A cross-object search for NetBox, an inventory system for networks and data-centre equipment. It finds matching devices, IP addresses, sites, VLANs, and other records in one query.

Use it to find network objects by a name fragment, then narrow results by site, tenant, role, tag, status, or VRF before viewing details.

It removes the need to know the record type or exact reference before searching. Results are ranked and duplicates are removed.

nbox-search — Skill by lance0

Install

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.

agentmods

npx agentmods add skills/lance0/nbox/search

Any agent

npx skills add lance0/nbox --skill search

Clone the repo

git clone --depth 1 https://github.com/lance0/nbox

Made for: Claude Code, Codex.

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,078 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00079	$0.01078
Opus 5	$0.00039	$0.00539
Sonnet 5	$0.00016	$0.00216
Haiku 4.5	$0.00008	$0.00108

Measured 3d ago against content hash e44d74f66658, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nbox-search 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 3d 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.

skills/search/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

nbox search

nbox search <query> runs one parallel, full-text search across every object kind — devices, sites, racks, rack-groups, IPs, prefixes, VLANs, circuits, virtual-circuits, aggregates, ASNs, IP-ranges, tenants, contacts, providers, VMs, VM-types, clusters, VRFs, route-targets — and returns one ranked, deduped result set. It is the entry point when the exact kind or reference isn't known yet: search first, then feed a hit into a detail lookup.

nbox --no-tui search edge01 --json --envelope
nbox --no-tui search edge --status active --site DC1 -o csv --cols kind,display,url

For the exact flags, run nbox search --help. This skill is flag-free by design — it describes what each flag answers, not its semantics, so it can't drift as the CLI evolves.

What it answers

"What objects in NetBox match this string, and what kind is each?" Each hit carries a kind (e.g. device, ip_address, prefix), a display, and a url. Search is REST-canonical — NetBox's GraphQL has no full-text q, so a search = "graphql" profile preference transparently falls back to REST.

Narrowing the result set

One scope filter at a time. The scope flags — --site / --region / --site-group / --location / --tenant / --role / --tag / --status / --owner / --owner-group / --vrf — narrow the search per-endpoint. The geographic scopes (--site/--region/--site-group/--location) are mutually exclusive: NetBox's polymorphic prefix scope is a single type+id, so passing more than one geographic scope is a usage error (exit 2). --vrf is orthogonal and may combine with a geographic scope.
Endpoints that can't honor a filter are skipped, not errored — a VRF filter drops devices/sites/VLANs; a --site filter drops VRFs. The remaining kinds still return.
An unknown reference is a not-found error (exit 4), not a silent empty result — a typo'd --site or --vrf is caught.
--limit caps the result count; --cols selects the columns for -o csv output.

Read the full file on GitHub · 87 lines

Changes

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.

3d ago First seen · 87 lines · 79 tokens per session scan A e44d74f66658

Subscribe to this mod's changes

nbox-search is a skill published in the GitHub repository lance0/nbox (11 stars, last pushed 21d ago), licensed Apache-2.0. It adds 79 tokens to every session and 1,078 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 2026-08-30.

DevOps and cloud cli dcim ipam mcp netbox network-automation

nbox-search

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

nbox search

What it answers

Narrowing the result set

What this file has done since we first saw it

Other skills, from other repositories

dcim-interfaces

generic-resource-actions

dcim-devices

ipam-prefixes

raw

config