dev/badge/skills/rsenna/rs-agent-plugin/opnsense-admin/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/rsenna/rs-agent-plugin/opnsense-admin"><img src="https://agentmods.dev/badge/skills/rsenna/rs-agent-plugin/opnsense-admin.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 | $0.00177 | $0.01424 |
| Opus 5.5 | $0.00071 | $0.00570 |
| Sonnet 5.5 | $0.00035 | $0.00285 |
| Haiku 4.5 | $0.00018 | $0.00142 |
Grade A, and why
opnsense-admin 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 1mo 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OPNsense administration via REST API
OPNsense exposes nearly its entire configuration surface over a REST API authenticated with a per-user API key/secret pair. This is almost always a better path than trying to script the web GUI or requesting shell access: it's scriptable, auditable (every call is attributable to the API user), and easy to scope down to read-only if that's all a task needs.
This is a live firewall for someone's network (often the only thing between their home and the internet). Move deliberately: read before you write, confirm before firing anything with a blast radius (VPN setup, firewall rule changes, HAProxy edits, firmware upgrades), and always leave yourself a way back — see the config-backup step below before anything nontrivial.
Getting access
You need a key/secret pair. If you don't have one yet, ask the user to
generate one (or point you to an existing scoped-down user) under
System → Access → Users → (user) → API keys → + in the GUI — this
downloads a .txt with key and secret once, non-recoverable after that.
For anything beyond read-only inspection, a dedicated user scoped to what's
actually needed beats reusing a full-admin account.
Don't assume port 443 — if the box also runs a reverse proxy (HAProxy is
common), the GUI/API often lives on 8443 or similar instead. Probe a few
ports if a plain https://<host>/ doesn't return a login page; see
references/lessons-learned.md for the one-liner.
Use scripts/opn-api.sh as the base for any calls:
export OPN_HOST=192.168.0.1 OPN_PORT=8443 OPN_KEY=... OPN_SECRET=...
./scripts/opn-api.sh /api/core/firmware/status
Before changing anything
- Pull a fresh config backup:
GET /api/core/backup/download/thisreturns the fullconfig.xml. Do this before any nontrivial change, and consider handing a copy to the user as an off-box safety net — some installs have no filesystem-level snapshot rollback available. - Read before you write. For any resource you're about to modify, call
its
get<Item>endpoint first (with no uuid, if it's a new item, to see the default template and every valid field/enum) so you know the real shape of what you're sending back. - If several changes are related (e.g. "hardening pass"), it's fine to do them one at a time and confirm each landed rather than batching blindly.
What ships with it
2 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.
- 1mo ago First seen · 101 lines · 177 tokens per session scan A dd59f1a2ab72
opnsense-admin is a skill published in the GitHub repository rsenna/rs-agent-plugin (2 stars, last pushed 2d ago), licensed MIT. It adds 177 tokens to every session and 1,424 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…