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 lance0/nbox --skill ipam-readgit clone --depth 1 https://github.com/lance0/nboxWrote 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/lance0/nbox/ipam-read)<a href="https://agentmods.dev/skills/lance0/nbox/ipam-read"><img src="https://agentmods.dev/badge/skills/lance0/nbox/ipam-read/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/lance0/nbox/ipam-read"><img src="https://agentmods.dev/badge/skills/lance0/nbox/ipam-read.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 | $0.00082 | $0.01104 |
| Opus 5.5 | $0.00033 | $0.00442 |
| Sonnet 5.5 | $0.00016 | $0.00221 |
| Haiku 4.5 | $0.00008 | $0.00110 |
Grade A, and why
nbox-ipam-read 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
nbox IPAM reads
The IPAM read commands answer addressing and routing questions: where an
address lives, how full a prefix is, what's free, and how VRFs/route-targets
relate. All are read-only. For the flags of any one, run nbox <cmd> --help —
this skill is flag-free by design, describing what each command answers.
What each command answers
nbox ip <address>— one IP, enriched with its most-specific parent prefix (VRF-scoped), that prefix's VLAN, and the prefix'sscope/scope_type(site, location, region, …). Surfacesnat_inside/nat_outside(NetBox 4.6) when set. "Where does203.0.113.10live, and in what prefix/VLAN/site?"nbox prefix <cidr>— one prefix with its utilization, child prefixes, and contained IPs. "How full is10.0.0.0/24, and what's under it?"nbox next-ip <cidr>/nbox next-prefix <cidr>— a read-only preview of the next free address / child block. They reserve nothing (see the warning below).nbox vlan <vid|name>— one VLAN with its referencing prefixes, its ownscope/scope_type, and (when it belongs to a scoped VLAN group) the group'sgroup_scope/group_scope_type.nbox ip-range <start|id>— one IP range (the start address or id).nbox aggregate <cidr|id>— one aggregate (the top-level allocation a prefix tree sits under).nbox vrf <name|rd|id>— a VRF as a routing context: RD, tenant, enforce-unique, import/export route targets, counts, plus its prefix tree and scoped addresses.nbox route-target <name|id>— a route target (e.g.65000:100) plus the VRFs that import and export it.
next-ip / next-prefix reserve NOTHING
next-ip and next-prefix are read-only previews — they show what NetBox
would hand out next, but claim nothing and race with other clients. To
actually claim an address or block, use the reserve write commands, which POST
to NetBox's available-ips / available-prefixes endpoints under the dry-run /
confirm gate. See the IPAM allocate and
safe writes skills.
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 · 74 lines · 82 tokens per session scan A 788f05475635
nbox-ipam-read is a skill published in the GitHub repository lance0/nbox (13 stars, last pushed today), licensed Apache-2.0. It adds 82 tokens to every session and 1,104 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 2026-08-30.
Other skills, from other repositories
dcim-devices
NetBox DCIM device CRUD with foreign-key name resolution and bulk operations.
dcim-interfaces
NetBox DCIM interface CRUD with composite addressing, VLAN/LAG name resolution, and cable trace.
generic-resource-actions
Shared CRUD pattern for NetBox resources whose entire CLI surface is generated from the OpenAPI schema.
ipam-prefixes
NetBox IPAM prefix CRUD plus available-ips and available-prefixes allocation helpers.
raw
Authenticated passthrough to any NetBox /api/ path that does not yet have a typed nbx command.
config
Manage nbx NetBox URL, token, and named contexts in /.config/nbx/config.toml.