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 servegit 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/serve)<a href="https://agentmods.dev/skills/lance0/nbox/serve"><img src="https://agentmods.dev/badge/skills/lance0/nbox/serve/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/serve"><img src="https://agentmods.dev/badge/skills/lance0/nbox/serve.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 | $0.00128 | $0.01813 |
| Opus 5.5 | $0.00051 | $0.00725 |
| Sonnet 5.5 | $0.00026 | $0.00363 |
| Haiku 4.5 | $0.00013 | $0.00181 |
Grade A, and why
nbox-serve 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 yesterday.
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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
nbox serve (MCP server, read-only by default)
nbox serve exposes nbox's read layer as an MCP server. The tools reuse the
CLI's query + view layer, so they return the same JSON view models as the
equivalent nbox <cmd>. Read-only is the default — the write tools are always
listed but reject at call time unless writes are explicitly opted in (see below).
For the flags, run nbox serve --help — this skill is flag-free by design.
Two transports
- stdio (default). An MCP host launches
nbox serveas a subprocess and speaks JSON-RPC over stdin/stdout. JSON-RPC on stdout, logs on stderr; URL/token come from the active profile (same--profile/--configflags). Read-only by default; enable local single-user MCP writes withnbox serve --local-writesor[serve].local_writes = true, using the active profile token. - HTTP —
nbox serve --http 127.0.0.1:8080, same tools mounted at/mcp, loopback only withOrigin/Hostvalidation and an optional static bearer. Add--oidc-issuer <URL>+--audience <VALUE>for OAuth 2.1 resource-server mode: inbound IdP JWTs are validated on/mcp(alg allowlist,iss/aud/exp,nbox:readscope), a routable bind is allowed (TLS terminates in front), and Protected Resource Metadata is served at/.well-known/oauth-protected-resource. HTTP/mcpalso carries an audit log and an opt-in per-caller rate limit. This is read-only Pattern 3: the last hop to NetBox still uses the one local profile token, so the audit log is accountability, not per-user RBAC — trusted single-team read-only only. - HTTP, multi-user —
nbox serve --http 0.0.0.0:8080 --netbox-token-passthrough(or[serve].netbox_token_passthrough = true) makes one process serve many users: each caller sends their own NetBox API token per request, inX-NetBox-Tokenor inAuthorizationwhen that header isn't already used by OIDC /--http-token, and nbox forwards it to NetBox. NetBox's permissions and changelog then apply to the real caller — no IdP, no[serve.vault]. Reads are cached per token so nobody sees another user's view; a request with no token is401, never downgraded to the server's token. Requires--http(stdio has no per-request headers); terminate TLS in front.
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.
- yesterday Changed · +12 lines 19c6f99ddfa6
- 1mo ago First seen · 100 lines · 128 tokens per session scan A 61956648d09d
nbox-serve is a skill published in the GitHub repository lance0/nbox (13 stars, last pushed today), licensed Apache-2.0. It adds 128 tokens to every session and 1,813 once invoked, about $0.0005 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
generic-resource-actions
Shared CRUD pattern for NetBox resources whose entire CLI surface is generated from the OpenAPI schema.
dcim-devices
NetBox DCIM device CRUD with foreign-key name resolution and bulk operations.
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.
dcim-interfaces
NetBox DCIM interface CRUD with composite addressing, VLAN/LAG name resolution, and cable trace.
config
Manage nbx NetBox URL, token, and named contexts in /.config/nbx/config.toml.